1
|
Dudas D, Saghand PG, Dilling TJ, Perez BA, Rosenberg SA, El Naqa I. Deep Learning-Guided Dosimetry for Mitigating Local Failure of Patients With Non-Small Cell Lung Cancer Receiving Stereotactic Body Radiation Therapy. Int J Radiat Oncol Biol Phys 2024; 119:990-1000. [PMID: 38056778 DOI: 10.1016/j.ijrobp.2023.11.059] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2023] [Revised: 11/14/2023] [Accepted: 11/25/2023] [Indexed: 12/08/2023]
Abstract
PURPOSE Non-small cell lung cancer (NSCLC) stereotactic body radiation therapy with 50 Gy/5 fractions is sometimes considered controversial, as the nominal biologically effective dose (BED) of 100 Gy is felt by some to be insufficient for long-term local control of some lesions. In this study, we analyzed such patients using explainable deep learning techniques and consequently proposed appropriate treatment planning criteria. These novel criteria could help planners achieve optimized treatment plans for maximal local control. METHODS AND MATERIALS A total of 535 patients treated with 50 Gy/5 fractions were used to develop a novel deep learning local response model. A multimodality approach, incorporating computed tomography images, 3-dimensional dose distribution, and patient demographics, combined with a discrete-time survival model, was applied to predict time to failure and the probability of local control. Subsequently, an integrated gradient-weighted class activation mapping method was used to identify the most significant dose-volume metrics predictive of local failure and their optimal cut-points. RESULTS The model was cross-validated, showing an acceptable performance (c-index: 0.72, 95% CI, 0.68-0.75); the testing c-index was 0.69. The model's spatial attention was concentrated mostly in the tumors' periphery (planning target volume [PTV] - internal gross target volume [IGTV]) region. Statistically significant dose-volume metrics in improved local control were BED Dnear-min ≥ 103.8 Gy in IGTV (hazard ratio [HR], 0.31; 95% CI, 015-0.63), V104 ≥ 98% in IGTV (HR, 0.30; 95% CI, 0.15-0.60), gEUD ≥ 103.8 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.50), and Dmean ≥ 104.5 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.51). CONCLUSIONS Deep learning-identified dose-volume metrics have shown significant prognostic power (log-rank, P = .003) and could be used as additional actionable criteria for treatment planning in NSCLC stereotactic body radiation therapy patients receiving 50 Gy in 5 fractions. Although our data do not confirm or refute that a significantly higher BED for the prescription dose is necessary for tumor control in NSCLC, it might be clinically effective to escalate the nominal prescribed dose from BED 100 to 105 Gy.
Collapse
Affiliation(s)
| | | | - Thomas J Dilling
- Radiation Oncology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, Florida
| | - Bradford A Perez
- Radiation Oncology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, Florida
| | - Stephen A Rosenberg
- Radiation Oncology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, Florida
| | - Issam El Naqa
- Departments of Machine Learning; Radiation Oncology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, Florida
| |
Collapse
|
2
|
Iqbal MS, Belal Bin Heyat M, Parveen S, Ammar Bin Hayat M, Roshanzamir M, Alizadehsani R, Akhtar F, Sayeed E, Hussain S, Hussein HS, Sawan M. Progress and trends in neurological disorders research based on deep learning. Comput Med Imaging Graph 2024; 116:102400. [PMID: 38851079 DOI: 10.1016/j.compmedimag.2024.102400] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2024] [Revised: 05/07/2024] [Accepted: 05/13/2024] [Indexed: 06/10/2024]
Abstract
In recent years, deep learning (DL) has emerged as a powerful tool in clinical imaging, offering unprecedented opportunities for the diagnosis and treatment of neurological disorders (NDs). This comprehensive review explores the multifaceted role of DL techniques in leveraging vast datasets to advance our understanding of NDs and improve clinical outcomes. Beginning with a systematic literature review, we delve into the utilization of DL, particularly focusing on multimodal neuroimaging data analysis-a domain that has witnessed rapid progress and garnered significant scientific interest. Our study categorizes and critically analyses numerous DL models, including Convolutional Neural Networks (CNNs), LSTM-CNN, GAN, and VGG, to understand their performance across different types of Neurology Diseases. Through particular analysis, we identify key benchmarks and datasets utilized in training and testing DL models, shedding light on the challenges and opportunities in clinical neuroimaging research. Moreover, we discuss the effectiveness of DL in real-world clinical scenarios, emphasizing its potential to revolutionize ND diagnosis and therapy. By synthesizing existing literature and describing future directions, this review not only provides insights into the current state of DL applications in ND analysis but also covers the way for the development of more efficient and accessible DL techniques. Finally, our findings underscore the transformative impact of DL in reshaping the landscape of clinical neuroimaging, offering hope for enhanced patient care and groundbreaking discoveries in the field of neurology. This review paper is beneficial for neuropathologists and new researchers in this field.
Collapse
Affiliation(s)
- Muhammad Shahid Iqbal
- Department of Computer Science and Information Technology, Women University of Azad Jammu & Kashmir, Bagh, Pakistan.
| | - Md Belal Bin Heyat
- CenBRAIN Neurotech Center of Excellence, School of Engineering, Westlake University, Hangzhou, Zhejiang, China.
| | - Saba Parveen
- College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China.
| | | | - Mohamad Roshanzamir
- Department of Computer Engineering, Faculty of Engineering, Fasa University, Fasa, Iran.
| | - Roohallah Alizadehsani
- Institute for Intelligent Systems Research and Innovation, Deakin University, VIC 3216, Australia.
| | - Faijan Akhtar
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China.
| | - Eram Sayeed
- Kisan Inter College, Dhaurahara, Kushinagar, India.
| | - Sadiq Hussain
- Department of Examination, Dibrugarh University, Assam 786004, India.
| | - Hany S Hussein
- Electrical Engineering Department, Faculty of Engineering, King Khalid University, Abha 61411, Saudi Arabia; Electrical Engineering Department, Faculty of Engineering, Aswan University, Aswan 81528, Egypt.
| | - Mohamad Sawan
- CenBRAIN Neurotech Center of Excellence, School of Engineering, Westlake University, Hangzhou, Zhejiang, China.
| |
Collapse
|
3
|
Chattopadhyay T, Joshy NA, Ozarkar SS, Buwa KS, Feng Y, Laltoo E, Thomopoulos SI, Villalon-Reina JE, Joshi H, Venkatasubramanian G, John JP, Thompson PM. Brain Age Analysis and Dementia Classification using Convolutional Neural Networks trained on Diffusion MRI: Tests in Indian and North American Cohorts. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.02.04.578829. [PMID: 38370641 PMCID: PMC10871286 DOI: 10.1101/2024.02.04.578829] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/20/2024]
Abstract
Deep learning models based on convolutional neural networks (CNNs) have been used to classify Alzheimer's disease or infer dementia severity from T1-weighted brain MRI scans. Here, we examine the value of adding diffusion-weighted MRI (dMRI) as an input to these models. Much research in this area focuses on specific datasets such as the Alzheimer's Disease Neuroimaging Initiative (ADNI), which assesses people of North American, largely European ancestry, so we examine how models trained on ADNI, generalize to a new population dataset from India (the NIMHANS cohort). We first benchmark our models by predicting 'brain age' - the task of predicting a person's chronological age from their MRI scan and proceed to AD classification. We also evaluate the benefit of using a 3D CycleGAN approach to harmonize the imaging datasets before training the CNN models. Our experiments show that classification performance improves after harmonization in most cases, as well as better performance for dMRI as input.
Collapse
|
4
|
Choukali MA, Amirani MC, Valizadeh M, Abbasi A, Komeili M. Pseudo-class part prototype networks for interpretable breast cancer classification. Sci Rep 2024; 14:10341. [PMID: 38710757 DOI: 10.1038/s41598-024-60743-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2023] [Accepted: 04/26/2024] [Indexed: 05/08/2024] Open
Abstract
Interpretability in machine learning has become increasingly important as machine learning is being used in more and more applications, including those with high-stakes consequences such as healthcare where Interpretability has been regarded as a key to the successful adoption of machine learning models. However, using confounding/irrelevant information in making predictions by deep learning models, even the interpretable ones, poses critical challenges to their clinical acceptance. That has recently drawn researchers' attention to issues beyond the mere interpretation of deep learning models. In this paper, we first investigate application of an inherently interpretable prototype-based architecture, known as ProtoPNet, for breast cancer classification in digital pathology and highlight its shortcomings in this application. Then, we propose a new method that uses more medically relevant information and makes more accurate and interpretable predictions. Our method leverages the clustering concept and implicitly increases the number of classes in the training dataset. The proposed method learns more relevant prototypes without any pixel-level annotated data. To have a more holistic assessment, in addition to classification accuracy, we define a new metric for assessing the degree of interpretability based on the comments of a group of skilled pathologists. Experimental results on the BreakHis dataset show that the proposed method effectively improves the classification accuracy and interpretability by respectively 8 % and 18 % . Therefore, the proposed method can be seen as a step toward implementing interpretable deep learning models for the detection of breast cancer using histopathology images.
Collapse
Affiliation(s)
| | - Mehdi Chehel Amirani
- Department of Electrical and Computer Engineering, Urmia University, Urmia, Iran
| | - Morteza Valizadeh
- Department of Electrical and Computer Engineering, Urmia University, Urmia, Iran.
| | - Ata Abbasi
- Cellular and Molecular Research Center, Cellular and Molecular Medicine Research Institute, Urmia University of Medical Sciences, Urmia, Iran
- Department of Pathology, Faculty of Medicine, Urmia University of medical sciences, Urmia, Iran
| | - Majid Komeili
- School of Computer Science, Carleton University, Ottawa, Canada
| |
Collapse
|
5
|
Chaudhari NN, Imms PE, Chowdhury NF, Gatz M, Trumble BC, Mack WJ, Law EM, Sutherland ML, Sutherland JD, Rowan CJ, Wann LS, Allam AH, Thompson RC, Michalik DE, Miyamoto M, Lombardi G, Cummings DK, Seabright E, Alami S, Garcia AR, Rodriguez DE, Gutierrez RQ, Copajira AJ, Hooper PL, Buetow KH, Stieglitz J, Gurven MD, Thomas GS, Kaplan HS, Finch CE, Irimia A. Increases in regional brain volume across two native South American male populations. GeroScience 2024:10.1007/s11357-024-01168-2. [PMID: 38683289 DOI: 10.1007/s11357-024-01168-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2024] [Accepted: 04/15/2024] [Indexed: 05/01/2024] Open
Abstract
Industrialized environments, despite benefits such as higher levels of formal education and lower rates of infections, can also have pernicious impacts upon brain atrophy. Partly for this reason, comparing age-related brain volume trajectories between industrialized and non-industrialized populations can help to suggest lifestyle correlates of brain health. The Tsimane, indigenous to the Bolivian Amazon, derive their subsistence from foraging and horticulture and are physically active. The Moseten, a mixed-ethnicity farming population, are physically active but less than the Tsimane. Within both populations (N = 1024; age range = 46-83), we calculated regional brain volumes from computed tomography and compared their cross-sectional trends with age to those of UK Biobank (UKBB) participants (N = 19,973; same age range). Surprisingly among Tsimane and Moseten (T/M) males, some parietal and occipital structures mediating visuospatial abilities exhibit small but significant increases in regional volume with age. UKBB males exhibit a steeper negative trend of regional volume with age in frontal and temporal structures compared to T/M males. However, T/M females exhibit significantly steeper rates of brain volume decrease with age compared to UKBB females, particularly for some cerebro-cortical structures (e.g., left subparietal cortex). Across the three populations, observed trends exhibit no interhemispheric asymmetry. In conclusion, the age-related rate of regional brain volume change may differ by lifestyle and sex. The lack of brain volume reduction with age is not known to exist in other human population, highlighting the putative role of lifestyle in constraining regional brain atrophy and promoting elements of non-industrialized lifestyle like higher physical activity.
Collapse
Affiliation(s)
- Nikhil N Chaudhari
- Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, CA, USA
| | - Phoebe E Imms
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, CA, USA
| | - Nahian F Chowdhury
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, CA, USA
| | - Margaret Gatz
- Center for Economic and Social Research, Dana and David Dornsife College of Letters, Arts and Sciences, University of Southern California, Los Angeles, CA, USA
| | - Benjamin C Trumble
- Center for Evolution & Medicine, School of Human Evolution and Social Change, School of Life Sciences, Arizona State University, Tempe, AZ, USA
| | - Wendy J Mack
- Department of Population and Public Health Sciences, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA
| | - E Meng Law
- iBRAIN Research Laboratory, Departments of Neuroscience, Computer Systems and Electrical Engineering, Monash University, Melbourne, VIC, Australia
- Department of Radiology, The Alfred Health Hospital, Melbourne, VIC, Australia
- Department of Neurology, Keck School of Medicine of USC, University of Southern California, Los Angeles, CA, USA
| | | | | | - Christopher J Rowan
- Renown Institute for Heart and Vascular Health, Reno, NV, USA
- School of Medicine, University of Nevada, Reno, NV, USA
| | - L Samuel Wann
- Division of Cardiology, University of New Mexico, Albuquerque, NM, USA
| | - Adel H Allam
- Department of Cardiology, School of Medicine, Al-Azhar University, Al Mikhaym Al Daem, Cairo, Egypt
| | - Randall C Thompson
- Saint Luke's Mid America Heart Institute, University of Missouri, Kansas City, MO, USA
| | - David E Michalik
- Department of Pediatrics, School of Medicine, University of California, Irvine, Orange, CA, USA
- MemorialCare Miller Children's & Women's Hospital, Long Beach Medical Center, Long Beach, CA, USA
| | - Michael Miyamoto
- Division of Cardiology, Mission Heritage Medical Group, Providence Health, Mission Viejo, CA, USA
| | | | - Daniel K Cummings
- Department of Anthropology, University of New Mexico, Albuquerque, NM, USA
- Economic Science Institute, Argyros School of Business and Economics, Chapman University, Orange, CA, USA
| | - Edmond Seabright
- Department of Anthropology, University of New Mexico, Albuquerque, NM, USA
| | - Sarah Alami
- Department of Anthropology, University of New Mexico, Albuquerque, NM, USA
| | - Angela R Garcia
- Center for Evolution & Medicine, School of Human Evolution and Social Change, School of Life Sciences, Arizona State University, Tempe, AZ, USA
| | - Daniel E Rodriguez
- Institute of Biomedical Research, San Simon University, Cochabamba, Bolivia
| | | | | | - Paul L Hooper
- Department of Anthropology, University of New Mexico, Albuquerque, NM, USA
| | - Kenneth H Buetow
- Center for Evolution & Medicine, School of Human Evolution and Social Change, School of Life Sciences, Arizona State University, Tempe, AZ, USA
| | - Jonathan Stieglitz
- Institute for Advanced Study in Toulouse, Toulouse 1 Capitol University, Toulouse, France
| | - Michael D Gurven
- Department of Anthropology, University of California, Santa Barbara, USA
| | - Gregory S Thomas
- MemorialCare Health Systems, Fountain Valley, CA, USA
- Division of Cardiology, University of California, Irvine, Orange, CA, USA
| | - Hillard S Kaplan
- Economic Science Institute, Argyros School of Business and Economics, Chapman University, Orange, CA, USA
| | - Caleb E Finch
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, CA, USA
- Departments of Biological Sciences, Anthropology and Psychology, Dana and David Dornsife College of Letters, Arts and Sciences, University of Southern California, Los Angeles, CA, USA
| | - Andrei Irimia
- Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA.
- Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, CA, USA.
- Department of Quantitative and Computational Biology, Dana and David Dornsife College of Letters, Arts and Sciences, University of Southern California, Los Angeles, CA, USA.
| |
Collapse
|
6
|
Cogill S, Nallamshetty S, Fullenkamp N, Heberer K, Lynch J, Lee KM, Aslan M, Shih MC, Lee JS. Predicting clinical outcomes of SARS-CoV-2 infection during the Omicron wave using machine learning. PLoS One 2024; 19:e0290221. [PMID: 38662748 PMCID: PMC11045098 DOI: 10.1371/journal.pone.0290221] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2023] [Accepted: 02/20/2024] [Indexed: 04/28/2024] Open
Abstract
The Omicron SARS-CoV-2 variant continues to strain healthcare systems. Developing tools that facilitate the identification of patients at highest risk of adverse outcomes is a priority. The study objectives are to develop population-scale predictive models that: 1) identify predictors of adverse outcomes with Omicron surge SARS-CoV-2 infections, and 2) predict the impact of prioritized vaccination of high-risk groups for said outcome. We prepared a retrospective longitudinal observational study of a national cohort of 172,814 patients in the U.S. Veteran Health Administration who tested positive for SARS-CoV-2 from January 15 to August 15, 2022. We utilized sociodemographic characteristics, comorbidities, and vaccination status, at time of testing positive for SARS-CoV-2 to predict hospitalization, escalation of care (high-flow oxygen, mechanical ventilation, vasopressor use, dialysis, or extracorporeal membrane oxygenation), and death within 30 days. Machine learning models demonstrated that advanced age, high comorbidity burden, lower body mass index, unvaccinated status, and oral anticoagulant use were the important predictors of hospitalization and escalation of care. Similar factors predicted death. However, anticoagulant use did not predict mortality risk. The all-cause death model showed the highest discrimination (Area Under the Curve (AUC) = 0.903, 95% Confidence Interval (CI): 0.895, 0.911) followed by hospitalization (AUC = 0.822, CI: 0.818, 0.826), then escalation of care (AUC = 0.793, CI: 0.784, 0.805). Assuming a vaccine efficacy range of 70.8 to 78.7%, our simulations projected that targeted prevention in the highest risk group may have reduced 30-day hospitalization and death in more than 2 of 5 unvaccinated patients.
Collapse
Affiliation(s)
- Steven Cogill
- VA Palo Alto Cooperative Studies Program Coordinating Center, Palo Alto, CA, United States of America
- Big Data-Scientist Training Enhancement Program at VA Palo Alto Health Care System, Palo Alto, CA, United States of America
| | - Shriram Nallamshetty
- VA Palo Alto Cooperative Studies Program Coordinating Center, Palo Alto, CA, United States of America
| | - Natalie Fullenkamp
- VA Palo Alto Cooperative Studies Program Coordinating Center, Palo Alto, CA, United States of America
| | - Kent Heberer
- VA Palo Alto Cooperative Studies Program Coordinating Center, Palo Alto, CA, United States of America
- Big Data-Scientist Training Enhancement Program at VA Palo Alto Health Care System, Palo Alto, CA, United States of America
| | - Julie Lynch
- VA Informatics and Computing Infrastructure, VA Salt Lake City Health Care System, Salt Lake City, UT, United States of America
- Division of Epidemiology, Department of Internal Medicine, University of Utah School of Medicine, Salt Lake City, UT, United States of America
| | - Kyung Min Lee
- VA Informatics and Computing Infrastructure, VA Salt Lake City Health Care System, Salt Lake City, UT, United States of America
| | - Mihaela Aslan
- VA Clinical Epidemiology Research Center (CERC), VA Connecticut Healthcare System, West Haven, CT, United States of America
- Department of Medicine, Yale University School of Medicine, New Haven, CT, United States of America
| | - Mei-Chiung Shih
- VA Palo Alto Cooperative Studies Program Coordinating Center, Palo Alto, CA, United States of America
- Department of Biomedical Data Science, Stanford University School of Medicine, Stanford, CA, United States of America
| | - Jennifer S. Lee
- VA Palo Alto Cooperative Studies Program Coordinating Center, Palo Alto, CA, United States of America
- Big Data-Scientist Training Enhancement Program at VA Palo Alto Health Care System, Palo Alto, CA, United States of America
- Division of Endocrinology, Department of Medicine, Gerontology, and Metabolism, and by Courtesy, of Epidemiology and Population Health, Stanford University School of Medicine, Stanford, CA, United States of America
| |
Collapse
|
7
|
Chang C, Shi W, Wang Y, Zhang Z, Huang X, Jiao Y. The path from task-specific to general purpose artificial intelligence for medical diagnostics: A bibliometric analysis. Comput Biol Med 2024; 172:108258. [PMID: 38467093 DOI: 10.1016/j.compbiomed.2024.108258] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2023] [Revised: 02/08/2024] [Accepted: 03/06/2024] [Indexed: 03/13/2024]
Abstract
Artificial intelligence (AI) has revolutionized many fields, and its potential in healthcare has been increasingly recognized. Based on diverse data sources such as imaging, laboratory tests, medical records, and electrophysiological data, diagnostic AI has witnessed rapid development in recent years. A comprehensive understanding of the development status, contributing factors, and their relationships in the application of AI to medical diagnostics is essential to further promote its use in clinical practice. In this study, we conducted a bibliometric analysis to explore the evolution of task-specific to general-purpose AI for medical diagnostics. We used the Web of Science database to search for relevant articles published between 2010 and 2023, and applied VOSviewer, the R package Bibliometrix, and CiteSpace to analyze collaborative networks and keywords. Our analysis revealed that the field of AI in medical diagnostics has experienced rapid growth in recent years, with a focus on tasks such as image analysis, disease prediction, and decision support. Collaborative networks were observed among researchers and institutions, indicating a trend of global cooperation in this field. Additionally, we identified several key factors contributing to the development of AI in medical diagnostics, including data quality, algorithm design, and computational power. Challenges to progress in the field include model explainability, robustness, and equality, which will require multi-stakeholder, interdisciplinary collaboration to tackle. Our study provides a holistic understanding of the path from task-specific, mono-modal AI toward general-purpose, multimodal AI for medical diagnostics. With the continuous improvement of AI technology and the accumulation of medical data, we believe that AI will play a greater role in medical diagnostics in the future.
Collapse
Affiliation(s)
- Chuheng Chang
- Department of General Practice (General Internal Medicine), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; 4+4 Medical Doctor Program, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
| | - Wen Shi
- Department of Gastroenterology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
| | - Youyang Wang
- Department of General Practice (General Internal Medicine), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
| | - Zhan Zhang
- Department of Computer Science and Technology, Tsinghua University, Beijing, China.
| | - Xiaoming Huang
- Department of General Practice (General Internal Medicine), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
| | - Yang Jiao
- Department of General Practice (General Internal Medicine), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
| |
Collapse
|
8
|
Kim C, Gadgil SU, DeGrave AJ, Omiye JA, Cai ZR, Daneshjou R, Lee SI. Transparent medical image AI via an image-text foundation model grounded in medical literature. Nat Med 2024; 30:1154-1165. [PMID: 38627560 DOI: 10.1038/s41591-024-02887-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/09/2023] [Accepted: 02/27/2024] [Indexed: 04/21/2024]
Abstract
Building trustworthy and transparent image-based medical artificial intelligence (AI) systems requires the ability to interrogate data and models at all stages of the development pipeline, from training models to post-deployment monitoring. Ideally, the data and associated AI systems could be described using terms already familiar to physicians, but this requires medical datasets densely annotated with semantically meaningful concepts. In the present study, we present a foundation model approach, named MONET (medical concept retriever), which learns how to connect medical images with text and densely scores images on concept presence to enable important tasks in medical AI development and deployment such as data auditing, model auditing and model interpretation. Dermatology provides a demanding use case for the versatility of MONET, due to the heterogeneity in diseases, skin tones and imaging modalities. We trained MONET based on 105,550 dermatological images paired with natural language descriptions from a large collection of medical literature. MONET can accurately annotate concepts across dermatology images as verified by board-certified dermatologists, competitively with supervised models built on previously concept-annotated dermatology datasets of clinical images. We demonstrate how MONET enables AI transparency across the entire AI system development pipeline, from building inherently interpretable models to dataset and model auditing, including a case study dissecting the results of an AI clinical trial.
Collapse
Affiliation(s)
- Chanwoo Kim
- Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA, USA
| | - Soham U Gadgil
- Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA, USA
| | - Alex J DeGrave
- Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA, USA
- Medical Scientist Training Program, University of Washington, Seattle, WA, USA
| | - Jesutofunmi A Omiye
- Department of Dermatology, Stanford School of Medicine, Stanford, CA, USA
- Department of Biomedical Data Science, Stanford School of Medicine, Stanford, CA, USA
| | - Zhuo Ran Cai
- Program for Clinical Research and Technology, Stanford University, Stanford, CA, USA
| | - Roxana Daneshjou
- Department of Dermatology, Stanford School of Medicine, Stanford, CA, USA.
- Department of Biomedical Data Science, Stanford School of Medicine, Stanford, CA, USA.
| | - Su-In Lee
- Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA, USA.
| |
Collapse
|
9
|
Chén OY, Vũ DT, Diaz CS, Bodelet JS, Phan H, Allali G, Nguyen VD, Cao H, He X, Müller Y, Zhi B, Shou H, Zhang H, He W, Wang X, Munafò M, Trung NL, Nagels G, Ryvlin P, Pantaleo G. Residual Partial Least Squares Learning: Brain Cortical Thickness Simultaneously Predicts Eight Non-pairwise-correlated Behavioural and Disease Outcomes in Alzheimer's Disease. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.03.11.584383. [PMID: 38559263 PMCID: PMC10979899 DOI: 10.1101/2024.03.11.584383] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/04/2024]
Abstract
Alzheimer's Disease (AD) is the leading cause of dementia. It results in cortical thickness changes and is associated with a decline in cognition and behaviour. Such decline affects multiple important day-to-day functions, including memory, language, orientation, judgment and problem-solving. Recent research has made important progress in identifying brain regions associated with single outcomes, such as individual AD status and general cognitive decline. The complex projection from multiple brain areas to multiple AD outcomes, however, remains poorly understood. This makes the assessment and especially the prediction of multiple AD outcomes - each of which may unveil an integral yet different aspect of the disease - challenging, particularly when some are not strongly correlated. Here, uniting residual learning, partial least squares (PLS), and predictive modelling, we develop an explainable, generalisable, and reproducible method called the Residual Partial Least Squares Learning (the re-PLS Learning) to (1) chart the pathways between large-scale multivariate brain cortical thickness data (inputs) and multivariate disease and behaviour data (outcomes); (2) simultaneously predict multiple, non-pairwise-correlated outcomes; (3) control for confounding variables (e.g., age and gender) affecting both inputs and outcomes and the pathways in-between; (4) perform longitudinal AD disease status classification and disease severity prediction. We evaluate the performance of the proposed method against a variety of alternatives on data from AD patients, subjects with mild cognitive impairment (MCI), and cognitively normal individuals ( n = 1,196 ) from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Our results unveil pockets of brain areas in the temporal, frontal, sensorimotor, and cingulate areas whose cortical thickness may be respectively associated with declines in different cognitive and behavioural subdomains in AD. Finally, we characterise re-PLS' geometric interpretation and mathematical support for delivering meaningful neurobiological insights and provide an open software package (re-PLS) available at https://github.com/thanhvd18/rePLS.
Collapse
Affiliation(s)
- Oliver Y Chén
- Département Médecine de Laboratoire et Pathologie, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
- Faculté de Biologie et de Médecine, Université de Lausanne (UNIL), Lausanne, Switzerland
| | - Duy Thanh Vũ
- Département Médecine de Laboratoire et Pathologie, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
- The Advanced Institute of Engineering and Technology, Vietnam National University, Hanoi, Vietnam
| | - Christelle Schneuwly Diaz
- Département Médecine de Laboratoire et Pathologie, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
- Faculté de Biologie et de Médecine, Université de Lausanne (UNIL), Lausanne, Switzerland
| | - Julien S Bodelet
- Département Médecine de Laboratoire et Pathologie, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
| | - Huy Phan
- Department of Electrical Engineering, KU Leuven, Leuven, Belgium
| | - Gilles Allali
- Centre Leenaards de la Mémoire, CHUV, Lausanne, Switzerland
| | - Viet-Dung Nguyen
- Lab-STICC, École Nationale Supérieure de Techniques Avancées de Bretagne, Bretagne, France
- The Advanced Institute of Engineering and Technology, Vietnam National University, Hanoi, Vietnam
| | - Hengyi Cao
- Center for Psychiatric Neuroscience, Feinstein Institutes for Medical Research, Manhasset, NY, USA
- Division of Psychiatry Research, Zucker Hillside Hospital, Glen Oaks, NY, USA
| | - Xingru He
- School of Public Health, He University, Shengyang, China
| | - Yannick Müller
- Département Médecine de Laboratoire et Pathologie, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
| | - Bangdong Zhi
- Innovation and Healthcare Group, University of Bristol, Bristol, UK
| | - Haochang Shou
- Department of Biostatistics, University of Pennsylvania, Philadelphia, PA, USA
| | - Haoyu Zhang
- Division of Cancer Epidemiology and Genetics, National Institutes of Health, Bethesda, MD, USA
| | - Wei He
- School of Public Health, He University, Shengyang, China
| | - Xiaojun Wang
- Innovation and Healthcare Group, University of Bristol, Bristol, UK
| | - Marcus Munafò
- School of Psychological Science, University of Bristol, Bristol, UK
| | - Nguyen Linh Trung
- The Advanced Institute of Engineering and Technology, Vietnam National University, Hanoi, Vietnam
| | - Guy Nagels
- Department of Neurology, Universitair Ziekenhuis Brussel, Jette, Belgium
- Institute of Biomedical Engineering, University of Oxford, Oxford, UK
| | - Philippe Ryvlin
- Département des Neurosciences Cliniques, CHUV, Lausanne, Switzerland
| | - Giuseppe Pantaleo
- Département Médecine de Laboratoire et Pathologie, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
| |
Collapse
|
10
|
Zhao L, Fong TC, Bell MAL. Detection of COVID-19 features in lung ultrasound images using deep neural networks. COMMUNICATIONS MEDICINE 2024; 4:41. [PMID: 38467808 PMCID: PMC10928066 DOI: 10.1038/s43856-024-00463-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2023] [Accepted: 02/16/2024] [Indexed: 03/13/2024] Open
Abstract
BACKGROUND Deep neural networks (DNNs) to detect COVID-19 features in lung ultrasound B-mode images have primarily relied on either in vivo or simulated images as training data. However, in vivo images suffer from limited access to required manual labeling of thousands of training image examples, and simulated images can suffer from poor generalizability to in vivo images due to domain differences. We address these limitations and identify the best training strategy. METHODS We investigated in vivo COVID-19 feature detection with DNNs trained on our carefully simulated datasets (40,000 images), publicly available in vivo datasets (174 images), in vivo datasets curated by our team (958 images), and a combination of simulated and internal or external in vivo datasets. Seven DNN training strategies were tested on in vivo B-mode images from COVID-19 patients. RESULTS Here, we show that Dice similarity coefficients (DSCs) between ground truth and DNN predictions are maximized when simulated data are mixed with external in vivo data and tested on internal in vivo data (i.e., 0.482 ± 0.211), compared with using only simulated B-mode image training data (i.e., 0.464 ± 0.230) or only external in vivo B-mode training data (i.e., 0.407 ± 0.177). Additional maximization is achieved when a separate subset of the internal in vivo B-mode images are included in the training dataset, with the greatest maximization of DSC (and minimization of required training time, or epochs) obtained after mixing simulated data with internal and external in vivo data during training, then testing on the held-out subset of the internal in vivo dataset (i.e., 0.735 ± 0.187). CONCLUSIONS DNNs trained with simulated and in vivo data are promising alternatives to training with only real or only simulated data when segmenting in vivo COVID-19 lung ultrasound features.
Collapse
Affiliation(s)
- Lingyi Zhao
- Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Tiffany Clair Fong
- Department of Emergency Medicine, Johns Hopkins Medicine, Baltimore, MD, USA
| | - Muyinatu A Lediju Bell
- Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA.
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA.
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA.
| |
Collapse
|
11
|
Elkadi OA, Abinzano F, Nippolainen E, González OB, Levato R, Malda J, Afara IO. Non-neotissue constituents as underestimated confounders in the assessment of tissue engineered constructs by near-infrared spectroscopy. Mater Today Bio 2024; 24:100879. [PMID: 38130429 PMCID: PMC10733684 DOI: 10.1016/j.mtbio.2023.100879] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2023] [Revised: 11/15/2023] [Accepted: 11/22/2023] [Indexed: 12/23/2023] Open
Abstract
Non-destructive assessments are required for the quality control of tissue-engineered constructs and the optimization of the tissue culture process. Near-infrared (NIR) spectroscopy coupled with machine learning (ML) provides a promising approach for such assessment. However, due to its nonspecific nature, each spectrum incorporates information on both neotissue and non-neotissue constituents of the construct; the effect of these constituents on the NIR-based assessments of tissue-engineered constructs has been overlooked in previous studies. This study investigates the effect of scaffolds, growth factors, and buffers on NIR-based assessments of tissue-engineered constructs. To determine if these non-neotissue constituents have a measurable effect on the NIR spectra of the constructs that can introduce bias in their assessment, nine ML algorithms were evaluated in classifying the NIR spectra of engineered cartilage according to the scaffold used to prepare the constructs, the growth factors added to the culture media, and the buffers used for storing the constructs. The effect of controlling for these constituents was also evaluated using controlled and uncontrolled NIR-based ML models for predicting tissue maturity as an example of neotissue-related properties of interest. Samples used in this study were prepared using norbornene-modified hyaluronic acid scaffolds with or without the conjugation of an N-cadherin mimetic peptide. Selected samples were supplemented with transforming growth factor-beta1 or bone morphogenetic protein-9 growth factor. Some samples were frozen in cell lysis buffer, while the remaining samples were frozen in PBS until required for NIR analysis. The ML models for classifying the spectra of the constructs according to the four constituents exhibited high to fair performances, with F1 scores ranging from 0.9 to 0.52. Moreover, controlling for the four constituents significantly improved the performance of the models for predicting tissue maturity, with improvement in F1 scores ranging from 0.09 to 0.77. In conclusion, non-neotissue constituents have measurable effects on the NIR spectra of tissue-engineered constructs that can be detected by ML algorithms and introduce bias in the assessment of the constructs by NIR spectroscopy. Therefore, controlling for these constituents is necessary for reliable NIR-based assessments of tissue-engineered constructs.
Collapse
Affiliation(s)
- Omar Anwar Elkadi
- Department of Technical Physics, University of Eastern Finland, Kuopio, Finland
| | - Florencia Abinzano
- Department of Orthopedics, University Medical Center Utrecht, Utrecht University, 3584 CX, Utrecht, the Netherlands
| | - Ervin Nippolainen
- Department of Technical Physics, University of Eastern Finland, Kuopio, Finland
| | - Ona Bach González
- Department of Orthopedics, University Medical Center Utrecht, Utrecht University, 3584 CX, Utrecht, the Netherlands
| | - Riccardo Levato
- Department of Orthopedics, University Medical Center Utrecht, Utrecht University, 3584 CX, Utrecht, the Netherlands
- Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, 3584 CT, Utrecht, the Netherlands
| | - Jos Malda
- Department of Orthopedics, University Medical Center Utrecht, Utrecht University, 3584 CX, Utrecht, the Netherlands
- Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, 3584 CT, Utrecht, the Netherlands
| | - Isaac O. Afara
- Department of Technical Physics, University of Eastern Finland, Kuopio, Finland
| |
Collapse
|
12
|
Quinn TP, Hess JL, Marshe VS, Barnett MM, Hauschild AC, Maciukiewicz M, Elsheikh SSM, Men X, Schwarz E, Trakadis YJ, Breen MS, Barnett EJ, Zhang-James Y, Ahsen ME, Cao H, Chen J, Hou J, Salekin A, Lin PI, Nicodemus KK, Meyer-Lindenberg A, Bichindaritz I, Faraone SV, Cairns MJ, Pandey G, Müller DJ, Glatt SJ. A primer on the use of machine learning to distil knowledge from data in biological psychiatry. Mol Psychiatry 2024; 29:387-401. [PMID: 38177352 DOI: 10.1038/s41380-023-02334-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/12/2022] [Revised: 09/21/2023] [Accepted: 11/17/2023] [Indexed: 01/06/2024]
Abstract
Applications of machine learning in the biomedical sciences are growing rapidly. This growth has been spurred by diverse cross-institutional and interdisciplinary collaborations, public availability of large datasets, an increase in the accessibility of analytic routines, and the availability of powerful computing resources. With this increased access and exposure to machine learning comes a responsibility for education and a deeper understanding of its bases and bounds, borne equally by data scientists seeking to ply their analytic wares in medical research and by biomedical scientists seeking to harness such methods to glean knowledge from data. This article provides an accessible and critical review of machine learning for a biomedically informed audience, as well as its applications in psychiatry. The review covers definitions and expositions of commonly used machine learning methods, and historical trends of their use in psychiatry. We also provide a set of standards, namely Guidelines for REporting Machine Learning Investigations in Neuropsychiatry (GREMLIN), for designing and reporting studies that use machine learning as a primary data-analysis approach. Lastly, we propose the establishment of the Machine Learning in Psychiatry (MLPsych) Consortium, enumerate its objectives, and identify areas of opportunity for future applications of machine learning in biological psychiatry. This review serves as a cautiously optimistic primer on machine learning for those on the precipice as they prepare to dive into the field, either as methodological practitioners or well-informed consumers.
Collapse
Affiliation(s)
- Thomas P Quinn
- Applied Artificial Intelligence Institute (A2I2), Burwood, VIC, 3125, Australia
| | - Jonathan L Hess
- Department of Psychiatry and Behavioral Sciences, Norton College of Medicine at SUNY Upstate Medical University, Syracuse, NY, 13210, USA
| | - Victoria S Marshe
- Institute of Medical Science, University of Toronto, Toronto, ON, M5S 1A1, Canada
- Pharmacogenetics Research Clinic, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, ON, M5S 1A1, Canada
| | - Michelle M Barnett
- School of Biomedical Sciences and Pharmacy, The University of Newcastle, Callaghan, NSW, 2308, Australia
- Precision Medicine Research Program, Hunter Medical Research Institute, Newcastle, NSW, 2308, Australia
| | - Anne-Christin Hauschild
- Department of Medical Informatics, Medical University Center Göttingen, Göttingen, Lower Saxony, 37075, Germany
| | - Malgorzata Maciukiewicz
- Hospital Zurich, University of Zurich, Zurich, 8091, Switzerland
- Department of Rheumatology and Immunology, University Hospital Bern, Bern, 3010, Switzerland
- Department for Biomedical Research (DBMR), University of Bern, Bern, 3010, Switzerland
| | - Samar S M Elsheikh
- Pharmacogenetics Research Clinic, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, ON, M5S 1A1, Canada
| | - Xiaoyu Men
- Pharmacogenetics Research Clinic, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, ON, M5S 1A1, Canada
- Department of Pharmacology and Toxicology, University of Toronto, Toronto, ON, M5S 1A1, Canada
| | - Emanuel Schwarz
- Department of Psychiatry and Psychotherapy, Central Institute of Mental Health, Mannheim, Baden-Württemberg, J5 68159, Germany
| | - Yannis J Trakadis
- Department Human Genetics, McGill University Health Centre, Montreal, QC, H4A 3J1, Canada
| | - Michael S Breen
- Psychiatry, Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA
| | - Eric J Barnett
- Department of Neuroscience and Physiology, Norton College of Medicine at SUNY Upstate Medical University, Syracuse, NY, 13210, USA
| | - Yanli Zhang-James
- Department of Psychiatry and Behavioral Sciences, Norton College of Medicine at SUNY Upstate Medical University, Syracuse, NY, 13210, USA
| | - Mehmet Eren Ahsen
- Department of Business Administration, Gies College of Business, University of Illinois at Urbana-Champaign, Champaign, IL, 61820, USA
- Department of Biomedical and Translational Sciences, Carle-Illinois School of Medicine, University of Illinois at Urbana-Champaign, Champaign, IL, 61820, USA
| | - Han Cao
- Department of Psychiatry and Psychotherapy, Central Institute of Mental Health, Mannheim, Baden-Württemberg, J5 68159, Germany
| | - Junfang Chen
- Department of Psychiatry and Psychotherapy, Central Institute of Mental Health, Mannheim, Baden-Württemberg, J5 68159, Germany
| | - Jiahui Hou
- Department of Psychiatry and Behavioral Sciences, Norton College of Medicine at SUNY Upstate Medical University, Syracuse, NY, 13210, USA
- Department of Neuroscience and Physiology, Norton College of Medicine at SUNY Upstate Medical University, Syracuse, NY, 13210, USA
| | - Asif Salekin
- Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, 13244, USA
| | - Ping-I Lin
- Discipline of Psychiatry and Mental Health, University of New South Wales, Sydney, NSW, 2052, Australia
- Mental Health Research Unit, South Western Sydney Local Health District, Liverpool, NSW, 2170, Australia
| | | | - Andreas Meyer-Lindenberg
- Clinical Department of Psychiatry and Psychotherapy, Central Institute of Mental Health, Mannheim, Baden-Württemberg, J5 68159, Germany
| | - Isabelle Bichindaritz
- Biomedical and Health Informatics/Computer Science Department, State University of New York at Oswego, Oswego, NY, 13126, USA
- Intelligent Bio Systems Lab, State University of New York at Oswego, Oswego, NY, 13126, USA
| | - Stephen V Faraone
- Department of Psychiatry and Behavioral Sciences, Norton College of Medicine at SUNY Upstate Medical University, Syracuse, NY, 13210, USA
- Department of Neuroscience and Physiology, Norton College of Medicine at SUNY Upstate Medical University, Syracuse, NY, 13210, USA
| | - Murray J Cairns
- School of Biomedical Sciences and Pharmacy, The University of Newcastle, Callaghan, NSW, 2308, Australia
- Precision Medicine Research Program, Hunter Medical Research Institute, Newcastle, NSW, 2308, Australia
| | - Gaurav Pandey
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA
| | - Daniel J Müller
- Pharmacogenetics Research Clinic, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, ON, M5S 1A1, Canada
- Department of Psychiatry, University of Toronto, Toronto, ON, M5S 1A1, Canada
- Department of Psychiatry, Psychosomatics and Psychotherapy, Center of Mental Health, University Hospital of Würzburg, Würzburg, 97080, Germany
| | - Stephen J Glatt
- Department of Psychiatry and Behavioral Sciences, Norton College of Medicine at SUNY Upstate Medical University, Syracuse, NY, 13210, USA.
- Department of Neuroscience and Physiology, Norton College of Medicine at SUNY Upstate Medical University, Syracuse, NY, 13210, USA.
- Department of Public Health and Preventive Medicine, Norton College of Medicine at SUNY Upstate Medical University, Syracuse, NY, 13210, USA.
| |
Collapse
|
13
|
Russe MF, Rebmann P, Tran PH, Kellner E, Reisert M, Bamberg F, Kotter E, Kim S. AI-based X-ray fracture analysis of the distal radius: accuracy between representative classification, detection and segmentation deep learning models for clinical practice. BMJ Open 2024; 14:e076954. [PMID: 38262641 PMCID: PMC10823998 DOI: 10.1136/bmjopen-2023-076954] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/22/2023] [Accepted: 12/21/2023] [Indexed: 01/25/2024] Open
Abstract
OBJECTIVES To aid in selecting the optimal artificial intelligence (AI) solution for clinical application, we directly compared performances of selected representative custom-trained or commercial classification, detection and segmentation models for fracture detection on musculoskeletal radiographs of the distal radius by aligning their outputs. DESIGN AND SETTING This single-centre retrospective study was conducted on a random subset of emergency department radiographs from 2008 to 2018 of the distal radius in Germany. MATERIALS AND METHODS An image set was created to be compatible with training and testing classification and segmentation models by annotating examinations for fractures and overlaying fracture masks, if applicable. Representative classification and segmentation models were trained on 80% of the data. After output binarisation, their derived fracture detection performances as well as that of a standard commercially available solution were compared on the remaining X-rays (20%) using mainly accuracy and area under the receiver operating characteristic (AUROC). RESULTS A total of 2856 examinations with 712 (24.9%) fractures were included in the analysis. Accuracies reached up to 0.97 for the classification model, 0.94 for the segmentation model and 0.95 for BoneView. Cohen's kappa was at least 0.80 in pairwise comparisons, while Fleiss' kappa was 0.83 for all models. Fracture predictions were visualised with all three methods at different levels of detail, ranking from downsampled image region for classification over bounding box for detection to single pixel-level delineation for segmentation. CONCLUSIONS All three investigated approaches reached high performances for detection of distal radius fractures with simple preprocessing and postprocessing protocols on the custom-trained models. Despite their underlying structural differences, selection of one's fracture analysis AI tool in the frame of this study reduces to the desired flavour of automation: automated classification, AI-assisted manual fracture reading or minimised false negatives.
Collapse
Affiliation(s)
- Maximilian Frederik Russe
- Department of Diagnostic and Interventional Radiology, Universitätsklinikum Freiburg Medizinische Universitätsklinik, Freiburg im Breisgau, Germany
| | - Philipp Rebmann
- Department of Diagnostic and Interventional Radiology, Universitätsklinikum Freiburg Medizinische Universitätsklinik, Freiburg im Breisgau, Germany
| | - Phuong Hien Tran
- Department of Diagnostic and Interventional Radiology, Universitätsklinikum Freiburg Medizinische Universitätsklinik, Freiburg im Breisgau, Germany
| | - Elias Kellner
- Department of Medical Physics, Universitätsklinikum Freiburg Medizinische Universitätsklinik, Freiburg im Breisgau, Germany
| | - Marco Reisert
- Department of Medical Physics, Universitätsklinikum Freiburg Medizinische Universitätsklinik, Freiburg im Breisgau, Germany
| | - Fabian Bamberg
- Department of Diagnostic and Interventional Radiology, Universitätsklinikum Freiburg Medizinische Universitätsklinik, Freiburg im Breisgau, Germany
| | - Elmar Kotter
- Department of Diagnostic and Interventional Radiology, Universitätsklinikum Freiburg Medizinische Universitätsklinik, Freiburg im Breisgau, Germany
| | - Suam Kim
- Department of Diagnostic and Interventional Radiology, Universitätsklinikum Freiburg Medizinische Universitätsklinik, Freiburg im Breisgau, Germany
| |
Collapse
|
14
|
Saeed T, Ijaz A, Sadiq I, Qureshi HN, Rizwan A, Imran A. An AI-Enabled Bias-Free Respiratory Disease Diagnosis Model Using Cough Audio. Bioengineering (Basel) 2024; 11:55. [PMID: 38247932 PMCID: PMC10813025 DOI: 10.3390/bioengineering11010055] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2023] [Revised: 12/25/2023] [Accepted: 01/03/2024] [Indexed: 01/23/2024] Open
Abstract
Cough-based diagnosis for respiratory diseases (RDs) using artificial intelligence (AI) has attracted considerable attention, yet many existing studies overlook confounding variables in their predictive models. These variables can distort the relationship between cough recordings (input data) and RD status (output variable), leading to biased associations and unrealistic model performance. To address this gap, we propose the Bias-Free Network (RBF-Net), an end-to-end solution that effectively mitigates the impact of confounders in the training data distribution. RBF-Net ensures accurate and unbiased RD diagnosis features, emphasizing its relevance by incorporating a COVID-19 dataset in this study. This approach aims to enhance the reliability of AI-based RD diagnosis models by navigating the challenges posed by confounding variables. A hybrid of a Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks is proposed for the feature encoder module of RBF-Net. An additional bias predictor is incorporated in the classification scheme to formulate a conditional Generative Adversarial Network (c-GAN) that helps in decorrelating the impact of confounding variables from RD prediction. The merit of RBF-Net is demonstrated by comparing classification performance with a State-of-The-Art (SoTA) Deep Learning (DL) model (CNN-LSTM) after training on different unbalanced COVID-19 data sets, created by using a large-scale proprietary cough data set. RBF-Net proved its robustness against extremely biased training scenarios by achieving test set accuracies of 84.1%, 84.6%, and 80.5% for the following confounding variables-gender, age, and smoking status, respectively. RBF-Net outperforms the CNN-LSTM model test set accuracies by 5.5%, 7.7%, and 8.2%, respectively.
Collapse
Affiliation(s)
- Tabish Saeed
- AI4Networks Research Center, Department of Electrical & Computer Engineering, University of Oklahoma, Tulsa, OK 74135, USA; (H.N.Q.); (A.I.)
| | - Aneeqa Ijaz
- AI4Networks Research Center, Department of Electrical & Computer Engineering, University of Oklahoma, Tulsa, OK 74135, USA; (H.N.Q.); (A.I.)
| | - Ismail Sadiq
- James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK;
| | - Haneya Naeem Qureshi
- AI4Networks Research Center, Department of Electrical & Computer Engineering, University of Oklahoma, Tulsa, OK 74135, USA; (H.N.Q.); (A.I.)
| | - Ali Rizwan
- AI4lyf, Bahria Town Lahore, Lahore 54000, Pakistan;
| | - Ali Imran
- AI4Networks Research Center, Department of Electrical & Computer Engineering, University of Oklahoma, Tulsa, OK 74135, USA; (H.N.Q.); (A.I.)
- James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK;
| |
Collapse
|
15
|
Sorace L, Raju N, O'Shaughnessy J, Kachel S, Jansz K, Yang N, Lim RP. Assessment of inspiration and technical quality in anteroposterior thoracic radiographs using machine learning. Radiography (Lond) 2024; 30:107-115. [PMID: 37918335 DOI: 10.1016/j.radi.2023.10.014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2023] [Revised: 10/16/2023] [Accepted: 10/17/2023] [Indexed: 11/04/2023]
Abstract
INTRODUCTION Chest radiographs are the most performed radiographic procedure, but suboptimal technical factors can impact clinical interpretation. A deep learning model was developed to assess technical and inspiratory adequacy of anteroposterior chest radiographs. METHODS Adult anteroposterior chest radiographs (n = 2375) were assessed for technical adequacy, and if otherwise technically adequate, for adequacy of inspiration. Images were labelled by an experienced radiologist with one of three ground truth labels: inadequate technique (n = 605, 25.5 %), adequate inspiration (n = 900, 37.9 %), and inadequate inspiration (n = 870, 36.6 %). A convolutional neural network was then iteratively trained to predict these labels and evaluated using recall, precision, F1 and micro-F1, and Gradient-weighted Class Activation Mapping analysis on a hold-out test set. Impact of kyphosis on model accuracy was assessed. RESULTS The model performed best for radiographs with adequate technique, and worst for images with inadequate technique. Recall was highest (89 %) for radiographs with both adequate technique and inspiration, with recall of 81 % for images with adequate technique and inadequate inspiration, and 60 % for images with inadequate technique, although precision was highest (85 %) for this category. Per-class F1 was 80 %, 81 % and 70 % for adequate inspiration, inadequate inspiration, and inadequate technique respectively. Weighted F1 and Micro F1 scores were 78 %. Presence or absence of kyphosis had no significant impact on model accuracy in images with adequate technique. CONCLUSION This study explores the promising performance of a machine learning algorithm for assessment of inspiratory adequacy and overall technical adequacy for anteroposterior chest radiograph acquisition. IMPLICATIONS FOR PRACTICE With further refinement, machine learning can contribute to education and quality improvement in radiology departments.
Collapse
Affiliation(s)
- L Sorace
- Department of Radiology, Austin Hospital, Heidelberg, Australia.
| | - N Raju
- Department of Radiology, Austin Hospital, Heidelberg, Australia
| | - J O'Shaughnessy
- Department of Radiology, Austin Hospital, Heidelberg, Australia
| | - S Kachel
- Department of Radiology, Austin Hospital, Heidelberg, Australia; The University of Melbourne, Parkville, Australia; Columbia University, New York, NY, USA
| | - K Jansz
- Department of Radiology, Austin Hospital, Heidelberg, Australia
| | - N Yang
- Department of Radiology, Austin Hospital, Heidelberg, Australia; The University of Melbourne, Parkville, Australia
| | - R P Lim
- Department of Radiology, Austin Hospital, Heidelberg, Australia; The University of Melbourne, Parkville, Australia
| |
Collapse
|
16
|
Lin M, Li T, Yang Y, Holste G, Ding Y, Van Tassel SH, Kovacs K, Shih G, Wang Z, Lu Z, Wang F, Peng Y. Improving model fairness in image-based computer-aided diagnosis. Nat Commun 2023; 14:6261. [PMID: 37803009 PMCID: PMC10558498 DOI: 10.1038/s41467-023-41974-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2023] [Accepted: 09/25/2023] [Indexed: 10/08/2023] Open
Abstract
Deep learning has become a popular tool for computer-aided diagnosis using medical images, sometimes matching or exceeding the performance of clinicians. However, these models can also reflect and amplify human bias, potentially resulting inaccurate missed diagnoses. Despite this concern, the problem of improving model fairness in medical image classification by deep learning has yet to be fully studied. To address this issue, we propose an algorithm that leverages the marginal pairwise equal opportunity to reduce bias in medical image classification. Our evaluations across four tasks using four independent large-scale cohorts demonstrate that our proposed algorithm not only improves fairness in individual and intersectional subgroups but also maintains overall performance. Specifically, the relative change in pairwise fairness difference between our proposed model and the baseline model was reduced by over 35%, while the relative change in AUC value was typically within 1%. By reducing the bias generated by deep learning models, our proposed approach can potentially alleviate concerns about the fairness and reliability of image-based computer-aided diagnosis.
Collapse
Affiliation(s)
- Mingquan Lin
- Department of Population Health Sciences, Weill Cornell Medicine, New York, USA.
| | - Tianhao Li
- School of Information, The University of Texas at Austin, Austin, TX, USA
| | - Yifan Yang
- National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health (NIH), Bethesda, MD, 20894, USA
| | - Gregory Holste
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA
| | - Ying Ding
- School of Information, The University of Texas at Austin, Austin, TX, USA
| | | | - Kyle Kovacs
- Department of Ophthalmology, Weill Cornell Medicine, New York, USA
| | - George Shih
- Department of Radiology, Weill Cornell Medicine, New York, USA
| | - Zhangyang Wang
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA
| | - Zhiyong Lu
- National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health (NIH), Bethesda, MD, 20894, USA
| | - Fei Wang
- Department of Population Health Sciences, Weill Cornell Medicine, New York, USA
| | - Yifan Peng
- Department of Population Health Sciences, Weill Cornell Medicine, New York, USA.
| |
Collapse
|
17
|
Liu M, Ning Y, Teixayavong S, Mertens M, Xu J, Ting DSW, Cheng LTE, Ong JCL, Teo ZL, Tan TF, RaviChandran N, Wang F, Celi LA, Ong MEH, Liu N. A translational perspective towards clinical AI fairness. NPJ Digit Med 2023; 6:172. [PMID: 37709945 PMCID: PMC10502051 DOI: 10.1038/s41746-023-00918-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2023] [Accepted: 09/04/2023] [Indexed: 09/16/2023] Open
Abstract
Artificial intelligence (AI) has demonstrated the ability to extract insights from data, but the fairness of such data-driven insights remains a concern in high-stakes fields. Despite extensive developments, issues of AI fairness in clinical contexts have not been adequately addressed. A fair model is normally expected to perform equally across subgroups defined by sensitive variables (e.g., age, gender/sex, race/ethnicity, socio-economic status, etc.). Various fairness measurements have been developed to detect differences between subgroups as evidence of bias, and bias mitigation methods are designed to reduce the differences detected. This perspective of fairness, however, is misaligned with some key considerations in clinical contexts. The set of sensitive variables used in healthcare applications must be carefully examined for relevance and justified by clear clinical motivations. In addition, clinical AI fairness should closely investigate the ethical implications of fairness measurements (e.g., potential conflicts between group- and individual-level fairness) to select suitable and objective metrics. Generally defining AI fairness as "equality" is not necessarily reasonable in clinical settings, as differences may have clinical justifications and do not indicate biases. Instead, "equity" would be an appropriate objective of clinical AI fairness. Moreover, clinical feedback is essential to developing fair and well-performing AI models, and efforts should be made to actively involve clinicians in the process. The adaptation of AI fairness towards healthcare is not self-evident due to misalignments between technical developments and clinical considerations. Multidisciplinary collaboration between AI researchers, clinicians, and ethicists is necessary to bridge the gap and translate AI fairness into real-life benefits.
Collapse
Affiliation(s)
- Mingxuan Liu
- Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore
| | - Yilin Ning
- Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore
| | | | - Mayli Mertens
- Centre for Ethics, Department of Philosophy, University of Antwerp, Antwerp, Belgium
- Antwerp Center on Responsible AI, University of Antwerp, Antwerp, Belgium
| | - Jie Xu
- Department of Health Outcomes and Biomedical Informatics, University of Florida, Gainesville, FL, USA
| | - Daniel Shu Wei Ting
- Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
- SingHealth AI Office, Singapore Health Services, Singapore, Singapore
| | - Lionel Tim-Ee Cheng
- Department of Diagnostic Radiology, Singapore General Hospital, Singapore, Singapore
| | | | - Zhen Ling Teo
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
| | - Ting Fang Tan
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
| | | | - Fei Wang
- Department of Population Health Sciences, Weill Cornell Medicine, New York, NY, USA
| | - Leo Anthony Celi
- Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, MA, USA
- Division of Pulmonary, Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA
| | - Marcus Eng Hock Ong
- Programme in Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore
- Department of Emergency Medicine, Singapore General Hospital, Singapore, Singapore
| | - Nan Liu
- Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore.
- SingHealth AI Office, Singapore Health Services, Singapore, Singapore.
- Programme in Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore.
- Institute of Data Science, National University of Singapore, Singapore, Singapore.
| |
Collapse
|
18
|
Horry MJ, Chakraborty S, Pradhan B, Paul M, Zhu J, Loh HW, Barua PD, Acharya UR. Development of Debiasing Technique for Lung Nodule Chest X-ray Datasets to Generalize Deep Learning Models. SENSORS (BASEL, SWITZERLAND) 2023; 23:6585. [PMID: 37514877 PMCID: PMC10385599 DOI: 10.3390/s23146585] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/14/2023] [Revised: 07/16/2023] [Accepted: 07/20/2023] [Indexed: 07/30/2023]
Abstract
Screening programs for early lung cancer diagnosis are uncommon, primarily due to the challenge of reaching at-risk patients located in rural areas far from medical facilities. To overcome this obstacle, a comprehensive approach is needed that combines mobility, low cost, speed, accuracy, and privacy. One potential solution lies in combining the chest X-ray imaging mode with federated deep learning, ensuring that no single data source can bias the model adversely. This study presents a pre-processing pipeline designed to debias chest X-ray images, thereby enhancing internal classification and external generalization. The pipeline employs a pruning mechanism to train a deep learning model for nodule detection, utilizing the most informative images from a publicly available lung nodule X-ray dataset. Histogram equalization is used to remove systematic differences in image brightness and contrast. Model training is then performed using combinations of lung field segmentation, close cropping, and rib/bone suppression. The resulting deep learning models, generated through this pre-processing pipeline, demonstrate successful generalization on an independent lung nodule dataset. By eliminating confounding variables in chest X-ray images and suppressing signal noise from the bone structures, the proposed deep learning lung nodule detection algorithm achieves an external generalization accuracy of 89%. This approach paves the way for the development of a low-cost and accessible deep learning-based clinical system for lung cancer screening.
Collapse
Affiliation(s)
- Michael J Horry
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
- IBM Australia Limited, Sydney, NSW 2000, Australia
| | - Subrata Chakraborty
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
- Faculty of Science, Agriculture, Business and Law, University of New England, Armidale, NSW 2351, Australia
| | - Biswajeet Pradhan
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
- Earth Observation Center, Institute of Climate Change, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia
| | - Manoranjan Paul
- Machine Vision and Digital Health (MaViDH), School of Computing and Mathematics, Charles Sturt University, Bathurst, NSW 2795, Australia
| | - Jing Zhu
- Department of Radiology, Westmead Hospital, Westmead, NSW 2145, Australia
| | - Hui Wen Loh
- School of Science and Technology, Singapore University of Social Sciences, Singapore 599494, Singapore
| | - Prabal Datta Barua
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
- Faculty of Science, Agriculture, Business and Law, University of New England, Armidale, NSW 2351, Australia
- Cogninet Brain Team, Cogninet Australia, Sydney, NSW 2010, Australia
- School of Business (Information Systems), Faculty of Business, Education, Law & Arts, University of Southern Queensland, Toowoomba, QLD 4350, Australia
| | - U Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, QLD 4300, Australia
| |
Collapse
|
19
|
Weinstein SM, Davatzikos C, Doshi J, Linn KA, Shinohara RT. Penalized decomposition using residuals (PeDecURe) for feature extraction in the presence of nuisance variables. Biostatistics 2023; 24:653-668. [PMID: 35950944 PMCID: PMC10345990 DOI: 10.1093/biostatistics/kxac031] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2022] [Revised: 07/12/2022] [Accepted: 07/16/2022] [Indexed: 11/13/2022] Open
Abstract
Neuroimaging data are an increasingly important part of etiological studies of neurological and psychiatric disorders. However, mitigating the influence of nuisance variables, including confounders, remains a challenge in image analysis. In studies of Alzheimer's disease, for example, an imbalance in disease rates by age and sex may make it difficult to distinguish between structural patterns in the brain (as measured by neuroimaging scans) attributable to disease progression and those characteristic of typical human aging or sex differences. Concerningly, when not properly accounted for, nuisance variables pose threats to the generalizability and interpretability of findings from these studies. Motivated by this critical issue, in this work, we examine the impact of nuisance variables on feature extraction methods and propose Penalized Decomposition Using Residuals (PeDecURe), a new method for obtaining nuisance variable-adjusted features. PeDecURe estimates primary directions of variation which maximize covariance between partially residualized imaging features and a variable of interest (e.g., Alzheimer's diagnosis) while simultaneously mitigating the influence of nuisance variation through a penalty on the covariance between partially residualized imaging features and those variables. Using features derived using PeDecURe's first direction of variation, we train a highly accurate and generalizable predictive model, as evidenced by its robustness in testing samples with different underlying nuisance variable distributions. We compare PeDecURe to commonly used decomposition methods (principal component analysis (PCA) and partial least squares) as well as a confounder-adjusted variation of PCA. We find that features derived from PeDecURe offer greater accuracy and generalizability and lower correlations with nuisance variables compared with the other methods. While PeDecURe is primarily motivated by challenges that arise in the analysis of neuroimaging data, it is broadly applicable to data sets with highly correlated features, where novel methods to handle nuisance variables are warranted.
Collapse
Affiliation(s)
- Sarah M Weinstein
- Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, Penn Statistics in Imaging and Visualization Center, 108/109B, Blockley Hall, University of Pennsylvania, 423 Guardian Drive, Philadelphia, PA 19104, USA
| | - Christos Davatzikos
- Department of Radiology, Perelman School of Medicine, Center for Biomedical Image Computing and Analytics, 3700 Hamilton Walk, Richards Building 7th Floor, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Jimit Doshi
- Department of Radiology, Perelman School of Medicine, Center for Biomedical Image Computing and Analytics, 3700 Hamilton Walk, Richards Building 7th Floor, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Kristin A Linn
- Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, Penn Statistics in Imaging and Visualization Center, 2nd Floor, Blockley Hall, University of Pennsylvania, 423 Guardian Drive, Philadelphia, PA 19104, USA and Department of Radiology, Perelman School of Medicine, Center for Biomedical Image Computing and Analytics, 3700 Hamilton Walk, Richards Building 7th Floor, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Russell T Shinohara
- Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, Penn Statistics in Imaging and Visualization Center, 2nd Floor, Blockley Hall, University of Pennsylvania, 423 Guardian Drive, Philadelphia, PA 19104, USA and Department of Radiology, Perelman School of Medicine, Center for Biomedical Image Computing and Analytics, 3700 Hamilton Walk, Richards Building 7th Floor, University of Pennsylvania, Philadelphia, PA 19104, USA
| | | |
Collapse
|
20
|
Leming MJ, Bron EE, Bruffaerts R, Ou Y, Iglesias JE, Gollub RL, Im H. Challenges of implementing computer-aided diagnostic models for neuroimages in a clinical setting. NPJ Digit Med 2023; 6:129. [PMID: 37443276 DOI: 10.1038/s41746-023-00868-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2022] [Accepted: 06/26/2023] [Indexed: 07/15/2023] Open
Abstract
Advances in artificial intelligence have cultivated a strong interest in developing and validating the clinical utilities of computer-aided diagnostic models. Machine learning for diagnostic neuroimaging has often been applied to detect psychological and neurological disorders, typically on small-scale datasets or data collected in a research setting. With the collection and collation of an ever-growing number of public datasets that researchers can freely access, much work has been done in adapting machine learning models to classify these neuroimages by diseases such as Alzheimer's, ADHD, autism, bipolar disorder, and so on. These studies often come with the promise of being implemented clinically, but despite intense interest in this topic in the laboratory, limited progress has been made in clinical implementation. In this review, we analyze challenges specific to the clinical implementation of diagnostic AI models for neuroimaging data, looking at the differences between laboratory and clinical settings, the inherent limitations of diagnostic AI, and the different incentives and skill sets between research institutions, technology companies, and hospitals. These complexities need to be recognized in the translation of diagnostic AI for neuroimaging from the laboratory to the clinic.
Collapse
Affiliation(s)
- Matthew J Leming
- Center for Systems Biology, Massachusetts General Hospital, Boston, MA, USA.
- Massachusetts Alzheimer's Disease Research Center, Charlestown, MA, USA.
| | - Esther E Bron
- Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands
| | - Rose Bruffaerts
- Computational Neurology, Experimental Neurobiology Unit (ENU), Department of Biomedical Sciences, University of Antwerp, Antwerp, Belgium
- Biomedical Research Institute, Hasselt University, Diepenbeek, Belgium
| | - Yangming Ou
- Boston Children's Hospital, 300 Longwood Ave, Boston, MA, USA
| | - Juan Eugenio Iglesias
- Center for Medical Image Computing, University College London, London, UK
- Martinos Center for Biomedical Imaging, Harvard Medical School, Boston, MA, USA
- Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Randy L Gollub
- Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Hyungsoon Im
- Center for Systems Biology, Massachusetts General Hospital, Boston, MA, USA.
- Massachusetts Alzheimer's Disease Research Center, Charlestown, MA, USA.
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA.
| |
Collapse
|
21
|
Veličković VM, Spelman T, Clark M, Probst S, Armstrong DG, Steyerberg E. Individualized Risk Prediction for Improved Chronic Wound Management. Adv Wound Care (New Rochelle) 2023; 12:387-398. [PMID: 36070447 PMCID: PMC10125399 DOI: 10.1089/wound.2022.0017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2022] [Accepted: 08/26/2022] [Indexed: 11/13/2022] Open
Abstract
Significance: Chronic wounds are associated with significant morbidity, marked loss of quality of life, and considerable economic burden. Evidence-based risk prediction to guide improved wound prevention and treatment is limited by the complexity in their etiology, clinical underreporting, and a lack of studies using large high-quality datasets. Recent Advancements: The objective of this review is to summarize key components and challenges in the development of personalized risk prediction tools for both prevention and management of chronic wounds, while highlighting several innovations in the development of better risk stratification. Critical Issues: Regression-based risk prediction approaches remain important for assessment of prognosis and risk stratification in chronic wound management. Advances in statistical computing have boosted the development of several promising machine learning (ML) and other semiautomated classification tools. These methods may be better placed to handle large number of wound healing risk factors from large datasets, potentially resulting in better risk prediction when combined with conventional methods and clinical experience and expertise. Future Directions: Where the number of predictors is large and heterogenous, the correlations between various risk factors complex, and very large data sets are available, ML may prove a powerful adjuvant for risk stratifying patients predisposed to chronic wounds. Conventional regression-based approaches remain important, particularly where the number of predictors is relatively small. Translating estimated risk derived from ML algorithms into practical prediction tools for use in clinical practice remains challenging.
Collapse
Affiliation(s)
- Vladica M. Veličković
- HARTMANN GROUP, Heidenheim, Germany
- Institute of Public Health, Medical Decision Making and HTA, UMIT, Hall in Tirol, Austria
| | - Tim Spelman
- Department of Clinical Neuroscience, Karolinska Institute, Stockholm, Sweden
- Burnet Institute, Melbourne, Australia
- Department of Health Services Research, Peter MacCallum Cancer Centre, Melbourne, Australia
| | - Michael Clark
- Welsh Wound Innovation Centre, Pontyclun, United Kingdom
- School of Health, Education and Life Sciences, Birmingham City University, Birmingham, United Kingdom
| | - Sebastian Probst
- Geneva School of Health Sciences, HES-SO University of Applied Sciences and Arts, Geneva, Western Switzerland
- Faculty of Medicine Nursing and Health Sciences, Monash University, Melbourne, Australia
- Care Directorate, University Hospital Geneva, Geneva, Switzerland
| | - David G. Armstrong
- Southwestern Academic Limb Salvage Alliance (SALSA), Department of Surgery, Keck School of Medicine, University of Southern California (USC), Los Angeles, California, USA
| | | |
Collapse
|
22
|
Kim C, Gadgil SU, DeGrave AJ, Cai ZR, Daneshjou R, Lee SI. Fostering transparent medical image AI via an image-text foundation model grounded in medical literature. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.06.07.23291119. [PMID: 37398017 PMCID: PMC10312868 DOI: 10.1101/2023.06.07.23291119] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/04/2023]
Abstract
Building trustworthy and transparent image-based medical AI systems requires the ability to interrogate data and models at all stages of the development pipeline: from training models to post-deployment monitoring. Ideally, the data and associated AI systems could be described using terms already familiar to physicians, but this requires medical datasets densely annotated with semantically meaningful concepts. Here, we present a foundation model approach, named MONET (Medical cONcept rETriever), which learns how to connect medical images with text and generates dense concept annotations to enable tasks in AI transparency from model auditing to model interpretation. Dermatology provides a demanding use case for the versatility of MONET, due to the heterogeneity in diseases, skin tones, and imaging modalities. We trained MONET on the basis of 105,550 dermatological images paired with natural language descriptions from a large collection of medical literature. MONET can accurately annotate concepts across dermatology images as verified by board-certified dermatologists, outperforming supervised models built on previously concept-annotated dermatology datasets. We demonstrate how MONET enables AI transparency across the entire AI development pipeline from dataset auditing to model auditing to building inherently interpretable models.
Collapse
Affiliation(s)
- Chanwoo Kim
- Paul G. Allen School of Computer Science and Engineering, University of Washington
| | - Soham U Gadgil
- Paul G. Allen School of Computer Science and Engineering, University of Washington
| | - Alex J DeGrave
- Paul G. Allen School of Computer Science and Engineering, University of Washington
- Medical Scientist Training Program, University of Washington
| | - Zhuo Ran Cai
- Program for Clinical Research and Technology, Stanford University
| | - Roxana Daneshjou
- Department of Dermatology, Stanford School of Medicine
- Department of Biomedical Data Science, Stanford School of Medicine
| | - Su-In Lee
- Paul G. Allen School of Computer Science and Engineering, University of Washington
| |
Collapse
|
23
|
Kocak B, Baessler B, Bakas S, Cuocolo R, Fedorov A, Maier-Hein L, Mercaldo N, Müller H, Orlhac F, Pinto Dos Santos D, Stanzione A, Ugga L, Zwanenburg A. CheckList for EvaluAtion of Radiomics research (CLEAR): a step-by-step reporting guideline for authors and reviewers endorsed by ESR and EuSoMII. Insights Imaging 2023; 14:75. [PMID: 37142815 PMCID: PMC10160267 DOI: 10.1186/s13244-023-01415-8] [Citation(s) in RCA: 61] [Impact Index Per Article: 61.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2023] [Accepted: 03/24/2023] [Indexed: 05/06/2023] Open
Abstract
Even though radiomics can hold great potential for supporting clinical decision-making, its current use is mostly limited to academic research, without applications in routine clinical practice. The workflow of radiomics is complex due to several methodological steps and nuances, which often leads to inadequate reporting and evaluation, and poor reproducibility. Available reporting guidelines and checklists for artificial intelligence and predictive modeling include relevant good practices, but they are not tailored to radiomic research. There is a clear need for a complete radiomics checklist for study planning, manuscript writing, and evaluation during the review process to facilitate the repeatability and reproducibility of studies. We here present a documentation standard for radiomic research that can guide authors and reviewers. Our motivation is to improve the quality and reliability and, in turn, the reproducibility of radiomic research. We name the checklist CLEAR (CheckList for EvaluAtion of Radiomics research), to convey the idea of being more transparent. With its 58 items, the CLEAR checklist should be considered a standardization tool providing the minimum requirements for presenting clinical radiomics research. In addition to a dynamic online version of the checklist, a public repository has also been set up to allow the radiomics community to comment on the checklist items and adapt the checklist for future versions. Prepared and revised by an international group of experts using a modified Delphi method, we hope the CLEAR checklist will serve well as a single and complete scientific documentation tool for authors and reviewers to improve the radiomics literature.
Collapse
Affiliation(s)
- Burak Kocak
- Department of Radiology, University of Health Sciences, Basaksehir Cam and Sakura City Hospital, Basaksehir, Istanbul, 34480, Turkey.
| | - Bettina Baessler
- Institute of Diagnostic and Interventional Radiology, University Hospital Würzburg, Würzburg, Germany
| | - Spyridon Bakas
- Center for Artificial Intelligence for Integrated Diagnostics (AI2D) & Center for Biomedical Image Computing & Analytics (CBICA), University of Pennsylvania, Philadelphia, PA, USA
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
- Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Renato Cuocolo
- Department of Medicine, Surgery, and Dentistry, University of Salerno, Baronissi, Italy
| | - Andrey Fedorov
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
| | - Lena Maier-Hein
- Division of Intelligent Medical Systems, German Cancer Research Center, Heidelberg, Germany
- National Center for Tumor Diseases (NCT), Heidelberg, Germany
| | - Nathaniel Mercaldo
- Institute for Technology Assessment, Massachusetts General Hospital, Boston, MA, USA
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - Henning Müller
- University of Applied Sciences of Western Switzerland (HES-SO Valais), Valais, Switzerland
- Department of Radiology and Medical Informatics, University of Geneva (UniGe), Geneva, Switzerland
| | - Fanny Orlhac
- Laboratoire d'Imagerie Translationnelle en Oncologie (LITO)-U1288, Institut Curie, Inserm, Université PSL, Orsay, France
| | - Daniel Pinto Dos Santos
- Department of Radiology, University Hospital of Cologne, Cologne, Germany
- Institute for Diagnostic and Interventional Radiology, Goethe-University Frankfurt Am Main, Frankfurt, Germany
| | - Arnaldo Stanzione
- Department of Advanced Biomedical Sciences, University of Naples "Federico II", Naples, Italy
| | - Lorenzo Ugga
- Department of Advanced Biomedical Sciences, University of Naples "Federico II", Naples, Italy
| | - Alex Zwanenburg
- OncoRay-National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Dresden, Germany
- German Cancer Research Center (DKFZ), Heidelberg, Germany
| |
Collapse
|
24
|
Mukerji SS, Petersen KJ, Pohl KM, Dastgheyb RM, Fox HS, Bilder RM, Brouillette MJ, Gross AL, Scott-Sheldon LAJ, Paul RH, Gabuzda D. Machine Learning Approaches to Understand Cognitive Phenotypes in People With HIV. J Infect Dis 2023; 227:S48-S57. [PMID: 36930638 PMCID: PMC10022709 DOI: 10.1093/infdis/jiac293] [Citation(s) in RCA: 13] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/18/2023] Open
Abstract
Cognitive disorders are prevalent in people with HIV (PWH) despite antiretroviral therapy. Given the heterogeneity of cognitive disorders in PWH in the current era and evidence that these disorders have different etiologies and risk factors, scientific rationale is growing for using data-driven models to identify biologically defined subtypes (biotypes) of these disorders. Here, we discuss the state of science using machine learning to understand cognitive phenotypes in PWH and their associated comorbidities, biological mechanisms, and risk factors. We also discuss methods, example applications, challenges, and what will be required from the field to successfully incorporate machine learning in research on cognitive disorders in PWH. These topics were discussed at the National Institute of Mental Health meeting on "Biotypes of CNS Complications in People Living with HIV" held in October 2021. These ongoing research initiatives seek to explain the heterogeneity of cognitive phenotypes in PWH and their associated biological mechanisms to facilitate clinical management and tailored interventions.
Collapse
Affiliation(s)
| | | | | | | | | | | | | | | | | | | | - Dana Gabuzda
- Correspondence: Dana Gabuzda, MD, Department of Cancer Immunology and Virology, Dana-Farber Cancer Institute, Center for Life Science 1010, 450 Brookline Avenue, Boston, MA 02215 ()
| |
Collapse
|
25
|
Ayala L, Adler TJ, Seidlitz S, Wirkert S, Engels C, Seitel A, Sellner J, Aksenov A, Bodenbach M, Bader P, Baron S, Vemuri A, Wiesenfarth M, Schreck N, Mindroc D, Tizabi M, Pirmann S, Everitt B, Kopp-Schneider A, Teber D, Maier-Hein L. Spectral imaging enables contrast agent-free real-time ischemia monitoring in laparoscopic surgery. SCIENCE ADVANCES 2023; 9:eadd6778. [PMID: 36897951 PMCID: PMC10005169 DOI: 10.1126/sciadv.add6778] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 06/27/2022] [Accepted: 02/03/2023] [Indexed: 06/18/2023]
Abstract
Laparoscopic surgery has evolved as a key technique for cancer diagnosis and therapy. While characterization of the tissue perfusion is crucial in various procedures, such as partial nephrectomy, doing so by means of visual inspection remains highly challenging. We developed a laparoscopic real-time multispectral imaging system featuring a compact and lightweight multispectral camera and the possibility to complement the conventional surgical view of the patient with functional information at a video rate of 25 Hz. To enable contrast agent-free ischemia monitoring during laparoscopic partial nephrectomy, we phrase the problem of ischemia detection as an out-of-distribution detection problem that does not rely on data from any other patient and uses an ensemble of invertible neural networks at its core. An in-human trial demonstrates the feasibility of our approach and highlights the potential of spectral imaging combined with advanced deep learning-based analysis tools for fast, efficient, reliable, and safe functional laparoscopic imaging.
Collapse
Affiliation(s)
- Leonardo Ayala
- Division of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Medical Faculty, Heidelberg University, Heidelberg, Germany
| | - Tim J. Adler
- Division of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany
| | - Silvia Seidlitz
- Division of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany
- Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany
| | - Sebastian Wirkert
- Division of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | | | - Alexander Seitel
- Division of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Jan Sellner
- Division of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany
- Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany
| | | | | | - Pia Bader
- Städtisches Klinikum Karlsruhe, Karlsruhe, Germany
| | | | - Anant Vemuri
- Division of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Manuel Wiesenfarth
- Division of Biostatistics, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Nicholas Schreck
- Division of Biostatistics, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Diana Mindroc
- Division of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Minu Tizabi
- Division of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Sebastian Pirmann
- Division of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Brittaney Everitt
- Division of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | | | - Dogu Teber
- Städtisches Klinikum Karlsruhe, Karlsruhe, Germany
| | - Lena Maier-Hein
- Division of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Medical Faculty, Heidelberg University, Heidelberg, Germany
- Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany
- Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany
| |
Collapse
|
26
|
Adversarial confound regression and uncertainty measurements to classify heterogeneous clinical MRI in Mass General Brigham. PLoS One 2023; 18:e0277572. [PMID: 36862751 PMCID: PMC9980829 DOI: 10.1371/journal.pone.0277572] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2022] [Accepted: 10/29/2022] [Indexed: 03/03/2023] Open
Abstract
In this work, we introduce a novel deep learning architecture, MUCRAN (Multi-Confound Regression Adversarial Network), to train a deep learning model on clinical brain MRI while regressing demographic and technical confounding factors. We trained MUCRAN using 17,076 clinical T1 Axial brain MRIs collected from Massachusetts General Hospital before 2019 and demonstrated that MUCRAN could successfully regress major confounding factors in the vast clinical dataset. We also applied a method for quantifying uncertainty across an ensemble of these models to automatically exclude out-of-distribution data in AD detection. By combining MUCRAN and the uncertainty quantification method, we showed consistent and significant increases in the AD detection accuracy for newly collected MGH data (post-2019; 84.6% with MUCRAN vs. 72.5% without MUCRAN) and for data from other hospitals (90.3% from Brigham and Women's Hospital and 81.0% from other hospitals). MUCRAN offers a generalizable approach for deep-learning-based disease detection in heterogenous clinical data.
Collapse
|
27
|
Pombo G, Gray R, Cardoso MJ, Ourselin S, Rees G, Ashburner J, Nachev P. Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models. Med Image Anal 2023; 84:102723. [PMID: 36542907 PMCID: PMC10591114 DOI: 10.1016/j.media.2022.102723] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2021] [Revised: 11/21/2022] [Accepted: 12/02/2022] [Indexed: 12/12/2022]
Abstract
We describe CounterSynth, a conditional generative model of diffeomorphic deformations that induce label-driven, biologically plausible changes in volumetric brain images. The model is intended to synthesise counterfactual training data augmentations for downstream discriminative modelling tasks where fidelity is limited by data imbalance, distributional instability, confounding, or underspecification, and exhibits inequitable performance across distinct subpopulations. Focusing on demographic attributes, we evaluate the quality of synthesised counterfactuals with voxel-based morphometry, classification and regression of the conditioning attributes, and the Fréchet inception distance. Examining downstream discriminative performance in the context of engineered demographic imbalance and confounding, we use UK Biobank and OASIS magnetic resonance imaging data to benchmark CounterSynth augmentation against current solutions to these problems. We achieve state-of-the-art improvements, both in overall fidelity and equity. The source code for CounterSynth is available at https://github.com/guilherme-pombo/CounterSynth.
Collapse
Affiliation(s)
- Guilherme Pombo
- UCL Queen Square Institute of Neurology, University College London, London, UK.
| | - Robert Gray
- UCL Queen Square Institute of Neurology, University College London, London, UK
| | - M Jorge Cardoso
- School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK
| | - Sebastien Ourselin
- School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK
| | - Geraint Rees
- UCL Queen Square Institute of Neurology, University College London, London, UK
| | - John Ashburner
- UCL Queen Square Institute of Neurology, University College London, London, UK
| | - Parashkev Nachev
- UCL Queen Square Institute of Neurology, University College London, London, UK
| |
Collapse
|
28
|
Hong J, Hwang J, Lee JH. General psychopathology factor (p-factor) prediction using resting-state functional connectivity and a scanner-generalization neural network. J Psychiatr Res 2023; 158:114-125. [PMID: 36580867 DOI: 10.1016/j.jpsychires.2022.12.037] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/08/2022] [Revised: 12/09/2022] [Accepted: 12/20/2022] [Indexed: 12/24/2022]
Abstract
The general psychopathology factor (p-factor) represents shared variance across mental disorders based on psychopathologic symptoms. The Adolescent Brain Cognitive Development (ABCD) Study offers an unprecedented opportunity to investigate functional networks (FNs) from functional magnetic resonance imaging (fMRI) associated with the psychopathology of an adolescent cohort (n > 10,000). However, the heterogeneities associated with the use of multiple sites and multiple scanners in the ABCD Study need to be overcome to improve the prediction of the p-factor using fMRI. We proposed a scanner-generalization neural network (SGNN) to predict the individual p-factor by systematically reducing the scanner effect for resting-state functional connectivity (RSFC). We included 6905 adolescents from 18 sites whose fMRI data were collected using either Siemens or GE scanners. The p-factor was estimated based on the Child Behavior Checklist (CBCL) scores available in the ABCD study using exploratory factor analysis. We evaluated the Pearson's correlation coefficients (CCs) for p-factor prediction via leave-one/two-site-out cross-validation (LOSOCV/LTSOCV) and identified important FNs from the weight features (WFs) of the SGNN. The CCs were higher for the SGNN than for alternative models when using both LOSOCV (0.1631 ± 0.0673 for the SGNN vs. 0.1497 ± 0.0710 for kernel ridge regression [KRR]; p < 0.05 from a two-tailed paired t-test) and LTSOCV (0.1469 ± 0.0381 for the SGNN vs. 0.1394 ± 0.0359 for KRR; p = 0.01). It was found that (a) the default-mode and dorsal attention FNs were important for p-factor prediction, and (b) the intra-visual FN was important for scanner generalization. We demonstrated the efficacy of our novel SGNN model for p-factor prediction while simultaneously eliminating scanner-related confounding effects for RSFC.
Collapse
Affiliation(s)
- Jinwoo Hong
- Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea
| | - Jundong Hwang
- Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea
| | - Jong-Hwan Lee
- Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea.
| |
Collapse
|
29
|
West J, Dasht Bozorgi Z, Herron J, Chizeck HJ, Chambers JD, Li L. Machine learning seizure prediction: one problematic but accepted practice. J Neural Eng 2023; 20. [PMID: 36548993 DOI: 10.1088/1741-2552/acae09] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2022] [Accepted: 12/22/2022] [Indexed: 12/24/2022]
Abstract
Objective.Epilepsy is one of the most common neurological disorders and can have a devastating effect on a person's quality of life. As such, the search for markers which indicate an upcoming seizure is a critically important area of research which would allow either on-demand treatment or early warning for people suffering with these disorders. There is a growing body of work which uses machine learning methods to detect pre-seizure biomarkers from electroencephalography (EEG), however the high prediction rates published do not translate into the clinical setting. Our objective is to investigate a potential reason for this.Approach.We conduct an empirical study of a commonly used data labelling method for EEG seizure prediction which relies on labelling small windows of EEG data in temporal groups then selecting randomly from those windows to validate results. We investigate a confound for this approach for seizure prediction and demonstrate the ease at which it can be inadvertently learned by a machine learning system.Main results.We find that non-seizure signals can create decision surfaces for machine learning approaches which can result in false high prediction accuracy on validation datasets. We prove this by training an artificial neural network to learn fake seizures (fully decoupled from biology) in real EEG.Significance.The significance of our findings is that many existing works may be reporting results based on this confound and that future work should adhere to stricter requirements in mitigating this confound. The problematic, but commonly accepted approach in the literature for seizure prediction labelling is potentially preventing real advances in developing solutions for these sufferers. By adhering to the guidelines in this paper future work in machine learning seizure prediction is more likely to be clinically relevant.
Collapse
Affiliation(s)
- Joseph West
- School of Computing and Information Systems, University of Melbourne, Melbourne, Victoria, Australia.,Department of Biomedical Engineering, University of Melbourne, Melbourne, Victoria, Australia
| | - Zahra Dasht Bozorgi
- School of Computing and Information Systems, University of Melbourne, Melbourne, Victoria, Australia
| | - Jeffrey Herron
- Department of Neurological Surgery, University of Washington, Seattle, Washington, United States of America
| | - Howard J Chizeck
- Department of Electrical and Computer Engineering, University of Washington, Seattle, Washington, United States of America
| | - Jordan D Chambers
- Department of Biomedical Engineering, University of Melbourne, Melbourne, Victoria, Australia
| | - Lyra Li
- Department of Biomedical Engineering, University of Melbourne, Melbourne, Victoria, Australia
| |
Collapse
|
30
|
Chalikiopoulou C, Gómez-Tamayo JC, Katsila T. Untargeted Metabolomics for Disease-Specific Signatures. Methods Mol Biol 2023; 2571:71-81. [PMID: 36152151 DOI: 10.1007/978-1-0716-2699-3_7] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/16/2023]
Abstract
Human diseases account for complex traits that usually exhibit markedly diverse clinical manifestations coming from a series of pathogenic processes that shape heterogeneous phenotypes. Considering that correlation does not imply causation as well as population differences and/or inter-individual variability, disease-specific signatures are becoming critical for biomarker discovery. Untargeted metabolomics is deemed to be a powerful approach to delineate molecular pathways of prime interest. Metabotypes capture the interplay of genomics and environmental influences per se. Untargeted metabolomics share the charm of being not only hypothesis-driven but also hypothesis-generating. Notwithstanding, the applicability of untargeted metabolomics toward clinically relevant outcomes depend on wet- and dry-lab procedures in the context of elegant study designs with clear rationale. As ideal may be far from feasible, herein we provide recommendations to combat sample mishandling that adversely affect data outcomes and if so, deal with imbalanced datasets toward data integrity.
Collapse
Affiliation(s)
| | | | - Theodora Katsila
- Institute of Chemical Biology, National Hellenic Research Foundation, Athens, Greece.
| |
Collapse
|
31
|
Hamdan S, Love BC, von Polier GG, Weis S, Schwender H, Eickhoff SB, Patil KR. Confound-leakage: confound removal in machine learning leads to leakage. Gigascience 2022; 12:giad071. [PMID: 37776368 PMCID: PMC10541796 DOI: 10.1093/gigascience/giad071] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2023] [Revised: 06/01/2023] [Accepted: 08/17/2023] [Indexed: 10/02/2023] Open
Abstract
BACKGROUND Machine learning (ML) approaches are a crucial component of modern data analysis in many fields, including epidemiology and medicine. Nonlinear ML methods often achieve accurate predictions, for instance, in personalized medicine, as they are capable of modeling complex relationships between features and the target. Problematically, ML models and their predictions can be biased by confounding information present in the features. To remove this spurious signal, researchers often employ featurewise linear confound regression (CR). While this is considered a standard approach for dealing with confounding, possible pitfalls of using CR in ML pipelines are not fully understood. RESULTS We provide new evidence that, contrary to general expectations, linear confound regression can increase the risk of confounding when combined with nonlinear ML approaches. Using a simple framework that uses the target as a confound, we show that information leaked via CR can increase null or moderate effects to near-perfect prediction. By shuffling the features, we provide evidence that this increase is indeed due to confound-leakage and not due to revealing of information. We then demonstrate the danger of confound-leakage in a real-world clinical application where the accuracy of predicting attention-deficit/hyperactivity disorder is overestimated using speech-derived features when using depression as a confound. CONCLUSIONS Mishandling or even amplifying confounding effects when building ML models due to confound-leakage, as shown, can lead to untrustworthy, biased, and unfair predictions. Our expose of the confound-leakage pitfall and provided guidelines for dealing with it can help create more robust and trustworthy ML models.
Collapse
Affiliation(s)
- Sami Hamdan
- Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum Jülich, 52428 Jülich, Germany
- Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine University Düsseldorf, 40225 Düsseldorf, Germany
| | - Bradley C Love
- Department of Experimental Psychology, University College London, WC1H 0AP London, UK
- The Alan Turing Institute, London NW1 2DB, UK
- European Lab for Learning & Intelligent Systems (ELLIS), WC1E 6BT, London, UK
| | - Georg G von Polier
- Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum Jülich, 52428 Jülich, Germany
- Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, University Hospital Frankfurt, 60528 Frankfurt, Germany
- Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, RWTH Aachen University, 52074 Aachen, Germany
| | - Susanne Weis
- Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum Jülich, 52428 Jülich, Germany
- Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine University Düsseldorf, 40225 Düsseldorf, Germany
| | - Holger Schwender
- Institute of Mathematics, Heinrich-Heine University Düsseldorf, 40225 Düsseldorf, Germany
| | - Simon B Eickhoff
- Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum Jülich, 52428 Jülich, Germany
- Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine University Düsseldorf, 40225 Düsseldorf, Germany
| | - Kaustubh R Patil
- Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum Jülich, 52428 Jülich, Germany
- Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine University Düsseldorf, 40225 Düsseldorf, Germany
| |
Collapse
|
32
|
Weber KA, Teplin ZM, Wager TD, Law CSW, Prabhakar NK, Ashar YK, Gilam G, Banerjee S, Delp SL, Glover GH, Hastie TJ, Mackey S. Confounds in neuroimaging: A clear case of sex as a confound in brain-based prediction. Front Neurol 2022; 13:960760. [PMID: 36601297 PMCID: PMC9806266 DOI: 10.3389/fneur.2022.960760] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/03/2022] [Accepted: 11/25/2022] [Indexed: 12/23/2022] Open
Abstract
Muscle weakness is common in many neurological, neuromuscular, and musculoskeletal conditions. Muscle size only partially explains muscle strength as adaptions within the nervous system also contribute to strength. Brain-based biomarkers of neuromuscular function could provide diagnostic, prognostic, and predictive value in treating these disorders. Therefore, we sought to characterize and quantify the brain's contribution to strength by developing multimodal MRI pipelines to predict grip strength. However, the prediction of strength was not straightforward, and we present a case of sex being a clear confound in brain decoding analyses. While each MRI modality-structural MRI (i.e., gray matter morphometry), diffusion MRI (i.e., white matter fractional anisotropy), resting state functional MRI (i.e., functional connectivity), and task-evoked functional MRI (i.e., left or right hand motor task activation)-and a multimodal prediction pipeline demonstrated significant predictive power for strength (R 2 = 0.108-0.536, p ≤ 0.001), after correcting for sex, the predictive power was substantially reduced (R 2 = -0.038-0.075). Next, we flipped the analysis and demonstrated that each MRI modality and a multimodal prediction pipeline could significantly predict sex (accuracy = 68.0%-93.3%, AUC = 0.780-0.982, p < 0.001). However, correcting the brain features for strength reduced the accuracy for predicting sex (accuracy = 57.3%-69.3%, AUC = 0.615-0.780). Here we demonstrate the effects of sex-correlated confounds in brain-based predictive models across multiple brain MRI modalities for both regression and classification models. We discuss implications of confounds in predictive modeling and the development of brain-based MRI biomarkers, as well as possible strategies to overcome these barriers.
Collapse
Affiliation(s)
- Kenneth A. Weber
- Systems Neuroscience and Pain Lab, Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Palo Alto, CA, United States,*Correspondence: Kenneth A. Weber II
| | - Zachary M. Teplin
- Systems Neuroscience and Pain Lab, Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Palo Alto, CA, United States
| | - Tor D. Wager
- Department of Psychological and Brain Sciences, Dartmouth College, Hanover, NH, United States
| | - Christine S. W. Law
- Systems Neuroscience and Pain Lab, Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Palo Alto, CA, United States
| | - Nitin K. Prabhakar
- Division of Physical Medicine and Rehabilitation, Department of Orthopaedic Surgery, Stanford University School of Medicine, Palo Alto, CA, United States
| | - Yoni K. Ashar
- Department of Psychiatry, Weill Cornell Medicine, New York, NY, United States
| | - Gadi Gilam
- Systems Neuroscience and Pain Lab, Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Palo Alto, CA, United States,The Institute of Biomedical and Oral Research, Faculty of Dental Medicine, Hebrew University of Jerusalem, Jerusalem, Israel
| | | | - Scott L. Delp
- Department of Bioengineering and Mechanical Engineering, Stanford University, Palo Alto, CA, United States
| | - Gary H. Glover
- Radiological Sciences Laboratory, Department of Radiology, Stanford University School of Medicine, Palo Alto, CA, United States
| | - Trevor J. Hastie
- Department of Statistics, Stanford University, Palo Alto, CA, United States
| | - Sean Mackey
- Systems Neuroscience and Pain Lab, Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Palo Alto, CA, United States
| |
Collapse
|
33
|
Lazard T, Bataillon G, Naylor P, Popova T, Bidard FC, Stoppa-Lyonnet D, Stern MH, Decencière E, Walter T, Vincent-Salomon A. Deep learning identifies morphological patterns of homologous recombination deficiency in luminal breast cancers from whole slide images. Cell Rep Med 2022; 3:100872. [PMID: 36516847 PMCID: PMC9798078 DOI: 10.1016/j.xcrm.2022.100872] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/10/2021] [Revised: 01/04/2022] [Accepted: 11/22/2022] [Indexed: 12/15/2022]
Abstract
Homologous recombination DNA-repair deficiency (HRD) is becoming a well-recognized marker of platinum salt and polyADP-ribose polymerase inhibitor chemotherapies in ovarian and breast cancers. While large-scale screening for HRD using genomic markers is logistically and economically challenging, stained tissue slides are routinely acquired in clinical practice. With the objectives of providing a robust deep-learning method for HRD prediction from tissue slides and identifying related morphological phenotypes, we first show that digital pathology workflows are sensitive to potential biases in the training set, then we propose a method to overcome the influence of these biases, and we develop an interpretation method capable of identifying complex phenotypes. Application to our carefully curated in-house dataset allows us to predict HRD with high accuracy (area under the receiver-operator characteristics curve 0.86) and to identify morphological phenotypes related to HRD. In particular, the presence of laminated fibrosis and clear tumor cells associated with HRD open new hypotheses regarding its phenotypic impact.
Collapse
Affiliation(s)
- Tristan Lazard
- Center for Computational Biology (CBIO), Mines Paris, PSL University, 60 Boulevard Saint Michel, 75006 Paris, France,Institut Curie, PSL University, 75005 Paris, France,INSERM U900, 75005 Paris, France
| | - Guillaume Bataillon
- Institut Curie, PSL University, 75005 Paris, France,INSERM U900, 75005 Paris, France,Diagnostic and Theranostic Medicine Division, Institut Curie, PSL University, Paris, France
| | - Peter Naylor
- Center for Computational Biology (CBIO), Mines Paris, PSL University, 60 Boulevard Saint Michel, 75006 Paris, France,Institut Curie, PSL University, 75005 Paris, France,INSERM U900, 75005 Paris, France
| | - Tatiana Popova
- INSERM U830, DNA Repair and Uveal Melanoma (DRUM), Equipe Labellisée par la Ligue Nationale Contre le Cancer, Institut Curie, PSL Research University, 75005 Paris, France
| | - François-Clément Bidard
- Department of Medical Oncology, Institut Curie, Université de Versailles Saint-Quentin, Saint-Cloud, France,INSERM CIC-BT 1428, Institut Curie, Paris, France
| | - Dominique Stoppa-Lyonnet
- INSERM U830, DNA Repair and Uveal Melanoma (DRUM), Equipe Labellisée par la Ligue Nationale Contre le Cancer, Institut Curie, PSL Research University, 75005 Paris, France,Université Paris Cité, 75006 Paris, France
| | - Marc-Henri Stern
- Diagnostic and Theranostic Medicine Division, Institut Curie, PSL University, Paris, France,INSERM U830, DNA Repair and Uveal Melanoma (DRUM), Equipe Labellisée par la Ligue Nationale Contre le Cancer, Institut Curie, PSL Research University, 75005 Paris, France
| | - Etienne Decencière
- Center for Mathematical Morphology (CMM), Mines Paris, PSL University, 77300 Fontainebleau, France
| | - Thomas Walter
- Center for Computational Biology (CBIO), Mines Paris, PSL University, 60 Boulevard Saint Michel, 75006 Paris, France,Institut Curie, PSL University, 75005 Paris, France,INSERM U900, 75005 Paris, France,Corresponding author
| | - Anne Vincent-Salomon
- Diagnostic and Theranostic Medicine Division, Institut Curie, PSL University, Paris, France,INSERM U934, CNRS UMR 3215, Paris, France,Corresponding author
| |
Collapse
|
34
|
Chen ZS, Kulkarni P(P, Galatzer-Levy IR, Bigio B, Nasca C, Zhang Y. Modern views of machine learning for precision psychiatry. PATTERNS (NEW YORK, N.Y.) 2022; 3:100602. [PMID: 36419447 PMCID: PMC9676543 DOI: 10.1016/j.patter.2022.100602] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/13/2022]
Abstract
In light of the National Institute of Mental Health (NIMH)'s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. We further review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We also discuss explainable AI (XAI) and neuromodulation in a closed human-in-the-loop manner and highlight the ML potential in multi-media information extraction and multi-modal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.
Collapse
Affiliation(s)
- Zhe Sage Chen
- Department of Psychiatry, New York University Grossman School of Medicine, New York, NY 10016, USA
- Department of Neuroscience and Physiology, New York University Grossman School of Medicine, New York, NY 10016, USA
- The Neuroscience Institute, New York University Grossman School of Medicine, New York, NY 10016, USA
- Department of Biomedical Engineering, New York University Tandon School of Engineering, Brooklyn, NY 11201, USA
| | | | - Isaac R. Galatzer-Levy
- Department of Psychiatry, New York University Grossman School of Medicine, New York, NY 10016, USA
- Meta Reality Lab, New York, NY, USA
| | - Benedetta Bigio
- Department of Psychiatry, New York University Grossman School of Medicine, New York, NY 10016, USA
| | - Carla Nasca
- Department of Psychiatry, New York University Grossman School of Medicine, New York, NY 10016, USA
- The Neuroscience Institute, New York University Grossman School of Medicine, New York, NY 10016, USA
| | - Yu Zhang
- Department of Bioengineering, Lehigh University, Bethlehem, PA 18015, USA
- Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, PA 18015, USA
| |
Collapse
|
35
|
Deng J, Yang J, Hou L, Wu J, He Y, Zhao M, Ni B, Wei D, Pfister H, Zhou C, Jiang T, She Y, Wu C, Chen C. Genopathomic profiling identifies signatures for immunotherapy response of lung adenocarcinoma via confounder-aware representation learning. iScience 2022; 25:105382. [PMCID: PMC9636035 DOI: 10.1016/j.isci.2022.105382] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2022] [Revised: 07/18/2022] [Accepted: 10/12/2022] [Indexed: 11/06/2022] Open
Affiliation(s)
- Jiajun Deng
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, P.R. China
| | - Jiancheng Yang
- Shanghai Jiao Tong University, Shanghai, P.R. China
- MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, P.R. China
- Dianei Technology, Shanghai, P.R. China
| | - Likun Hou
- Department of Pathology, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, P.R. China
| | - Junqi Wu
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, P.R. China
| | - Yi He
- Dianei Technology, Shanghai, P.R. China
| | - Mengmeng Zhao
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, P.R. China
| | - Bingbing Ni
- Shanghai Jiao Tong University, Shanghai, P.R. China
- MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, P.R. China
- Huawei Hisilicon, Shanghai, P.R. China
| | | | | | - Caicun Zhou
- Department of Medical Oncology, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, P.R. China
| | - Tao Jiang
- Department of Medical Oncology, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, P.R. China
| | - Yunlang She
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, P.R. China
- Corresponding author
| | - Chunyan Wu
- Department of Pathology, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, P.R. China
- Corresponding author
| | - Chang Chen
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, P.R. China
- The First Hospital of Lanzhou University, Gansu, P.R. China
- The International Science and Technology Cooperation Base for Development and Application of Key Technologies in Thoracic Surgery, Gansu, P.R. China
- Corresponding author
| |
Collapse
|
36
|
Bayer JMM, Thompson PM, Ching CRK, Liu M, Chen A, Panzenhagen AC, Jahanshad N, Marquand A, Schmaal L, Sämann PG. Site effects how-to and when: An overview of retrospective techniques to accommodate site effects in multi-site neuroimaging analyses. Front Neurol 2022; 13:923988. [PMID: 36388214 PMCID: PMC9661923 DOI: 10.3389/fneur.2022.923988] [Citation(s) in RCA: 20] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2022] [Accepted: 08/12/2022] [Indexed: 09/12/2023] Open
Abstract
Site differences, or systematic differences in feature distributions across multiple data-acquisition sites, are a known source of heterogeneity that may adversely affect large-scale meta- and mega-analyses of independently collected neuroimaging data. They influence nearly all multi-site imaging modalities and biomarkers, and methods to compensate for them can improve reliability and generalizability in the analysis of genetics, omics, and clinical data. The origins of statistical site effects are complex and involve both technical differences (scanner vendor, head coil, acquisition parameters, imaging processing) and differences in sample characteristics (inclusion/exclusion criteria, sample size, ancestry) between sites. In an age of expanding international consortium research, there is a growing need to disentangle technical site effects from sample characteristics of interest. Numerous statistical and machine learning methods have been developed to control for, model, or attenuate site effects - yet to date, no comprehensive review has discussed the benefits and drawbacks of each for different use cases. Here, we provide an overview of the different existing statistical and machine learning methods developed to remove unwanted site effects from independently collected neuroimaging samples. We focus on linear mixed effect models, the ComBat technique and its variants, adjustments based on image quality metrics, normative modeling, and deep learning approaches such as generative adversarial networks. For each method, we outline the statistical foundation and summarize strengths and weaknesses, including their assumptions and conditions of use. We provide information on software availability and comment on the ease of use and the applicability of these methods to different types of data. We discuss validation and comparative reports, mention caveats and provide guidance on when to use each method, depending on context and specific research questions.
Collapse
Affiliation(s)
- Johanna M. M. Bayer
- Centre for Youth Mental Health, University of Melbourne, Melbourne, VIC, Australia
- Orygen, Parkville, VIC, Australia
| | - Paul M. Thompson
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States
| | - Christopher R. K. Ching
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States
| | - Mengting Liu
- School of Biomedical Engineering, Sun Yat-sen University, Shenzhen, China
| | - Andrew Chen
- Department of Biostatistics, Epidemiology, and Informatics, Penn Statistics in Imaging and Visualization Center, University of Pennsylvania, Philadelphia, PA, United States
- Center for Biomedical Image Computing and Analytics, University of Pennsylvania, Philadelphia, PA, United States
| | - Alana C. Panzenhagen
- Programa de Pós-graduação em Ciências Biológicas: Bioquímica, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil
- Department of Translational Psychiatry, Max Planck Institute of Psychiatry, Munich, Germany
| | - Neda Jahanshad
- Laboratory of Brain eScience, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of USC, University of Southern California, Marina del Rey, CA, United States
| | - Andre Marquand
- Department of Cognitive Neuroscience, Donders Institute for Brain, Cognition and Behavior, Radboudumc, Nijmegen, Netherlands
| | - Lianne Schmaal
- Centre for Youth Mental Health, University of Melbourne, Melbourne, VIC, Australia
- Orygen, Parkville, VIC, Australia
| | | |
Collapse
|
37
|
You S, Reyes M. Influence of contrast and texture based image modifications on the performance and attention shift of U-Net models for brain tissue segmentation. FRONTIERS IN NEUROIMAGING 2022; 1:1012639. [PMID: 37555149 PMCID: PMC10406260 DOI: 10.3389/fnimg.2022.1012639] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/05/2022] [Accepted: 10/12/2022] [Indexed: 08/10/2023]
Abstract
Contrast and texture modifications applied during training or test-time have recently shown promising results to enhance the generalization performance of deep learning segmentation methods in medical image analysis. However, a deeper understanding of this phenomenon has not been investigated. In this study, we investigated this phenomenon using a controlled experimental setting, using datasets from the Human Connectome Project and a large set of simulated MR protocols, in order to mitigate data confounders and investigate possible explanations as to why model performance changes when applying different levels of contrast and texture-based modifications. Our experiments confirm previous findings regarding the improved performance of models subjected to contrast and texture modifications employed during training and/or testing time, but further show the interplay when these operations are combined, as well as the regimes of model improvement/worsening across scanning parameters. Furthermore, our findings demonstrate a spatial attention shift phenomenon of trained models, occurring for different levels of model performance, and varying in relation to the type of applied image modification.
Collapse
Affiliation(s)
- Suhang You
- Medical Image Analysis Group, ARTORG, Graduate School for Cellular and Biomedical Sciences, University of Bern, Bern, Switzerland
| | | |
Collapse
|
38
|
Patcas R, Bornstein MM, Schätzle MA, Timofte R. Artificial intelligence in medico-dental diagnostics of the face: a narrative review of opportunities and challenges. Clin Oral Investig 2022; 26:6871-6879. [DOI: 10.1007/s00784-022-04724-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2022] [Accepted: 09/14/2022] [Indexed: 11/24/2022]
Abstract
Abstract
Objectives
This review aims to share the current developments of artificial intelligence (AI) solutions in the field of medico-dental diagnostics of the face. The primary focus of this review is to present the applicability of artificial neural networks (ANN) to interpret medical images, together with the associated opportunities, obstacles, and ethico-legal concerns.
Material and methods
Narrative literature review.
Results
Narrative literature review.
Conclusion
Curated facial images are widely available and easily accessible and are as such particularly suitable big data for ANN training. New AI solutions have the potential to change contemporary dentistry by optimizing existing processes and enriching dental care with the introduction of new tools for assessment or treatment planning. The analyses of health-related big data may also contribute to revolutionize personalized medicine through the detection of previously unknown associations. In regard to facial images, advances in medico-dental AI-based diagnostics include software solutions for the detection and classification of pathologies, for rating attractiveness and for the prediction of age or gender. In order for an ANN to be suitable for medical diagnostics of the face, the arising challenges regarding computation and management of the software are discussed, with special emphasis on the use of non-medical big data for ANN training. The legal and ethical ramifications of feeding patients’ facial images to a neural network for diagnostic purposes are related to patient consent, data privacy, data security, liability, and intellectual property. Current ethico-legal regulation practices seem incapable of addressing all concerns and ensuring accountability.
Clinical significance
While this review confirms the many benefits derived from AI solutions used for the diagnosis of medical images, it highlights the evident lack of regulatory oversight, the urgent need to establish licensing protocols, and the imperative to investigate the moral quality of new norms set with the implementation of AI applications in medico-dental diagnostics.
Collapse
|
39
|
Identification of key somatic oncogenic mutation based on a confounder-free causal inference model. PLoS Comput Biol 2022; 18:e1010529. [PMID: 36137089 PMCID: PMC9499235 DOI: 10.1371/journal.pcbi.1010529] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2022] [Accepted: 08/31/2022] [Indexed: 11/30/2022] Open
Abstract
Abnormal cell proliferation and epithelial-mesenchymal transition (EMT) are the essential events that induce cancer initiation and progression. A fundamental goal in cancer research is to develop an efficient method to detect mutational genes capable of driving cancer. Although several computational methods have been proposed to identify these key mutations, many of them focus on the association between genetic mutations and functional changes in relevant biological processes, but not their real causality. Causal effect inference provides a way to estimate the real induce effect of a certain mutation on vital biological processes of cancer initiation and progression, through addressing the confounder bias due to neutral mutations and unobserved latent variables. In this study, integrating genomic and transcriptomic data, we construct a novel causal inference model based on a deep variational autoencoder to identify key oncogenic somatic mutations. Applied to 10 cancer types, our method quantifies the causal effect of genetic mutations on cell proliferation and EMT by reducing both observed and unobserved confounding biases. The experimental results indicate that genes with higher mutation frequency do not necessarily mean they are more potent in inducing cancer and promoting cancer development. Moreover, our study fills a gap in the use of machine learning for causal inference to identify oncogenic mutations. Identifying key mutations of cancers is helpful to better understand the mechanisms of cancer cell transformation and is critical for therapeutic approaches. Besides sequence and structure-based computational approaches, some functional impact-based methods which consider the association between mutation events and the activity of cancer-related biological processes have also been developed to detect key mutations. However, these methods mainly consider the correlation but ignore that the correlation is far from causality due to the existence of observed and unobserved confounding factors. We develop a confounder-free machine learning-based causal inference framework to estimate the causal effect of mutations on abnormal cell proliferation and epithelial-mesenchymal transition (EMT). It fills a gap in the use of causal mechanisms to discover potential driver mutations in cancer biological systems. Applying our method to 10 cancer types, the identified key mutations are highly consistent with public well-verified ones. Additionally, some new key mutations have also been discovered.
Collapse
|
40
|
Vento A, Zhao Q, Paul R, Pohl K, Adeli E. A Penalty Approach for Normalizing Feature Distributions to Build Confounder-Free Models. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION : MICCAI ... INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION 2022; 13433:387-397. [PMID: 36331278 PMCID: PMC9629333 DOI: 10.1007/978-3-031-16437-8_37] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/16/2023]
Abstract
Translating the use of modern machine learning algorithms into clinical applications requires settling challenges related to explain-ability and management of nuanced confounding factors. To suitably interpret the results, removing or explaining the effect of confounding variables (or metadata) is essential. Confounding variables affect the relationship between input training data and target outputs. Accordingly, when we train a model on such data, confounding variables will bias the distribution of the learned features. A recent promising solution, Meta-Data Normalization (MDN), estimates the linear relationship between the metadata and each feature based on a non-trainable closed-form solution. However, this estimation is confined by the sample size of a mini-batch and thereby may result in an oscillating performance. In this paper, we extend the MDN method by applying a Penalty approach (referred to as PDMN). We cast the problem into a bi-level nested optimization problem. We then approximate that objective using a penalty method so that the linear parameters within the MDN layer are trainable and learned on all samples. This enables PMDN to be plugged into any architectures, even those unfit to run batch-level operations such as transformers and recurrent models. We show improvement in model accuracy and independence from the confounders using PMDN over MDN in a synthetic experiment and a multi-label, multi-site classification of magnetic resonance images.
Collapse
Affiliation(s)
| | | | - Robert Paul
- Missouri Institute of Mental Health, St. Louis MO 63121, USA
| | - Kilian Pohl
- Stanford University, Stanford CA 94305, USA
- SRI International, Menlo Park CA 94025, USA
| | | |
Collapse
|
41
|
Conditional generation of medical time series for extrapolation to underrepresented populations. PLOS DIGITAL HEALTH 2022; 1:e0000074. [PMID: 36812549 PMCID: PMC9931259 DOI: 10.1371/journal.pdig.0000074] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/15/2022] [Accepted: 06/10/2022] [Indexed: 11/19/2022]
Abstract
The widespread adoption of electronic health records (EHRs) and subsequent increased availability of longitudinal healthcare data has led to significant advances in our understanding of health and disease with direct and immediate impact on the development of new diagnostics and therapeutic treatment options. However, access to EHRs is often restricted due to their perceived sensitive nature and associated legal concerns, and the cohorts therein typically are those seen at a specific hospital or network of hospitals and therefore not representative of the wider population of patients. Here, we present HealthGen, a new approach for the conditional generation of synthetic EHRs that maintains an accurate representation of real patient characteristics, temporal information and missingness patterns. We demonstrate experimentally that HealthGen generates synthetic cohorts that are significantly more faithful to real patient EHRs than the current state-of-the-art, and that augmenting real data sets with conditionally generated cohorts of underrepresented subpopulations of patients can significantly enhance the generalisability of models derived from these data sets to different patient populations. Synthetic conditionally generated EHRs could help increase the accessibility of longitudinal healthcare data sets and improve the generalisability of inferences made from these data sets to underrepresented populations.
Collapse
|
42
|
Shenoy S, Rajan AK, Rashid M, Chandran VP, Poojari PG, Kunhikatta V, Acharya D, Nair S, Varma M, Thunga G. Artificial intelligence in differentiating tropical infections: A step ahead. PLoS Negl Trop Dis 2022; 16:e0010455. [PMID: 35771774 PMCID: PMC9246149 DOI: 10.1371/journal.pntd.0010455] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2022] [Accepted: 04/29/2022] [Indexed: 11/19/2022] Open
Abstract
Background and objective Differentiating tropical infections are difficult due to its homogenous nature of clinical and laboratorial presentations among them. Sophisticated differential tests and prediction tools are better ways to tackle this issue. Here, we aimed to develop a clinician assisted decision making tool to differentiate the common tropical infections. Methodology A cross sectional study through 9 item self-administered questionnaire were performed to understand the need of developing a decision making tool and its parameters. The most significant differential parameters among the identified infections were measured through a retrospective study and decision tree was developed. Based on the parameters identified, a multinomial logistic regression model and a machine learning model were developed which could better differentiate the infection. Results A total of 40 physicians involved in the management of tropical infections were included for need analysis. Dengue, malaria, leptospirosis and scrub typhus were the common tropical infections in our settings. Sodium, total bilirubin, albumin, lymphocytes and platelets were the laboratory parameters; and abdominal pain, arthralgia, myalgia and urine output were the clinical presentation identified as better predictors. In multinomial logistic regression analysis with dengue as a reference revealed a predictability of 60.7%, 62.5% and 66% for dengue, malaria and leptospirosis, respectively, whereas, scrub typhus showed only 38% of predictability. The multi classification machine learning model observed to have an overall predictability of 55–60%, whereas a binary classification machine learning algorithms showed an average of 79–84% for one vs other and 69–88% for one vs one disease category. Conclusion This is a first of its kind study where both statistical and machine learning approaches were explored simultaneously for differentiating tropical infections. Machine learning techniques in healthcare sectors will aid in early detection and better patient care. Distinguishing tropical infections is difficult due to its homogeneous nature from clinical and laboratory presentations among them. This is a first of its kind study where both statistical and machine learning approaches were explored simultaneously for differentiating tropical infections. Dengue, malaria, leptospirosis and scrub typhus were the common tropical infections in our settings as per the need analysis. Better predictors in terms of laboratory parameters and clinical presentations were identified from retrospective analysis and used for the regression and machine learning models. The parameters such as accuracy, true positive rate/sensitivity/recall, false positive rate, precision/positive predictive value, F-measure and ROC area for both the training and validation sets (10-fold cross validation) for all modelling approaches and diseases (One vs One and One vs others) were calculated. All the models observed to have an acceptable range of model performance in differentiating tropical infections. Albumin can be considered as the main parameter in differentiating these tropical infections. These models should be implemented in daily clinical routine practice via mobile or desktop assisted applications or tools.
Collapse
Affiliation(s)
- Shreelaxmi Shenoy
- Department of Pharmacy Practice, Manipal College of Pharmaceutical Sciences, Manipal Academy of Higher Education, Manipal, India
| | - Asha K. Rajan
- Department of Pharmacy Practice, Manipal College of Pharmaceutical Sciences, Manipal Academy of Higher Education, Manipal, India
| | - Muhammed Rashid
- Department of Pharmacy Practice, Manipal College of Pharmaceutical Sciences, Manipal Academy of Higher Education, Manipal, India
| | - Viji Pulikkel Chandran
- Department of Pharmacy Practice, Manipal College of Pharmaceutical Sciences, Manipal Academy of Higher Education, Manipal, India
| | - Pooja Gopal Poojari
- Department of Pharmacy Practice, Manipal College of Pharmaceutical Sciences, Manipal Academy of Higher Education, Manipal, India
| | - Vijayanarayana Kunhikatta
- Department of Pharmacy Practice, Manipal College of Pharmaceutical Sciences, Manipal Academy of Higher Education, Manipal, India
| | - Dinesh Acharya
- Department of Computer Science & Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India
| | - Sreedharan Nair
- Department of Pharmacy Practice, Manipal College of Pharmaceutical Sciences, Manipal Academy of Higher Education, Manipal, India
| | - Muralidhar Varma
- Department of Infectious Diseases, Kasturba Medical College, Manipal Academy of Higher Education, Manipal, India
| | - Girish Thunga
- Department of Pharmacy Practice, Manipal College of Pharmaceutical Sciences, Manipal Academy of Higher Education, Manipal, India
- * E-mail:
| |
Collapse
|
43
|
Hierarchical confounder discovery in the experiment-machine learning cycle. PATTERNS 2022; 3:100451. [PMID: 35465234 PMCID: PMC9024009 DOI: 10.1016/j.patter.2022.100451] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/16/2021] [Revised: 11/28/2021] [Accepted: 01/26/2022] [Indexed: 01/22/2023]
Abstract
The promise of machine learning (ML) to extract insights from high-dimensional datasets is tempered by confounding variables. It behooves scientists to determine if a model has extracted the desired information or instead fallen prey to bias. Due to features of natural phenomena and experimental design constraints, bioscience datasets are often organized in nested hierarchies that obfuscate the origins of confounding effects and render confounder amelioration methods ineffective. We propose a non-parametric statistical method called the rank-to-group (RTG) score that identifies hierarchical confounder effects in raw data and ML-derived embeddings. We show that RTG scores correctly assign the effects of hierarchical confounders when linear methods fail. In a public biomedical image dataset, we discover unreported effects of experimental design. We then use RTG scores to discover crossmodal correlated variability in a multi-phenotypic biological dataset. This approach should be generally useful in experiment-analysis cycles and to ensure confounder robustness in ML models. Hierarchical confounder effects in complex datasets can bias ML models RTG scoring identifies confounding variables in real-world biomedical data RTG scoring can be used to guide model debiasing and inform experimental design
The promise of using machine learning (ML) to extract insights from high-dimensional data is tempered by the frequent presence of confounding variables. For example, models attempting to identify biomarkers of disease can be severely biased by disease-irrelevant features, such as the physical site where an experiment is performed. While we have many tools to grapple with known confounders, we lack a general method to identify which of a set of potential confounders warrant debiasing. Here, we present a simple non-parametric statistical method called the rank-to-group (RTG) score, which identifies hierarchical confounder effects in raw data and ML-derived data embeddings. We show that RTG scoring identifies previously unreported effects of experimental design in a public dataset and uncovers cross-model correlated variability in a multi-phenotypic biological dataset. This approach should be of general use in experiment-analysis cycles and to ensure confounder robustness in ML models.
Collapse
|
44
|
Chyzhyk D, Varoquaux G, Milham M, Thirion B. How to remove or control confounds in predictive models, with applications to brain biomarkers. Gigascience 2022; 11:giac014. [PMID: 35277962 PMCID: PMC8917515 DOI: 10.1093/gigascience/giac014] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2021] [Revised: 09/19/2021] [Indexed: 12/30/2022] Open
Abstract
BACKGROUND With increasing data sizes and more easily available computational methods, neurosciences rely more and more on predictive modeling with machine learning, e.g., to extract disease biomarkers. Yet, a successful prediction may capture a confounding effect correlated with the outcome instead of brain features specific to the outcome of interest. For instance, because patients tend to move more in the scanner than controls, imaging biomarkers of a disease condition may mostly reflect head motion, leading to inefficient use of resources and wrong interpretation of the biomarkers. RESULTS Here we study how to adapt statistical methods that control for confounds to predictive modeling settings. We review how to train predictors that are not driven by such spurious effects. We also show how to measure the unbiased predictive accuracy of these biomarkers, based on a confounded dataset. For this purpose, cross-validation must be modified to account for the nuisance effect. To guide understanding and practical recommendations, we apply various strategies to assess predictive models in the presence of confounds on simulated data and population brain imaging settings. Theoretical and empirical studies show that deconfounding should not be applied to the train and test data jointly: modeling the effect of confounds, on the training data only, should instead be decoupled from removing confounds. CONCLUSIONS Cross-validation that isolates nuisance effects gives an additional piece of information: confound-free prediction accuracy.
Collapse
Affiliation(s)
- Darya Chyzhyk
- Parietal project-team, INRIA Saclay-île de France, France
- CEA/Neurospin bât 145, 91191 Gif-Sur-Yvette, France
- Center for the Developing Brain, Child Mind Institute, New York, NY 10022, USA
| | - Gaël Varoquaux
- Parietal project-team, INRIA Saclay-île de France, France
- CEA/Neurospin bât 145, 91191 Gif-Sur-Yvette, France
| | - Michael Milham
- Center for the Developing Brain, Child Mind Institute, New York, NY 10022, USA
- Center for Biomedical Imaging and Neuromodulation, Nathan S. Kline Institute for Psychiatric Research, Orangeburg, NY 10962, USA
| | - Bertrand Thirion
- Parietal project-team, INRIA Saclay-île de France, France
- CEA/Neurospin bât 145, 91191 Gif-Sur-Yvette, France
| |
Collapse
|
45
|
Kartal E. A Comprehensive Study on Bias in Artificial Intelligence Systems. INTERNATIONAL JOURNAL OF INTELLIGENT INFORMATION TECHNOLOGIES 2022. [DOI: 10.4018/ijiit.309582] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
Humans are social beings. Emotions, like their thoughts, play an essential role in decision-making. Today, artificial intelligence (AI) raises expectations for faster, more accurate, more rational, and fairer decisions with technological advancements. As a result, AI systems have often been seen as an ideal decision-making mechanism. But what if these systems decide against you based on gender, race, or other characteristics? Biased or unbiased AI, that's the question! The motivation of this study is to raise awareness among researchers about bias in AI and contribute to the advancement of AI studies and systems. As the primary purpose of this study is to examine bias in the decision-making process of AI systems, this paper focused on (1) bias in humans and AI, (2) the factors that lead to bias in AI systems, (3) current examples of bias in AI systems, and (4) various methods and recommendations to mitigate bias in AI systems.
Collapse
Affiliation(s)
- Elif Kartal
- Faculty of Economics, Istanbul University, Turkey
| |
Collapse
|
46
|
Turnbull A, Kaplan R, Adeli E, Lin FV. A Novel Explainability Approach for Technology-Driven Translational Research on Brain Aging. J Alzheimers Dis 2022; 88:1229-1239. [PMID: 35754280 PMCID: PMC9399001 DOI: 10.3233/jad-220441] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/03/2023]
Abstract
Brain aging leads to difficulties in functional independence. Mitigating these difficulties can benefit from technology that predicts, monitors, and modifies brain aging. Translational research prioritizes solutions that can be causally linked to specific pathophysiologies at the same time as demonstrating improvements in impactful real-world outcome measures. This poses a challenge for brain aging technology that needs to address the tension between mechanism-driven precision and clinical relevance. In the current opinion, by synthesizing emerging mechanistic, translational, and clinical research-related frameworks, and our own development of technology-driven brain aging research, we suggest incorporating the appreciation of four desiderata (causality, informativeness, transferability, and fairness) of explainability into early-stage research that designs and tests brain aging technology. We apply a series of work on electrocardiography-based "peripheral" neuroplasticity markers from our work as an illustration of our proposed approach. We believe this novel approach will promote the development and adoption of brain aging technology that links and addresses brain pathophysiology and functional independence in the field of translational research.
Collapse
Affiliation(s)
- Adam Turnbull
- Department of Psychiatry and Behavioral Sciences, Stanford University, CA, USA
- School of Nursing, University of Rochester Medical Center, NY, USA
| | - Robert Kaplan
- Clinical Excellence Research Center (CERC), Stanford University, CA, USA
| | - Ehsan Adeli
- Department of Psychiatry and Behavioral Sciences, Stanford University, CA, USA
- Wu Tsai Neurosciences Institute, Stanford University, CA, USA
| | - Feng V. Lin
- Department of Psychiatry and Behavioral Sciences, Stanford University, CA, USA
- Wu Tsai Neurosciences Institute, Stanford University, CA, USA
| |
Collapse
|
47
|
Zhang J, Zhao Q, Adeli E, Pfefferbaum A, Sullivan EV, Paul R, Valcour V, Pohl KM. Multi-label, multi-domain learning identifies compounding effects of HIV and cognitive impairment. Med Image Anal 2022; 75:102246. [PMID: 34706304 PMCID: PMC8678333 DOI: 10.1016/j.media.2021.102246] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2021] [Revised: 09/12/2021] [Accepted: 09/14/2021] [Indexed: 01/03/2023]
Abstract
Older individuals infected by Human Immunodeficiency Virus (HIV) are at risk for developing HIV-Associated Neurocognitive Disorder (HAND), i.e., from reduced cognitive functioning similar to HIV-negative individuals with Mild Cognitive Impairment (MCI) or to Alzheimer's Disease (AD) if more severely affected. Incompletely understood is how brain structure can serve to differentiate cognitive impairment (CI) in the HIV-positive (i.e., HAND) from the HIV-negative cohort (i.e., MCI and AD). To that end, we designed a multi-label classifier that labels the structural magnetic resonance images (MRI) of individuals by their HIV and CI status via two binary variables. Proper training of such an approach traditionally requires well-curated datasets containing large number of samples for each of the corresponding four cohorts (healthy controls, CI HIV-negative adults a.k.a. CI-only, HIV-positive patients without CI a.k.a. HIV-only, and HAND). Because of the rarity of such datasets, we proposed to improve training of the multi-label classifier via a multi-domain learning scheme that also incorporates domain-specific classifiers on auxiliary single-label datasets specific to either binary label. Specifically, we complement the training dataset of MRIs of the four cohorts (Control: 156, CI-only: 335, HIV-only: 37, HAND: 145) acquired by the Memory and Aging Center at the University of California - San Francisco with a CI-specific dataset only containing MRIs of HIV-negative subjects (Controls: 229, CI-only: 397) from the Alzheimer's Disease Neuroimaging Initiative and an HIV-specific dataset (Controls: 75, HIV-only: 75) provided by SRI International. Based on cross-validation on the UCSF dataset, the multi-domain and multi-label learning strategy leads to superior classification accuracy compared with one-domain or multi-class learning approaches, specifically for the undersampled HIV-only cohort. The 'prediction logits' of CI computed by the multi-label formulation also successfully stratify motor performance among the HIV-positive subjects (including HAND). Finally, brain patterns driving the subject-level predictions across all four cohorts characterize the independent and compounding effects of HIV and CI in the HAND cohort.
Collapse
Affiliation(s)
- Jiequan Zhang
- Department of Psychiatry & Behavioral Sciences, Stanford University, Stanford, CA 94305
| | - Qingyu Zhao
- Department of Psychiatry & Behavioral Sciences, Stanford University, Stanford, CA 94305
| | - Ehsan Adeli
- Department of Psychiatry & Behavioral Sciences, Stanford University, Stanford, CA 94305
| | - Adolf Pfefferbaum
- Department of Psychiatry & Behavioral Sciences, Stanford University, Stanford, CA 94305,Center for Biomedical Sciences, SRI International, Menlo Park, CA 94205
| | - Edith V. Sullivan
- Department of Psychiatry & Behavioral Sciences, Stanford University, Stanford, CA 94305
| | - Robert Paul
- Missouri Institute of Mental Health - St. Louis, MO 63134
| | - Victor Valcour
- Memory and Aging Center, University of California - San Francisco, San Fransisco, CA 94158
| | - Kilian M. Pohl
- Department of Psychiatry & Behavioral Sciences, Stanford University, Stanford, CA 94305,Center for Biomedical Sciences, SRI International, Menlo Park, CA 94205,Corresponding author: (Kilian M. Pohl)
| |
Collapse
|
48
|
Liu L, Zhang J, Wang JX, Xiong S, Zhang H. Co-optimization Learning Network for MRI Segmentation of Ischemic Penumbra Tissues. Front Neuroinform 2021; 15:782262. [PMID: 34975444 PMCID: PMC8717777 DOI: 10.3389/fninf.2021.782262] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2021] [Accepted: 11/25/2021] [Indexed: 11/17/2022] Open
Abstract
Convolutional neural networks (CNNs) have brought hope for the medical image auxiliary diagnosis. However, the shortfall of labeled medical image data is the bottleneck that limits the performance improvement of supervised CNN methods. In addition, annotating a large number of labeled medical image data is often expensive and time-consuming. In this study, we propose a co-optimization learning network (COL-Net) for Magnetic Resonance Imaging (MRI) segmentation of ischemic penumbra tissues. COL-Net base on the limited labeled samples and consists of an unsupervised reconstruction network (R), a supervised segmentation network (S), and a transfer block (T). The reconstruction network extracts the robust features from reconstructing pseudo unlabeled samples, which is the auxiliary branch of the segmentation network. The segmentation network is used to segment the target lesions under the limited labeled samples and the auxiliary of the reconstruction network. The transfer block is used to co-optimization the feature maps between the bottlenecks of the reconstruction network and segmentation network. We propose a mix loss function to optimize COL-Net. COL-Net is verified on the public ischemic penumbra segmentation challenge (SPES) with two dozen labeled samples. Results demonstrate that COL-Net has high predictive accuracy and generalization with the Dice coefficient of 0.79. The extended experiment also shows COL-Net outperforms most supervised segmentation methods. COL-Net is a meaningful attempt to alleviate the limited labeled sample problem in medical image segmentation.
Collapse
Affiliation(s)
- Liangliang Liu
- College of Information and Management Science, Henan Agricultural University, Zhengzhou, China
| | - Jing Zhang
- Department of Computer Science, Henan Quality Engineering Vocational College, Pingdingshan, China
| | - Jin-xiang Wang
- Department of Computer Science, University of Melbourne, Parkville, VIC, Australia
| | - Shufeng Xiong
- College of Information and Management Science, Henan Agricultural University, Zhengzhou, China
| | - Hui Zhang
- College of Information and Management Science, Henan Agricultural University, Zhengzhou, China
| |
Collapse
|
49
|
Garcia Santa Cruz B, Bossa MN, Sölter J, Husch AD. Public Covid-19 X-ray datasets and their impact on model bias - A systematic review of a significant problem. Med Image Anal 2021. [PMID: 34597937 DOI: 10.1101/2021.02.15.21251775] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/09/2023]
Abstract
Computer-aided-diagnosis and stratification of COVID-19 based on chest X-ray suffers from weak bias assessment and limited quality-control. Undetected bias induced by inappropriate use of datasets, and improper consideration of confounders prevents the translation of prediction models into clinical practice. By adopting established tools for model evaluation to the task of evaluating datasets, this study provides a systematic appraisal of publicly available COVID-19 chest X-ray datasets, determining their potential use and evaluating potential sources of bias. Only 9 out of more than a hundred identified datasets met at least the criteria for proper assessment of risk of bias and could be analysed in detail. Remarkably most of the datasets utilised in 201 papers published in peer-reviewed journals, are not among these 9 datasets, thus leading to models with high risk of bias. This raises concerns about the suitability of such models for clinical use. This systematic review highlights the limited description of datasets employed for modelling and aids researchers to select the most suitable datasets for their task.
Collapse
Affiliation(s)
- Beatriz Garcia Santa Cruz
- Centre Hospitalier de Luxembourg, 4, Rue Ernest Barble, Luxembourg L-1210, Luxembourg; Luxembourg Centre for Systems Biomedicine, University of Luxembourg, 7, Avenue des Hauts Fourneaux, Esch-sur-Alzette L-4362, Luxembourg.
| | - Matías Nicolás Bossa
- Luxembourg Centre for Systems Biomedicine, University of Luxembourg, 7, Avenue des Hauts Fourneaux, Esch-sur-Alzette L-4362, Luxembourg; Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), Pleinlaan 2, Brussels B-1050, Belgium
| | - Jan Sölter
- Luxembourg Centre for Systems Biomedicine, University of Luxembourg, 7, Avenue des Hauts Fourneaux, Esch-sur-Alzette L-4362, Luxembourg
| | - Andreas Dominik Husch
- Luxembourg Centre for Systems Biomedicine, University of Luxembourg, 7, Avenue des Hauts Fourneaux, Esch-sur-Alzette L-4362, Luxembourg
| |
Collapse
|
50
|
Bustos A, Payá A, Torrubia A, Jover R, Llor X, Bessa X, Castells A, Carracedo Á, Alenda C. xDEEP-MSI: Explainable Bias-Rejecting Microsatellite Instability Deep Learning System in Colorectal Cancer. Biomolecules 2021; 11:1786. [PMID: 34944430 PMCID: PMC8699085 DOI: 10.3390/biom11121786] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2021] [Revised: 11/25/2021] [Accepted: 11/26/2021] [Indexed: 02/06/2023] Open
Abstract
The prediction of microsatellite instability (MSI) using deep learning (DL) techniques could have significant benefits, including reducing cost and increasing MSI testing of colorectal cancer (CRC) patients. Nonetheless, batch effects or systematic biases are not well characterized in digital histology models and lead to overoptimistic estimates of model performance. Methods to not only palliate but to directly abrogate biases are needed. We present a multiple bias rejecting DL system based on adversarial networks for the prediction of MSI in CRC from tissue microarrays (TMAs), trained and validated in 1788 patients from EPICOLON and HGUA. The system consists of an end-to-end image preprocessing module that tile samples at multiple magnifications and a tissue classification module linked to the bias-rejecting MSI predictor. We detected three biases associated with the learned representations of a baseline model: the project of origin of samples, the patient's spot and the TMA glass where each spot was placed. The system was trained to directly avoid learning the batch effects of those variables. The learned features from the bias-ablated model achieved maximum discriminative power with respect to the task and minimal statistical mean dependence with the biases. The impact of different magnifications, types of tissues and the model performance at tile vs patient level is analyzed. The AUC at tile level, and including all three selected tissues (tumor epithelium, mucin and lymphocytic regions) and 4 magnifications, was 0.87 ± 0.03 and increased to 0.9 ± 0.03 at patient level. To the best of our knowledge, this is the first work that incorporates a multiple bias ablation technique at the DL architecture in digital pathology, and the first using TMAs for the MSI prediction task.
Collapse
Affiliation(s)
- Aurelia Bustos
- AI Cancer Research Unit, MedBravo, 03560 Alicante, Spain;
| | - Artemio Payá
- Pathology Department, Alicante University General Hospital (HGUA), 03010 Alicante, Spain; (A.P.); (R.J.)
- Alicante Institute for Health and Biomedical Research (ISABIAL), 03010 Alicante, Spain
| | | | - Rodrigo Jover
- Pathology Department, Alicante University General Hospital (HGUA), 03010 Alicante, Spain; (A.P.); (R.J.)
- Alicante Institute for Health and Biomedical Research (ISABIAL), 03010 Alicante, Spain
| | - Xavier Llor
- Department of Medicine, Yale Cancer Center, Yale University, New Haven, CT 06511, USA;
| | - Xavier Bessa
- Gastroenterology Department, Hospital del Mar Medical Research Institute (IMIM), 08003 Barcelona, Spain;
| | - Antoni Castells
- Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBERehd), Gastroenterology Department, Institut d’Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Hospital Clinic, University of Barcelona, 08036 Barcelona, Spain;
| | - Ángel Carracedo
- Fundación Pública Gallega de Medicina Genómica (GMX), 15706 Santiago de Compostela, Spain;
| | - Cristina Alenda
- Pathology Department, Alicante University General Hospital (HGUA), 03010 Alicante, Spain; (A.P.); (R.J.)
- Alicante Institute for Health and Biomedical Research (ISABIAL), 03010 Alicante, Spain
| |
Collapse
|