1
|
Glielmo P, Fusco S, Gitto S, Zantonelli G, Albano D, Messina C, Sconfienza LM, Mauri G. Artificial intelligence in interventional radiology: state of the art. Eur Radiol Exp 2024; 8:62. [PMID: 38693468 PMCID: PMC11063019 DOI: 10.1186/s41747-024-00452-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2023] [Accepted: 02/26/2024] [Indexed: 05/03/2024] Open
Abstract
Artificial intelligence (AI) has demonstrated great potential in a wide variety of applications in interventional radiology (IR). Support for decision-making and outcome prediction, new functions and improvements in fluoroscopy, ultrasound, computed tomography, and magnetic resonance imaging, specifically in the field of IR, have all been investigated. Furthermore, AI represents a significant boost for fusion imaging and simulated reality, robotics, touchless software interactions, and virtual biopsy. The procedural nature, heterogeneity, and lack of standardisation slow down the process of adoption of AI in IR. Research in AI is in its early stages as current literature is based on pilot or proof of concept studies. The full range of possibilities is yet to be explored.Relevance statement Exploring AI's transformative potential, this article assesses its current applications and challenges in IR, offering insights into decision support and outcome prediction, imaging enhancements, robotics, and touchless interactions, shaping the future of patient care.Key points• AI adoption in IR is more complex compared to diagnostic radiology.• Current literature about AI in IR is in its early stages.• AI has the potential to revolutionise every aspect of IR.
Collapse
Affiliation(s)
- Pierluigi Glielmo
- Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Via Mangiagalli, 31, 20133, Milan, Italy.
| | - Stefano Fusco
- Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Via Mangiagalli, 31, 20133, Milan, Italy
| | - Salvatore Gitto
- Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Via Mangiagalli, 31, 20133, Milan, Italy
- IRCCS Istituto Ortopedico Galeazzi, Via Cristina Belgioioso, 173, 20157, Milan, Italy
| | - Giulia Zantonelli
- Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Via Mangiagalli, 31, 20133, Milan, Italy
| | - Domenico Albano
- IRCCS Istituto Ortopedico Galeazzi, Via Cristina Belgioioso, 173, 20157, Milan, Italy
- Dipartimento di Scienze Biomediche, Chirurgiche ed Odontoiatriche, Università degli Studi di Milano, Via della Commenda, 10, 20122, Milan, Italy
| | - Carmelo Messina
- Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Via Mangiagalli, 31, 20133, Milan, Italy
- IRCCS Istituto Ortopedico Galeazzi, Via Cristina Belgioioso, 173, 20157, Milan, Italy
| | - Luca Maria Sconfienza
- Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Via Mangiagalli, 31, 20133, Milan, Italy
- IRCCS Istituto Ortopedico Galeazzi, Via Cristina Belgioioso, 173, 20157, Milan, Italy
| | - Giovanni Mauri
- Divisione di Radiologia Interventistica, IEO, IRCCS Istituto Europeo di Oncologia, Milan, Italy
| |
Collapse
|
2
|
Yang TH, Su YY, Tsai CL, Lin KH, Lin WY, Sung SF. Magnetic resonance imaging-based deep learning imaging biomarker for predicting functional outcomes after acute ischemic stroke. Eur J Radiol 2024; 174:111405. [PMID: 38447430 DOI: 10.1016/j.ejrad.2024.111405] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2023] [Revised: 02/05/2024] [Accepted: 03/01/2024] [Indexed: 03/08/2024]
Abstract
PURPOSE Clinical risk scores are essential for predicting outcomes in stroke patients. The advancements in deep learning (DL) techniques provide opportunities to develop prediction applications using magnetic resonance (MR) images. We aimed to develop an MR-based DL imaging biomarker for predicting outcomes in acute ischemic stroke (AIS) and evaluate its additional benefit to current risk scores. METHOD This study included 3338 AIS patients. We trained a DL model using deep neural network architectures on MR images and radiomics to predict poor functional outcomes at three months post-stroke. The DL model generated a DL score, which served as the DL imaging biomarker. We compared the predictive performance of this biomarker to five risk scores on a holdout test set. Additionally, we assessed whether incorporating the imaging biomarker into the risk scores improved the predictive performance. RESULTS The DL imaging biomarker achieved an area under the receiver operating characteristic curve (AUC) of 0.788. The AUCs of the five studied risk scores were 0.789, 0.793, 0.804, 0.810, and 0.826, respectively. The imaging biomarker's predictive performance was comparable to four of the risk scores but inferior to one (p = 0.038). Adding the imaging biomarker to the risk scores improved the AUCs (p-values) to 0.831 (0.003), 0.825 (0.001), 0.834 (0.003), 0.836 (0.003), and 0.839 (0.177), respectively. The net reclassification improvement and integrated discrimination improvement indices also showed significant improvements (all p < 0.001). CONCLUSIONS Using DL techniques to create an MR-based imaging biomarker is feasible and enhances the predictive ability of current risk scores.
Collapse
Affiliation(s)
- Tzu-Hsien Yang
- Department of Radiology, Ditmanson Medical Foundation Chia-Yi Christian Hospital, Chiayi City, Taiwan
| | - Ying-Ying Su
- Department of Radiology, Ditmanson Medical Foundation Chia-Yi Christian Hospital, Chiayi City, Taiwan
| | - Chia-Ling Tsai
- Computer Science Department, Queens College, City University of New York, Flushing, NY, USA
| | - Kai-Hsuan Lin
- Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi, Taiwan
| | - Wei-Yang Lin
- Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi, Taiwan; Advanced Institute of Manufacturing with High-Tech Innovations, National Chung Cheng University, Chiayi, Taiwan.
| | - Sheng-Feng Sung
- Division of Neurology, Department of Internal Medicine, Ditmanson Medical Foundation Chia-Yi Christian Hospital, Chiayi City, Taiwan; Department of Beauty & Health Care, Min-Hwei Junior College of Health Care Management, Tainan, Taiwan.
| |
Collapse
|
3
|
Qu M, Xu Y, Lu L. Global research evolution and frontier analysis of artificial intelligence in brain injury: A bibliometric analysis. Brain Res Bull 2024; 209:110920. [PMID: 38453035 DOI: 10.1016/j.brainresbull.2024.110920] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2023] [Revised: 12/18/2023] [Accepted: 03/03/2024] [Indexed: 03/09/2024]
Abstract
Research on artificial intelligence for brain injury is currently a prominent area of scientific research. A significant amount of related literature has been accumulated in this field. This study aims to identify hotspots and clarify research resources by conducting literature metrology visualization analysis, providing valuable ideas and references for related fields. The research object of this paper consists of 3000 articles cited in the core database of Web of Science from 1998 to 2023. These articles are visualized and analyzed using VOSviewer and CiteSpace. The bibliometric analysis reveals a continuous increase in the number of articles published on this topic, particularly since 2016, indicating significant growth. The United States stands out as the leading country in artificial intelligence for brain injury, followed by China, which tends to catch up. The core research institutions are primarily universities in developed countries, but there is a lack of cooperation and communication between research groups. With the development of computer technology, the research in this field has shown strong wave characteristics, experiencing the early stage of applied research based on expert systems, the middle stage of prediction research based on machine learning, and the current phase of diversified research focused on deep learning. Artificial intelligence has innovative development prospects in brain injury, providing a new orientation for the treatment and auxiliary diagnosis in this field.
Collapse
Affiliation(s)
- Mengqi Qu
- Institute of Disaster and Emergency Medicine, Tianjin University, Tianjin 300072, China.
| | - Yang Xu
- Institute of Disaster and Emergency Medicine, Tianjin University, Tianjin 300072, China.
| | - Lu Lu
- Institute of Disaster and Emergency Medicine, Tianjin University, Tianjin 300072, China.
| |
Collapse
|
4
|
Zhao Z, Zhang Y, Su J, Yang L, Pang L, Gao Y, Wang H. A comprehensive review for artificial intelligence on neuroimaging in rehabilitation of ischemic stroke. Front Neurol 2024; 15:1367854. [PMID: 38606275 PMCID: PMC11007047 DOI: 10.3389/fneur.2024.1367854] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2024] [Accepted: 03/08/2024] [Indexed: 04/13/2024] Open
Abstract
Stroke is the second leading cause of death worldwide, with ischemic stroke accounting for a significant proportion of morbidity and mortality among stroke patients. Ischemic stroke often causes disability and cognitive impairment in patients, which seriously affects the quality of life of patients. Therefore, how to predict the recovery of patients can provide support for clinical intervention in advance and improve the enthusiasm of patients for rehabilitation treatment. With the popularization of imaging technology, the diagnosis and treatment of ischemic stroke patients are often accompanied by a large number of imaging data. Through machine learning and Deep Learning, information from imaging data can be used more effectively. In this review, we discuss recent advances in neuroimaging, machine learning, and Deep Learning in the rehabilitation of ischemic stroke.
Collapse
Affiliation(s)
- Zijian Zhao
- Rehabilitation Center, ShengJing Hospital of China Medical University, Shenyang, Liaoning Province, China
| | - Yuanyuan Zhang
- Rehabilitation Center, ShengJing Hospital of China Medical University, Shenyang, Liaoning Province, China
| | - Jiuhui Su
- Department of Orthopedics, Haicheng Bonesetting Hospital, Haicheng, Liaoning Province, China
| | - Lianbo Yang
- Department of Reparative and Reconstructive Surgery, The Second Hospital of Dalian Medical University, Dalian Liaoning Province, China
| | - Luhang Pang
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, Liaoning Province, China
| | - Yingshan Gao
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, Liaoning Province, China
| | - Hongbo Wang
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, Liaoning Province, China
| |
Collapse
|
5
|
Diprose JP, Diprose WK, Chien TY, Wang MTM, McFetridge A, Tarr GP, Ghate K, Beharry J, Hong J, Wu T, Campbell D, Barber PA. Deep learning on pre-procedural computed tomography and clinical data predicts outcome following stroke thrombectomy. J Neurointerv Surg 2024:jnis-2023-021154. [PMID: 38527795 DOI: 10.1136/jnis-2023-021154] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2023] [Accepted: 02/23/2024] [Indexed: 03/27/2024]
Abstract
BACKGROUND Deep learning using clinical and imaging data may improve pre-treatment prognostication in ischemic stroke patients undergoing endovascular thrombectomy (EVT). METHODS Deep learning models were trained and tested on baseline clinical and imaging (CT head and CT angiography) data to predict 3-month functional outcomes in stroke patients who underwent EVT. Classical machine learning models (logistic regression and random forest classifiers) were constructed to compare their performance with the deep learning models. An external validation dataset was used to validate the models. The MR PREDICTS prognostic tool was tested on the external validation set, and its performance was compared with the deep learning and classical machine learning models. RESULTS A total of 975 patients (550 men; mean±SD age 67.5±15.1 years) were studied with 778 patients in the model development cohort and 197 in the external validation cohort. The deep learning model trained on baseline CT and clinical data, and the logistic regression model (clinical data alone) demonstrated the strongest discriminative abilities for 3-month functional outcome and were comparable (AUC 0.811 vs 0.817, Q=0.82). Both models exhibited superior prognostic performance than the other deep learning (CT head alone, CT head, and CT angiography) and MR PREDICTS models (all Q<0.05). CONCLUSIONS The discriminative performance of deep learning for predicting functional independence was comparable to logistic regression. Future studies should focus on whether incorporating procedural and post-procedural data significantly improves model performance.
Collapse
Affiliation(s)
| | - William K Diprose
- Department of Medicine, Faculty of Medical and Health Sciences, University of Auckland, Auckland, New Zealand
| | | | - Michael T M Wang
- Department of Medicine, Faculty of Medical and Health Sciences, University of Auckland, Auckland, New Zealand
| | - Andrew McFetridge
- Department of Radiology, Auckland City Hospital, Auckland, New Zealand
| | - Gregory P Tarr
- Department of Radiology, Auckland City Hospital, Auckland, New Zealand
| | - Kaustubha Ghate
- Department of Neurology, Auckland City Hospital, Auckland, New Zealand
| | - James Beharry
- Department of Neurology, Christchurch Hospital, Christchurch, New Zealand
| | - JaeBeom Hong
- Department of Neurology, Auckland City Hospital, Auckland, New Zealand
| | - Teddy Wu
- Department of Neurology, Christchurch Hospital, Christchurch, New Zealand
| | - Doug Campbell
- Department of Anaesthesia and Perioperative Medicine, Auckland City Hospital, Auckland, New Zealand
| | - P Alan Barber
- Department of Medicine, Faculty of Medical and Health Sciences, University of Auckland, Auckland, New Zealand
- Department of Neurology, Auckland City Hospital, Auckland, New Zealand
| |
Collapse
|
6
|
Pedro T, Sousa JM, Fonseca L, Gama MG, Moreira G, Pintalhão M, Chaves PC, Aires A, Alves G, Augusto L, Pinheiro Albuquerque L, Castro P, Silva ML. Exploring the use of ChatGPT in predicting anterior circulation stroke functional outcomes after mechanical thrombectomy: a pilot study. J Neurointerv Surg 2024:jnis-2024-021556. [PMID: 38453462 DOI: 10.1136/jnis-2024-021556] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2024] [Accepted: 02/27/2024] [Indexed: 03/09/2024]
Abstract
BACKGROUND Accurate prediction of functional outcomes is crucial in stroke management, but this remains challenging. OBJECTIVE To evaluate the performance of the generative language model ChatGPT in predicting the functional outcome of patients with acute ischemic stroke (AIS) 3 months after mechanical thrombectomy (MT) in order to assess whether ChatGPT can used to be accurately predict the modified Rankin Scale (mRS) score at 3 months post-thrombectomy. METHODS We conducted a retrospective analysis of clinical, neuroimaging, and procedure-related data from 163 patients with AIS undergoing MT. The agreement between ChatGPT's exact and dichotomized predictions and actual mRS scores was assessed using Cohen's κ. The added value of ChatGPT was measured by evaluating the agreement of predicted dichotomized outcomes using an existing validated score, the MT-DRAGON. RESULTS ChatGPT demonstrated fair (κ=0.354, 95% CI 0.260 to 0.448) and good (κ=0.727, 95% CI 0.620 to 0.833) agreement with the true exact and dichotomized mRS scores at 3 months, respectively, outperforming MT-DRAGON in overall and subgroup predictions. ChatGPT agreement was higher for patients with shorter last-time-seen-well-to-door delay, distal occlusions, and better modified Thrombolysis in Cerebral Infarction scores. CONCLUSIONS ChatGPT adequately predicted short-term functional outcomes in post-thrombectomy patients with AIS and was better than the existing risk score. Integrating AI models into clinical practice holds promise for patient care, yet refining these models is crucial for enhanced accuracy in stroke management.
Collapse
Affiliation(s)
- Tiago Pedro
- Department of Neuroradiology, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - José Maria Sousa
- Department of Neuroradiology, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - Luísa Fonseca
- Department of Medicine, University of Porto, Porto, Portugal
- Department of Internal Medicine, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - Manuel G Gama
- Department of Medicine, University of Porto, Porto, Portugal
- Department of Internal Medicine, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - Goreti Moreira
- Department of Medicine, University of Porto, Porto, Portugal
- Department of Internal Medicine, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - Mariana Pintalhão
- Department of Medicine, University of Porto, Porto, Portugal
- Department of Internal Medicine, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - Paulo C Chaves
- Department of Medicine, University of Porto, Porto, Portugal
- Department of Internal Medicine, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - Ana Aires
- Department of Internal Medicine, Centro Hospitalar Universitário de São João, Porto, Portugal
- Department of Neurology, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - Gonçalo Alves
- Department of Neuroradiology, Centro Hospitalar Universitário de São João, Porto, Portugal
- Centro de Referência de Neurorradiologia de Intervenção na Doença Cerebrovascular, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - Luís Augusto
- Department of Neuroradiology, Centro Hospitalar Universitário de São João, Porto, Portugal
- Centro de Referência de Neurorradiologia de Intervenção na Doença Cerebrovascular, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - Luís Pinheiro Albuquerque
- Department of Neuroradiology, Centro Hospitalar Universitário de São João, Porto, Portugal
- Centro de Referência de Neurorradiologia de Intervenção na Doença Cerebrovascular, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - Pedro Castro
- Department of Neurology, Centro Hospitalar Universitário de São João, Porto, Portugal
- Department of Clinical Neurosciences and Mental Health, University of Porto, Porto, Portugal
| | - Maria Luís Silva
- Department of Neuroradiology, Centro Hospitalar Universitário de São João, Porto, Portugal
- Centro de Referência de Neurorradiologia de Intervenção na Doença Cerebrovascular, Centro Hospitalar Universitário de São João, Porto, Portugal
| |
Collapse
|
7
|
Chen M, Qian D, Wang Y, An J, Meng K, Xu S, Liu S, Sun M, Li M, Pang C. Systematic Review of Machine Learning Applied to the Secondary Prevention of Ischemic Stroke. J Med Syst 2024; 48:8. [PMID: 38165495 DOI: 10.1007/s10916-023-02020-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2023] [Accepted: 11/13/2023] [Indexed: 01/03/2024]
Abstract
Ischemic stroke is a serious disease posing significant threats to human health and life, with the highest absolute and relative risks of a poor prognosis following the first occurrence, and more than 90% of strokes are attributable to modifiable risk factors. Currently, machine learning (ML) is widely used for the prediction of ischemic stroke outcomes. By identifying risk factors, predicting the risk of poor prognosis and thus developing personalized treatment plans, it effectively reduces the probability of poor prognosis, leading to more effective secondary prevention. This review includes 41 studies since 2018 that used ML algorithms to build prognostic prediction models for ischemic stroke, transient ischemic attack (TIA), and acute ischemic stroke (AIS). We analyzed in detail the risk factors used in these studies, the sources and processing methods of the required data, the model building and validation, and their application in different prediction time windows. The results indicate that among the included studies, the top five risk factors in terms of frequency were cardiovascular diseases, age, sex, national institutes of health stroke scale (NIHSS) score, and diabetes. Furthermore, 64% of the studies used single-center data, 65% of studies using imbalanced data did not perform data balancing, 88% of the studies did not utilize external validation datasets for model validation, and 72% of the studies did not provide explanations for their models. Addressing these issues is crucial for enhancing the credibility and effectiveness of the research, consequently improving the development and implementation of secondary prevention measures.
Collapse
Affiliation(s)
- Meng Chen
- School of Life Science and Technology, Changchun University of Science and Technology, Jilin Province, Changchun, 130022, People's Republic of China
| | - Dongbao Qian
- School of Life Science and Technology, Changchun University of Science and Technology, Jilin Province, Changchun, 130022, People's Republic of China
| | - Yixuan Wang
- Union Hospital of Jilin University, Jilin Province, Neurosurgery, Changchun, 130033, People's Republic of China
| | - Junyan An
- Union Hospital of Jilin University, Jilin Province, Neurosurgery, Changchun, 130033, People's Republic of China
| | - Ke Meng
- Union Hospital of Jilin University, Jilin Province, Neurosurgery, Changchun, 130033, People's Republic of China
| | - Shuai Xu
- School of Life Science and Technology, Changchun University of Science and Technology, Jilin Province, Changchun, 130022, People's Republic of China
| | - Sheng Liu
- School of Life Science and Technology, Changchun University of Science and Technology, Jilin Province, Changchun, 130022, People's Republic of China
| | - Meiyan Sun
- Union Hospital of Jilin University, Jilin Province, Neurosurgery, Changchun, 130033, People's Republic of China
| | - Miao Li
- School of Life Science and Technology, Changchun University of Science and Technology, Jilin Province, Changchun, 130022, People's Republic of China.
- Union Hospital of Jilin University, Jilin Province, Neurosurgery, Changchun, 130033, People's Republic of China.
| | - Chunying Pang
- School of Life Science and Technology, Changchun University of Science and Technology, Jilin Province, Changchun, 130022, People's Republic of China.
| |
Collapse
|
8
|
Pacchiano F, Tortora M, Criscuolo S, Jaber K, Acierno P, De Simone M, Tortora F, Briganti F, Caranci F. Artificial intelligence applied in acute ischemic stroke: from child to elderly. Radiol Med 2024; 129:83-92. [PMID: 37878222 PMCID: PMC10808481 DOI: 10.1007/s11547-023-01735-1] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/17/2023] [Accepted: 09/28/2023] [Indexed: 10/26/2023]
Abstract
This review will summarize artificial intelligence developments in acute ischemic stroke in recent years and forecasts for the future. Stroke is a major healthcare concern due to its effects on the patient's quality of life and its dependence on the timing of the identification as well as the treatment. In recent years, attention increased on the use of artificial intelligence (AI) systems to help categorize, prognosis, and to channel these patients toward the right therapeutic procedure. Machine learning (ML) and in particular deep learning (DL) systems using convoluted neural networks (CNN) are becoming increasingly popular. Various studies over the years evaluated the use of these methods of analysis and prediction in the assessment of stroke patients, and at the same time, several applications and software have been developed to support the neuroradiologists and the stroke team to improve patient outcomes.
Collapse
Affiliation(s)
- Francesco Pacchiano
- Department of Precision Medicine, University of Campania "L. Vanvitelli", Caserta, Italy
| | - Mario Tortora
- Department of Advanced Biomedical Sciences, University "Federico II", Via Pansini, 5, 80131, Naples, Italy.
| | - Sabrina Criscuolo
- Pediatric University Department, Bambino Gesù Children Hospital, Rome, Italy
| | - Katya Jaber
- Department of Elektrotechnik und Informatik, Hochschule Bremen, Bremen, Germany
| | | | - Marta De Simone
- UOC Neuroradiology, AORN San Giuseppe Moscati, Avellino, Italy
| | - Fabio Tortora
- Department of Advanced Biomedical Sciences, University "Federico II", Via Pansini, 5, 80131, Naples, Italy
| | - Francesco Briganti
- Department of Advanced Biomedical Sciences, University "Federico II", Via Pansini, 5, 80131, Naples, Italy
| | - Ferdinando Caranci
- Department of Precision Medicine, University of Campania "L. Vanvitelli", Caserta, Italy
| |
Collapse
|
9
|
Hokkinen L, Mäkelä T, Savolainen S, Kangasniemi M. Factors influencing the reliability of a CT angiography-based deep learning method for infarct volume estimation. BJR Open 2024; 6:tzae001. [PMID: 38352187 PMCID: PMC10860582 DOI: 10.1093/bjro/tzae001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2022] [Revised: 12/03/2023] [Accepted: 12/26/2023] [Indexed: 02/16/2024] Open
Abstract
Objectives CT angiography (CTA)-based machine learning methods for infarct volume estimation have shown a tendency to overestimate infarct core and final infarct volumes (FIV). Our aim was to assess factors influencing the reliability of these methods. Methods The effect of collateral circulation on the correlation between convolutional neural network (CNN) estimations and FIV was assessed based on the Miteff system and hypoperfusion intensity ratio (HIR) in 121 patients with anterior circulation acute ischaemic stroke using Pearson correlation coefficients and median volumes. Correlation was also assessed between successful and futile thrombectomies. The timing of individual CTAs in relation to CTP studies was analysed. Results The strength of correlation between CNN estimated volumes and FIV did not change significantly depending on collateral status as assessed with the Miteff system or HIR, being poor to moderate (r = 0.09-0.50). The strongest correlation was found in patients with futile thrombectomies (r = 0.61). Median CNN estimates showed a trend for overestimation compared to FIVs. CTA was acquired in the mid arterial phase in virtually all patients (120/121). Conclusions This study showed no effect of collateral status on the reliability of the CNN and best correlation was found in patients with futile thrombectomies. CTA timing in the mid arterial phase in virtually all patients can explain infarct volume overestimation. Advances in knowledge CTA timing seems to be the most important factor influencing the reliability of current CTA-based machine learning methods, emphasizing the need for CTA protocol optimization for infarct core estimation.
Collapse
Affiliation(s)
- Lasse Hokkinen
- Radiology, HUS Medical Imaging Centre, University of Helsinki and Helsinki University Hospital, Helsinki 00290, Finland
| | - Teemu Mäkelä
- Radiology, HUS Medical Imaging Centre, University of Helsinki and Helsinki University Hospital, Helsinki 00290, Finland
- Department of Physics, University of Helsinki, Helsinki 00014, Finland
| | - Sauli Savolainen
- Radiology, HUS Medical Imaging Centre, University of Helsinki and Helsinki University Hospital, Helsinki 00290, Finland
- Department of Physics, University of Helsinki, Helsinki 00014, Finland
| | - Marko Kangasniemi
- Radiology, HUS Medical Imaging Centre, University of Helsinki and Helsinki University Hospital, Helsinki 00290, Finland
| |
Collapse
|
10
|
Liang J, Feng J, Lin Z, Wei J, Luo X, Wang QM, He B, Chen H, Ye Y. Research on prognostic risk assessment model for acute ischemic stroke based on imaging and multidimensional data. Front Neurol 2023; 14:1294723. [PMID: 38192576 PMCID: PMC10773779 DOI: 10.3389/fneur.2023.1294723] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Accepted: 11/30/2023] [Indexed: 01/10/2024] Open
Abstract
Accurately assessing the prognostic outcomes of patients with acute ischemic stroke and adjusting treatment plans in a timely manner for those with poor prognosis is crucial for intervening in modifiable risk factors. However, there is still controversy regarding the correlation between imaging-based predictions of complications in acute ischemic stroke. To address this, we developed a cross-modal attention module for integrating multidimensional data, including clinical information, imaging features, treatment plans, prognosis, and complications, to achieve complementary advantages. The fused features preserve magnetic resonance imaging (MRI) characteristics while supplementing clinical relevant information, providing a more comprehensive and informative basis for clinical diagnosis and treatment. The proposed framework based on multidimensional data for activity of daily living (ADL) scoring in patients with acute ischemic stroke demonstrates higher accuracy compared to other state-of-the-art network models, and ablation experiments confirm the effectiveness of each module in the framework.
Collapse
Affiliation(s)
- Jiabin Liang
- Postgraduate Cultivation Base of Guangzhou University of Chinese Medicine, Panyu Central Hospital, Guangzhou, China
- Graduate School, Guangzhou University of Chinese Medicine, Guangzhou, China
- Medical Imaging Institute of Panyu, Guangzhou, China
| | - Jie Feng
- Radiology Department of Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Zhijie Lin
- Laboratory for Intelligent Information Processing, Guangdong University of Technology, Guangzhou, China
| | - Jinbo Wei
- Postgraduate Cultivation Base of Guangzhou University of Chinese Medicine, Panyu Central Hospital, Guangzhou, China
| | - Xun Luo
- Kerry Rehabilitation Medicine Research Institute, Shenzhen, China
| | - Qing Mei Wang
- Stroke Biological Recovery Laboratory, Spaulding Rehabilitation Hospital, Teaching Affiliate of Harvard Medical School, Charlestown, MA, United States
| | - Bingjie He
- Panyu Health Management Center, Guangzhou, China
| | - Hanwei Chen
- Postgraduate Cultivation Base of Guangzhou University of Chinese Medicine, Panyu Central Hospital, Guangzhou, China
- Medical Imaging Institute of Panyu, Guangzhou, China
- Panyu Health Management Center, Guangzhou, China
| | - Yufeng Ye
- Postgraduate Cultivation Base of Guangzhou University of Chinese Medicine, Panyu Central Hospital, Guangzhou, China
- Medical Imaging Institute of Panyu, Guangzhou, China
| |
Collapse
|
11
|
Oliveira G, Fonseca AC, Ferro J, Oliveira AL. Deep Learning-Based Extraction of Biomarkers for the Prediction of the Functional Outcome of Ischemic Stroke Patients. Diagnostics (Basel) 2023; 13:3604. [PMID: 38132189 PMCID: PMC10743068 DOI: 10.3390/diagnostics13243604] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2023] [Revised: 11/26/2023] [Accepted: 12/01/2023] [Indexed: 12/23/2023] Open
Abstract
Accurately predicting functional outcomes in stroke patients remains challenging yet clinically relevant. While brain CTs provide prognostic information, their practical value for outcome prediction is unclear. We analyzed a multi-center cohort of 743 ischemic stroke patients (<72 h onset), including their admission brain NCCT and CTA scans as well as their clinical data. Our goal was to predict the patients' future functional outcome, measured by the 3-month post-stroke modified Rankin Scale (mRS), dichotomized into good (mRS ≤ 2) and poor (mRS > 2). To this end, we developed deep learning models to predict the outcome from CT data only, and models that incorporate other patient variables. Three deep learning architectures were tested in the image-only prediction, achieving 0.779 ± 0.005 AUC. In addition, we created a model fusing imaging and tabular data by feeding the output of a deep learning model trained to detect occlusions on CT angiograms into our prediction framework, which achieved an AUC of 0.806 ± 0.082. These findings highlight how further refinement of prognostic models incorporating both image biomarkers and clinical data could enable more accurate outcome prediction for ischemic stroke patients.
Collapse
Affiliation(s)
- Gonçalo Oliveira
- NeuralShift, 1000-138 Lisbon, Portugal
- INESC-ID, Instituto Superior Técnico, 1000-029 Lisbon, Portugal
| | - Ana Catarina Fonseca
- Faculdade de Medicina, Universidade de Lisboa, 1649-028 Lisbon, Portugal; (A.C.F.); (J.F.)
| | - José Ferro
- Faculdade de Medicina, Universidade de Lisboa, 1649-028 Lisbon, Portugal; (A.C.F.); (J.F.)
| | | |
Collapse
|
12
|
Chang H, Zhang H, Shi G, Guo J, Chu X, Wang Z, Yao Y, Wang X. Ischemic stroke prediction using machine learning in elderly Chinese population: The Rugao Longitudinal Ageing Study. Brain Behav 2023; 13:e3307. [PMID: 37934082 PMCID: PMC10726889 DOI: 10.1002/brb3.3307] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/24/2023] [Revised: 09/22/2023] [Accepted: 10/18/2023] [Indexed: 11/08/2023] Open
Abstract
OBJECTIVE Compared logistic regression (LR) with machine learning (ML) models, to predict the risk of ischemic stroke in an elderly population in China. METHODS We applied 2208 records from the Rugao Longitudinal Ageing Study (RLAS) for ischemic stroke risk prediction assessment. Input variables included 103 phenotypes. For 3-year ischemic stroke risk prediction, we compared the discrimination and calibration of LR model and ML methods, where ML methods include Random Forest (RF), Gaussian kernel Support Vector Machines (SVM), Multilayer perceptron (MLP), K-Nearest Neighbors Algorithm (KNN), and Gradient Boosting Decision Tree (GBDT) to develop an ischemic stroke risk prediction model. RESULTS Age, pulse, waist circumference, education level, β2-microglobulin, homocysteine, cystatin C, folate, free triiodothyronine, platelet distribution width, QT interval, and QTc interval were significant induced predictors of ischemic stroke. For ischemic stroke prediction, the ML approach was able to tap more biochemical and ECG-related multidimensional phenotypic indicators compared to the LR model, which placed more importance on general demographic indicators. Compared to the LR model, SVM provided the best discrimination and calibration (C-index: 0.79 vs. 0.71, 11.27% improvement in model utility), with the best performance in both validation and test data. CONCLUSION In a comparison of LR with five ML models, the accuracy of ischemic stroke prediction was higher by combining ML with multiple phenotypes. Combined with other studies based on elderly populations in China, ML techniques, especially SVM, have shown good long-term predictive performance, inspiring the potential value of ML use in clinical practice.
Collapse
Affiliation(s)
- Huai‐Wen Chang
- Department of Computational Biology, School of Life SciencesFudan UniversityShanghaiChina
| | - Hui Zhang
- Department of Cardiovascular Disease Aging ResearchFudan University–the People's Hospital of Rugao Joint Research Institute of Longevity and AgingRugaoJiangsuChina
- Zhangjiang Fudan International Innovation Center, Human Phenome InstituteFudan UniversityShanghaiChina
| | - Guo‐Ping Shi
- Department of Cardiovascular Disease Aging ResearchFudan University–the People's Hospital of Rugao Joint Research Institute of Longevity and AgingRugaoJiangsuChina
- The People's Hospital of RugaoRugaoJiangsuChina
| | - Jiang‐Hong Guo
- Department of Cardiovascular Disease Aging ResearchFudan University–the People's Hospital of Rugao Joint Research Institute of Longevity and AgingRugaoJiangsuChina
- The People's Hospital of RugaoRugaoJiangsuChina
| | - Xue‐Feng Chu
- Department of Cardiovascular Disease Aging ResearchFudan University–the People's Hospital of Rugao Joint Research Institute of Longevity and AgingRugaoJiangsuChina
- The People's Hospital of RugaoRugaoJiangsuChina
| | - Zheng‐Dong Wang
- Department of Cardiovascular Disease Aging ResearchFudan University–the People's Hospital of Rugao Joint Research Institute of Longevity and AgingRugaoJiangsuChina
- The People's Hospital of RugaoRugaoJiangsuChina
| | - Yin Yao
- Department of Computational Biology, School of Life SciencesFudan UniversityShanghaiChina
- Department of Cardiovascular Disease Aging ResearchFudan University–the People's Hospital of Rugao Joint Research Institute of Longevity and AgingRugaoJiangsuChina
| | - Xiao‐Feng Wang
- Department of Cardiovascular Disease Aging ResearchFudan University–the People's Hospital of Rugao Joint Research Institute of Longevity and AgingRugaoJiangsuChina
- Zhangjiang Fudan International Innovation Center, Human Phenome InstituteFudan UniversityShanghaiChina
| |
Collapse
|
13
|
Nageler G, Gergel I, Fangerau M, Breckwoldt M, Seker F, Bendszus M, Möhlenbruch M, Neuberger U. Deep Learning-based Assessment of Internal Carotid Artery Anatomy to Predict Difficult Intracranial Access in Endovascular Recanalization of Acute Ischemic Stroke. Clin Neuroradiol 2023; 33:783-792. [PMID: 36928398 PMCID: PMC10449951 DOI: 10.1007/s00062-023-01276-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2022] [Accepted: 02/03/2023] [Indexed: 03/18/2023]
Abstract
BACKGROUND Endovascular thrombectomy (EVT) duration is an important predictor for neurological outcome. Recently it was shown that an angle of ≤ 90° of the internal carotid artery (ICA) is predictive for longer EVT duration. As manual angle measurement is not trivial and time-consuming, deep learning (DL) could help identifying difficult EVT cases in advance. METHODS We included 379 CT angiographies (CTA) of patients who underwent EVT between January 2016 and December 2020. Manual segmentation of 121 CTAs was performed for the aortic arch, common carotid artery (CCA) and ICA. These were used to train a nnUNet. The remaining 258 CTAs were segmented using the trained nnUNet with manual verification afterwards. Angles of left and right ICAs were measured resulting in two classes: acute angle ≤ 90° and > 90°. The segmentations together with angle measurements were used to train a convolutional neural network (CNN) determining the ICA angle. The performance was evaluated using Dice scores. The classification was evaluated using AUC and accuracy. Associations of ICA angle and procedural times was explored using median and Whitney‑U test. RESULTS Median EVT duration for cases with ICA angle > 90° was 48 min and with ≤ 90° was 64 min (p = 0.001). Segmentation evaluation showed Dice scores of 0.94 for the aorta and 0.86 for CCA/ICA, respectively. Evaluation of ICA angle determination resulted in an AUC of 0.92 and accuracy of 0.85. CONCLUSION The association between ICA angle and EVT duration could be verified and a DL-based method for semi-automatic assessment with the potential for full automation was developed. More anatomical features of interest could be examined in a similar fashion.
Collapse
Affiliation(s)
- Gregor Nageler
- Dept. of Neuroradiology, Heidelberg University Hospital, Im Neuenheimer Feld 400, 69120, Heidelberg, Germany
- mbits imaging GmbH, Heidelberg, Germany
| | | | | | - Michael Breckwoldt
- Dept. of Neuroradiology, Heidelberg University Hospital, Im Neuenheimer Feld 400, 69120, Heidelberg, Germany
| | - Fatih Seker
- Dept. of Neuroradiology, Heidelberg University Hospital, Im Neuenheimer Feld 400, 69120, Heidelberg, Germany
| | - Martin Bendszus
- Dept. of Neuroradiology, Heidelberg University Hospital, Im Neuenheimer Feld 400, 69120, Heidelberg, Germany
| | - Markus Möhlenbruch
- Dept. of Neuroradiology, Heidelberg University Hospital, Im Neuenheimer Feld 400, 69120, Heidelberg, Germany
| | - Ulf Neuberger
- Dept. of Neuroradiology, Heidelberg University Hospital, Im Neuenheimer Feld 400, 69120, Heidelberg, Germany.
| |
Collapse
|
14
|
Li Q, Chi L, Zhao W, Wu L, Jiao C, Zheng X, Zhang K, Li X. Machine learning prediction of motor function in chronic stroke patients: a systematic review and meta-analysis. Front Neurol 2023; 14:1039794. [PMID: 37388543 PMCID: PMC10299899 DOI: 10.3389/fneur.2023.1039794] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2022] [Accepted: 05/25/2023] [Indexed: 07/01/2023] Open
Abstract
Background Recent studies have reported that machine learning (ML), with a relatively strong capacity for processing non-linear data and adaptive ability, could improve the accuracy and efficiency of prediction. The article summarizes the published studies on ML models that predict motor function 3-6 months post-stroke. Methods A systematic literature search was conducted in PubMed, Embase, Cochorane and Web of Science as of April 3, 2023 for studies on ML prediction of motor function in stroke patients. The quality of the literature was assessed using the Prediction model Risk Of Bias Assessment Tool (PROBAST). A random-effects model was preferred for meta-analysis using R4.2.0 because of the different variables and parameters. Results A total of 44 studies were included in this meta-analysis, involving 72,368 patients and 136 models. Models were categorized into subgroups according to the predicted outcome Modified Rankin Scale cut-off value and whether they were constructed based on radiomics. C-statistics, sensitivity, and specificity were calculated. The random-effects model showed that the C-statistics of all models were 0.81 (95% CI: 0.79; 0.83) in the training set and 0.82 (95% CI: 0.80; 0.85) in the validation set. According to different Modified Rankin Scale cut-off values, C-statistics of ML models predicting Modified Rankin Scale>2(used most widely) in stroke patients were 0.81 (95% CI: 0.78; 0.84) in the training set, and 0.84 (95% CI: 0.81; 0.87) in the validation set. C-statistics of radiomics-based ML models in the training set and validation set were 0.81 (95% CI: 0.78; 0.84) and 0.87 (95% CI: 0.83; 0.90), respectively. Conclusion ML can be used as an assessment tool for predicting the motor function in patients with 3-6 months of post-stroke. Additionally, the study found that ML models with radiomics as a predictive variable were also demonstrated to have good predictive capabilities. This systematic review provides valuable guidance for the future optimization of ML prediction systems that predict poor motor outcomes in stroke patients. Systematic review registration https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022335260, identifier: CRD42022335260.
Collapse
Affiliation(s)
- Qinglin Li
- Second Clinical Medical School, Heilongjiang University of Chinese Medicine, Harbin, Heilongjiang, China
| | - Lei Chi
- Department of Acupuncture, The Second Affiliated Hospital of Heilongjiang University of Chinese Medicine, Harbin, Heilongjiang, China
| | - Weiying Zhao
- Second Clinical Medical School, Heilongjiang University of Chinese Medicine, Harbin, Heilongjiang, China
| | - Lei Wu
- Department of Acupuncture, The Third Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, Zhejiang, China
| | - Chuanxu Jiao
- Department of Neurorehabilitation, Taizhou Enze Medical Center Luqiao Hospital, Taizhou, Zhejiang, China
| | - Xue Zheng
- Second Clinical Medical School, Heilongjiang University of Chinese Medicine, Harbin, Heilongjiang, China
| | - Kaiyue Zhang
- Second Clinical Medical School, Heilongjiang University of Chinese Medicine, Harbin, Heilongjiang, China
| | - Xiaoning Li
- Department of Acupuncture, The Second Affiliated Hospital of Heilongjiang University of Chinese Medicine, Harbin, Heilongjiang, China
| |
Collapse
|
15
|
Akay EMZ, Hilbert A, Carlisle BG, Madai VI, Mutke MA, Frey D. Artificial Intelligence for Clinical Decision Support in Acute Ischemic Stroke: A Systematic Review. Stroke 2023; 54:1505-1516. [PMID: 37216446 DOI: 10.1161/strokeaha.122.041442] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2022] [Accepted: 02/21/2023] [Indexed: 05/24/2023]
Abstract
BACKGROUND Established randomized trial-based parameters for acute ischemic stroke group patients into generic treatment groups, leading to attempts using various artificial intelligence (AI) methods to directly correlate patient characteristics to outcomes and thereby provide decision support to stroke clinicians. We review AI-based clinical decision support systems in the development stage, specifically regarding methodological robustness and constraints for clinical implementation. METHODS Our systematic review included full-text English language publications proposing a clinical decision support system using AI techniques for direct decision support in acute ischemic stroke cases in adult patients. We (1) describe data and outcomes used in those systems, (2) estimate the systems' benefits compared with traditional stroke diagnosis and treatment, and (3) reported concordance with reporting standards for AI in healthcare. RESULTS One hundred twenty-one studies met our inclusion criteria. Sixty-five were included for full extraction. In our sample, utilized data sources, methods, and reporting practices were highly heterogeneous. CONCLUSIONS Our results suggest significant validity threats, dissonance in reporting practices, and challenges to clinical translation. We outline practical recommendations for the successful implementation of AI research in acute ischemic stroke treatment and diagnosis.
Collapse
Affiliation(s)
- Ela Marie Z Akay
- Charité Lab for Artificial Intelligence in Medicine (CLAIM) (E.M.Z.A., A.H., D.F.), Charité Universitätsmedizin Berlin, Germany
| | - Adam Hilbert
- Charité Lab for Artificial Intelligence in Medicine (CLAIM) (E.M.Z.A., A.H., D.F.), Charité Universitätsmedizin Berlin, Germany
| | - Benjamin G Carlisle
- QUEST Center for Responsible Research, Berlin Institute of Health (BIH) (B.G.C., V.I.M.), Charité Universitätsmedizin Berlin, Germany
| | - Vince I Madai
- QUEST Center for Responsible Research, Berlin Institute of Health (BIH) (B.G.C., V.I.M.), Charité Universitätsmedizin Berlin, Germany
- Faculty of Computing, Engineering and the Built Environment, School of Computing and Digital Technology, Birmingham City University, United Kingdom (V.I.M.)
| | - Matthias A Mutke
- Department of Neuroradiology, Heidelberg University Hospital, Germany (M.A.M.)
| | - Dietmar Frey
- Charité Lab for Artificial Intelligence in Medicine (CLAIM) (E.M.Z.A., A.H., D.F.), Charité Universitätsmedizin Berlin, Germany
| |
Collapse
|
16
|
Qian J, Li H, Wang J, He L. Recent Advances in Explainable Artificial Intelligence for Magnetic Resonance Imaging. Diagnostics (Basel) 2023; 13:1571. [PMID: 37174962 PMCID: PMC10178221 DOI: 10.3390/diagnostics13091571] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2023] [Revised: 03/29/2023] [Accepted: 04/26/2023] [Indexed: 05/15/2023] Open
Abstract
Advances in artificial intelligence (AI), especially deep learning (DL), have facilitated magnetic resonance imaging (MRI) data analysis, enabling AI-assisted medical image diagnoses and prognoses. However, most of the DL models are considered as "black boxes". There is an unmet need to demystify DL models so domain experts can trust these high-performance DL models. This has resulted in a sub-domain of AI research called explainable artificial intelligence (XAI). In the last decade, many experts have dedicated their efforts to developing novel XAI methods that are competent at visualizing and explaining the logic behind data-driven DL models. However, XAI techniques are still in their infancy for medical MRI image analysis. This study aims to outline the XAI applications that are able to interpret DL models for MRI data analysis. We first introduce several common MRI data modalities. Then, a brief history of DL models is discussed. Next, we highlight XAI frameworks and elaborate on the principles of multiple popular XAI methods. Moreover, studies on XAI applications in MRI image analysis are reviewed across the tissues/organs of the human body. A quantitative analysis is conducted to reveal the insights of MRI researchers on these XAI techniques. Finally, evaluations of XAI methods are discussed. This survey presents recent advances in the XAI domain for explaining the DL models that have been utilized in MRI applications.
Collapse
Affiliation(s)
- Jinzhao Qian
- Imaging Research Center, Department of Radiology, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH 45229, USA
- Department of Computer Science, University of Cincinnati, Cincinnati, OH 45221, USA
| | - Hailong Li
- Imaging Research Center, Department of Radiology, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH 45229, USA
- Department of Radiology, College of Medicine, University of Cincinnati, Cincinnati, OH 45221, USA
| | - Junqi Wang
- Imaging Research Center, Department of Radiology, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH 45229, USA
| | - Lili He
- Imaging Research Center, Department of Radiology, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH 45229, USA
- Department of Computer Science, University of Cincinnati, Cincinnati, OH 45221, USA
- Department of Radiology, College of Medicine, University of Cincinnati, Cincinnati, OH 45221, USA
| |
Collapse
|
17
|
Nazir S, Dickson DM, Akram MU. Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks. Comput Biol Med 2023; 156:106668. [PMID: 36863192 DOI: 10.1016/j.compbiomed.2023.106668] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2022] [Revised: 01/12/2023] [Accepted: 02/10/2023] [Indexed: 02/21/2023]
Abstract
Artificial Intelligence (AI) techniques of deep learning have revolutionized the disease diagnosis with their outstanding image classification performance. In spite of the outstanding results, the widespread adoption of these techniques in clinical practice is still taking place at a moderate pace. One of the major hindrance is that a trained Deep Neural Networks (DNN) model provides a prediction, but questions about why and how that prediction was made remain unanswered. This linkage is of utmost importance for the regulated healthcare domain to increase the trust in the automated diagnosis system by the practitioners, patients and other stakeholders. The application of deep learning for medical imaging has to be interpreted with caution due to the health and safety concerns similar to blame attribution in the case of an accident involving autonomous cars. The consequences of both a false positive and false negative cases are far reaching for patients' welfare and cannot be ignored. This is exacerbated by the fact that the state-of-the-art deep learning algorithms comprise of complex interconnected structures, millions of parameters, and a 'black box' nature, offering little understanding of their inner working unlike the traditional machine learning algorithms. Explainable AI (XAI) techniques help to understand model predictions which help develop trust in the system, accelerate the disease diagnosis, and meet adherence to regulatory requirements. This survey provides a comprehensive review of the promising field of XAI for biomedical imaging diagnostics. We also provide a categorization of the XAI techniques, discuss the open challenges, and provide future directions for XAI which would be of interest to clinicians, regulators and model developers.
Collapse
Affiliation(s)
- Sajid Nazir
- Department of Computing, Glasgow Caledonian University, Glasgow, UK.
| | - Diane M Dickson
- Department of Podiatry and Radiography, Research Centre for Health, Glasgow Caledonian University, Glasgow, UK
| | - Muhammad Usman Akram
- Computer and Software Engineering Department, National University of Sciences and Technology, Islamabad, Pakistan
| |
Collapse
|
18
|
Moulton E, Valabregue R, Piotin M, Marnat G, Saleme S, Lapergue B, Lehericy S, Clarencon F, Rosso C. Interpretable deep learning for the prognosis of long-term functional outcome post-stroke using acute diffusion weighted imaging. J Cereb Blood Flow Metab 2023; 43:198-209. [PMID: 36169033 PMCID: PMC9903217 DOI: 10.1177/0271678x221129230] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/17/2021] [Revised: 08/19/2022] [Accepted: 09/04/2022] [Indexed: 01/24/2023]
Abstract
Advances in deep learning can be applied to acute stroke imaging to build powerful and explainable prediction models that could supersede traditionally used biomarkers. We aimed to evaluate the performance and interpretability of a deep learning model based on convolutional neural networks (CNN) in predicting long-term functional outcome with diffusion-weighted imaging (DWI) acquired at day 1 post-stroke. Ischemic stroke patients (n = 322) were included from the ASTER and INSULINFARCT trials as well as the Pitié-Salpêtrière registry. We trained a CNN to predict long-term functional outcome assessed at 3 months with the modified Rankin Scale (dichotomized as good [mRS ≤ 2] vs. poor [mRS ≥ 3]) and compared its performance to two logistic regression models using lesion volume and ASPECTS. The CNN contained an attention mechanism, which allowed to visualize the areas of the brain that drove prediction. The deep learning model yielded a significantly higher area under the curve (0.83 95%CI [0.78-0.87]) than lesion volume (0.78 [0.73-0.83]) and ASPECTS (0.77 [0.71-0.83]) (p < 0.05). Setting all classifiers to the specificity as the deep learning model (i.e., 0.87 [0.82-0.92]), the CNN yielded a significantly higher sensitivity (0.67 [0.59-0.73]) than lesion volume (0.48 [0.40-0.56]) and ASPECTS (0.50 [0.41-0.58]) (p = 0.002). The attention mechanism revealed that the network learned to naturally attend to the lesion to predict outcome.
Collapse
Affiliation(s)
- Eric Moulton
- Institut du Cerveau et de la Moelle épinière, ICM, Inserm U 1127, CNRS UMR 7225, Sorbonne Université, Paris, France
| | - Romain Valabregue
- Institut du Cerveau et de la Moelle épinière, ICM, Inserm U 1127, CNRS UMR 7225, Sorbonne Université, Paris, France
- Centre de Neuro-Imagerie de Recherche, CENIR, ICM, Paris, France
| | - Michel Piotin
- Department of Diagnostic and Interventional Neuroradiology, Rothschild Foundation, Paris, France
| | - Gaultier Marnat
- Department of Diagnostic and Interventional Neuroradiology, University Hospital of Bordeaux, Bordeaux, France
| | - Suzana Saleme
- Diagnostic and Interventional Neuroradiology, University Hospital of Limoges, Limoges, France
| | - Bertrand Lapergue
- Department of Stroke Center and Diagnostic and Interventional Neuroradiology, University of Versailles and Saint Quentin en Yvelines, Foch Hospital, Suresnes, France
| | - Stephane Lehericy
- Institut du Cerveau et de la Moelle épinière, ICM, Inserm U 1127, CNRS UMR 7225, Sorbonne Université, Paris, France
- Centre de Neuro-Imagerie de Recherche, CENIR, ICM, Paris, France
- AP-HP Service de Neuroradiologie diagnostique, Hôpital Pitié-Salpêtrière, Paris, France
| | - Frederic Clarencon
- Institut du Cerveau et de la Moelle épinière, ICM, Inserm U 1127, CNRS UMR 7225, Sorbonne Université, Paris, France
- AP-HP Service de Neuroradiologie interventionelle Hôpital Pitié-Salpêtrière, Paris, France
- ICM iCRIN team: STAR (Stroke Therapy And Registries)
| | - Charlotte Rosso
- Institut du Cerveau et de la Moelle épinière, ICM, Inserm U 1127, CNRS UMR 7225, Sorbonne Université, Paris, France
- ICM iCRIN team: STAR (Stroke Therapy And Registries)
- AP-HP, Urgences Cérébro-Vasculaires, Hôpital Pitié-Salpêtrière, Paris, France
| |
Collapse
|
19
|
Gerbasi A, Konduri P, Tolhuisen M, Cavalcante F, Rinkel L, Kappelhof M, Wolff L, Coutinho JM, Emmer BJ, Costalat V, Arquizan C, Hofmeijer J, Uyttenboogaart M, van Zwam W, Roos Y, Quaglini S, Bellazzi R, Majoie C, Marquering H. Prognostic Value of Combined Radiomic Features from Follow-Up DWI and T2-FLAIR in Acute Ischemic Stroke. J Cardiovasc Dev Dis 2022; 9:jcdd9120468. [PMID: 36547465 PMCID: PMC9786822 DOI: 10.3390/jcdd9120468] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2022] [Revised: 12/13/2022] [Accepted: 12/15/2022] [Indexed: 12/24/2022] Open
Abstract
The biological pathways involved in lesion formation after an acute ischemic stroke (AIS) are poorly understood. Despite successful reperfusion treatment, up to two thirds of patients with large vessel occlusion remain functionally dependent. Imaging characteristics extracted from DWI and T2-FLAIR follow-up MR sequences could aid in providing a better understanding of the lesion constituents. We built a fully automated pipeline based on a tree ensemble machine learning model to predict poor long-term functional outcome in patients from the MR CLEAN-NO IV trial. Several feature sets were compared, considering only imaging, only clinical, or both types of features. Nested cross-validation with grid search and a feature selection procedure based on SHapley Additive exPlanations (SHAP) was used to train and validate the models. Considering features from both imaging modalities in combination with clinical characteristics led to the best prognostic model (AUC = 0.85, 95%CI [0.81, 0.89]). Moreover, SHAP values showed that imaging features from both sequences have a relevant impact on the final classification, with texture heterogeneity being the most predictive imaging biomarker. This study suggests the prognostic value of both DWI and T2-FLAIR follow-up sequences for AIS patients. If combined with clinical characteristics, they could lead to better understanding of lesion pathophysiology and improved long-term functional outcome prediction.
Collapse
Affiliation(s)
- Alessia Gerbasi
- Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 PV Pavia, Italy
- Correspondence:
| | - Praneeta Konduri
- Department of Biomedical Engineering and Physics, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
- Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
| | - Manon Tolhuisen
- Department of Biomedical Engineering and Physics, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
- Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
| | - Fabiano Cavalcante
- Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
| | - Leon Rinkel
- Department of Neurology, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
| | - Manon Kappelhof
- Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
| | - Lennard Wolff
- Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Center, 3015 Rotterdam, The Netherlands
| | - Jonathan M. Coutinho
- Department of Neurology, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
| | - Bart J. Emmer
- Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
| | - Vincent Costalat
- Department of Neuroradiology, Centre Hospitalier Universitaire de Montpellier, 34400 Montpellier, France
| | - Caroline Arquizan
- Department of Neurology, Centre Hospitalier Universitaire de Montpellier, 34400 Montpellier, France
| | - Jeannette Hofmeijer
- Department of Neurology, Rijnstate Hospital, 6836 BH Arnhem, The Netherlands
| | - Maarten Uyttenboogaart
- Department of Neurology and Department of Medical Imaging Center, University Medical Center Groningen, 9713 GZ Groningen, The Netherlands
| | - Wim van Zwam
- Department of Radiology and Nuclear Medicine, Maastricht University Medical Center, 6229 HX Maastricht, The Netherlands
| | - Yvo Roos
- Department of Neurology, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
| | - Silvana Quaglini
- Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 PV Pavia, Italy
| | - Riccardo Bellazzi
- Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 PV Pavia, Italy
| | - Charles Majoie
- Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
| | - Henk Marquering
- Department of Biomedical Engineering and Physics, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
- Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
| |
Collapse
|
20
|
Eshmawi AA, Khayyat M, Algarni AD, Hilali-jaghdam I. An Ensemble of Deep Learning Enabled Brain Stroke Classification Model in Magnetic Resonance Images. Journal of Healthcare Engineering 2022; 2022:1-11. [PMID: 36437817 PMCID: PMC9699768 DOI: 10.1155/2022/7815434] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/30/2021] [Revised: 01/27/2022] [Accepted: 02/04/2022] [Indexed: 11/19/2022]
Abstract
Brain stroke is a major cause of global death and it necessitates earlier identification process to reduce the mortality rate. Magnetic resonance imaging (MRI) techniques is a commonly available imaging modality used to diagnose brain stroke. Presently, machine learning (ML) and deep learning (DL) models can be extremely utilized for disease detection and classification processes. Amongst the available approaches, the convolutional neural network (CNN) models have been widely used for computer vision and image processing issues such as ImageNet, facial detection, and digit classification. In this article, a novel computer aided diagnosis (CAD) based brain stroke detection and classification (CAD-BSDC) model has been developed for MRI images. The proposed CAD-BSDC technique aims in classifying the provided MR brain image as normal or abnormal. The CAD-BSDC technique involves different subprocesses such as preprocessing, feature extraction, and classification. Firstly, the input image undergoes preprocessing using adaptive thresholding (AT) technique for improving the image quality. Followed by, an ensemble of feature extractors such as MobileNet, CapsuleNet, and EfficientNet models are used. Besides, the hyperparameter tuning of the deep learning models takes place using the improved dragonfly optimization (IDFO) algorithm. Moreover, satin bowerbird optimization (SBO) based stacked autoencoder (SAE) is used for the classification of brain stroke. The design of optimal SAE using the SBO algorithm shows the novelty of the work. The performance of the presented technique was validated utilizing benchmark dataset which includes T2-weighted MR brain image collected from the axial axis with size of 256 × 256. The simulation outcomes indicated the promising efficiency of the proposed CAD-BSDC technique over the latest state of art approaches in terms of various performance measures.
Collapse
|
21
|
ALHATEMİ RAJ, SAVAŞ S. Transfer Learning-Based Classification Comparison of Stroke. BBD 2022. [DOI: 10.53070/bbd.1172807] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022] Open
Abstract
One type of brain disease that significantly harms people's lives and health is stroke. The diagnosis and management of strokes both heavily rely on the quantitative analysis of brain Magnetic Resonance (MR) images. The early diagnosis process is of great importance for the prevention of stroke cases. Stroke prediction is made possible by deep neural networks with the capacity for enormous data learning. Therefore, in thus study, several deep neural network models, including DenseNet121, ResNet50, Xception, MobileNet, VGG16, and EfficientNetB2 are proposed for transfer learning to classify MR images into two categories (stroke and non-stroke) in order to study the characteristics of the stroke lesions and achieve full intelligent automatic detection. The study dataset comprises of 1901 training images, 475 validation images, and 250 testing images. On the training and validation sets, data augmentation was used to increase the number of images to improve the models’ learning. The experimental results outperform all the state of arts that were used the same dataset. The overall accuracy of the best model is 98.8% and the same value for precision, recall, and f1-score using the EfficientNetB2 model for transfer learning.
Collapse
|
22
|
Zeng M, Oakden-Rayner L, Bird A, Smith L, Wu Z, Scroop R, Kleinig T, Jannes J, Jenkinson M, Palmer LJ. Pre-thrombectomy prognostic prediction of large-vessel ischemic stroke using machine learning: A systematic review and meta-analysis. Front Neurol 2022; 13:945813. [PMID: 36158960 PMCID: PMC9495610 DOI: 10.3389/fneur.2022.945813] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2022] [Accepted: 08/18/2022] [Indexed: 11/20/2022] Open
Abstract
Introduction Machine learning (ML) methods are being increasingly applied to prognostic prediction for stroke patients with large vessel occlusion (LVO) treated with endovascular thrombectomy. This systematic review aims to summarize ML-based pre-thrombectomy prognostic models for LVO stroke and identify key research gaps. Methods Literature searches were performed in Embase, PubMed, Web of Science, and Scopus. Meta-analyses of the area under the receiver operating characteristic curves (AUCs) of ML models were conducted to synthesize model performance. Results Sixteen studies describing 19 models were eligible. The predicted outcomes include functional outcome at 90 days, successful reperfusion, and hemorrhagic transformation. Functional outcome was analyzed by 10 conventional ML models (pooled AUC=0.81, 95% confidence interval [CI]: 0.77–0.85, AUC range: 0.68–0.93) and four deep learning (DL) models (pooled AUC=0.75, 95% CI: 0.70–0.81, AUC range: 0.71–0.81). Successful reperfusion was analyzed by three conventional ML models (pooled AUC=0.72, 95% CI: 0.56–0.88, AUC range: 0.55–0.88) and one DL model (AUC=0.65, 95% CI: 0.62–0.68). Conclusions Conventional ML and DL models have shown variable performance in predicting post-treatment outcomes of LVO without generally demonstrating superiority compared to existing prognostic scores. Most models were developed using small datasets, lacked solid external validation, and at high risk of potential bias. There is considerable scope to improve study design and model performance. The application of ML and DL methods to improve the prediction of prognosis in LVO stroke, while promising, remains nascent. Systematic review registration https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021266524, identifier CRD42021266524
Collapse
Affiliation(s)
- Minyan Zeng
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
- School of Public Health, University of Adelaide, Adelaide, SA, Australia
- *Correspondence: Minyan Zeng
| | - Lauren Oakden-Rayner
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
- School of Public Health, University of Adelaide, Adelaide, SA, Australia
- Department of Radiology, Royal Adelaide Hospital, Adelaide, SA, Australia
| | - Alix Bird
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
- School of Public Health, University of Adelaide, Adelaide, SA, Australia
| | - Luke Smith
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
- School of Public Health, University of Adelaide, Adelaide, SA, Australia
| | - Zimu Wu
- School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, Australia
| | - Rebecca Scroop
- Department of Radiology, Royal Adelaide Hospital, Adelaide, SA, Australia
- Faculty Health and Medical Science, School of Medicine, University of Adelaide, Adelaide, SA, Australia
| | - Timothy Kleinig
- Faculty Health and Medical Science, School of Medicine, University of Adelaide, Adelaide, SA, Australia
- Department of Neurology, Royal Adelaide Hospital, Adelaide, SA, Australia
| | - Jim Jannes
- Faculty Health and Medical Science, School of Medicine, University of Adelaide, Adelaide, SA, Australia
- Department of Neurology, Royal Adelaide Hospital, Adelaide, SA, Australia
| | - Mark Jenkinson
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
- Functional Magnetic Resonance Imaging of the Brain Centre, University of Oxford, Oxford, United Kingdom
| | - Lyle J. Palmer
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
- School of Public Health, University of Adelaide, Adelaide, SA, Australia
| |
Collapse
|
23
|
Huang C, Wang J, Wang SH, Zhang YD. Applicable artificial intelligence for brain disease: A survey. Neurocomputing 2022. [DOI: 10.1016/j.neucom.2022.07.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/17/2022]
|
24
|
Zhang Z, Song C, Zhang L, Yang W. Predictive Modeling of Short-Term Poor Prognosis of Successful Reperfusion after Endovascular Treatment in Patients with Anterior Circulation Acute Ischemic Stroke. Journal of Healthcare Engineering 2022; 2022:1-9. [PMID: 35991294 PMCID: PMC9391146 DOI: 10.1155/2022/3185211] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/14/2022] [Revised: 06/10/2022] [Accepted: 07/07/2022] [Indexed: 11/24/2022]
Abstract
This study aimed to propose and internally validate a prediction model of short-term poor prognosis in patients with acute ischemic stroke (AIS). In the retrospective study, 356 eligible AIS patients receiving endovascular treatment (EVT) were included and divided into the good prognosis group and the poor prognosis group. Data from 70% of patients were collected as training set and the 30% as validation set. Univariate analysis and multivariate logistic regression were used for identifying independent predictors. The performance of the model was evaluated by receiver operating characteristic (ROC) curve and the paired Chi-square test was used for internal validation. A model for the prediction of short-term poor prognosis in atherosclerotic AIS patients who successfully underwent endovascular reperfusion was developed: log (Pr/1 − Pr) = 3.500 + Blood glucose ∗ 0.174 + Infarct volume ∗ 0.128 + the National Institutes of Health Stroke Scale score × Onset-to-reperfusion time (NIHSS-ORT) ∗ 0.014 + Intraoperative hypotension (Yes) ∗ 1.037 + Mean arterial pressure (MAP) decrease from baseline (>40%) ∗ 2.061 (Pr represented the probability of short-term poor prognosis). The area under the curve (AUC) was 0.806 (0.748 − 0.864) in the training set and 0.850 (0.779 − 0.920) in the testing set, which suggested the good performance of the model. We proposed and validated a combined prediction model to predict the short-term poor prognosis of AIS patients after EVT, which could provide reference for clinicians to identify AIS patients with a higher risk of poor outcomes and thus improving the prognosis of EVT.
Collapse
|
25
|
Tolhuisen ML, Hoving JW, Koopman MS, Kappelhof M, van Voorst H, Bruggeman AE, Demchuck AM, Dippel DWJ, Emmer BJ, Bracard S, Guillemin F, van Oostenbrugge RJ, Mitchell PJ, van Zwam WH, Hill MD, Roos YBWEM, Jovin TG, Berkhemer OA, Campbell BCV, Saver J, White P, Muir KW, Goyal M, Marquering HA, Majoie CB, Caan MWA. Outcome Prediction Based on Automatically Extracted Infarct Core Image Features in Patients with Acute Ischemic Stroke. Diagnostics (Basel) 2022; 12:1786. [PMID: 35892499 PMCID: PMC9331690 DOI: 10.3390/diagnostics12081786] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2022] [Revised: 07/09/2022] [Accepted: 07/18/2022] [Indexed: 11/18/2022] Open
Abstract
Infarct volume (FIV) on follow-up diffusion-weighted imaging (FU-DWI) is only moderately associated with functional outcome in acute ischemic stroke patients. However, FU-DWI may contain other imaging biomarkers that could aid in improving outcome prediction models for acute ischemic stroke. We included FU-DWI data from the HERMES, ISLES, and MR CLEAN-NO IV databases. Lesions were segmented using a deep learning model trained on the HERMES and ISLES datasets. We assessed the performance of three classifiers in predicting functional independence for the MR CLEAN-NO IV trial cohort based on: (1) FIV alone, (2) the most important features obtained from a trained convolutional autoencoder (CAE), and (3) radiomics. Furthermore, we investigated feature importance in the radiomic-feature-based model. For outcome prediction, we included 206 patients: 144 scans were included in the training set, 21 in the validation set, and 41 in the test set. The classifiers that included the CAE and the radiomic features showed AUC values of 0.88 and 0.81, respectively, while the model based on FIV had an AUC of 0.79. This difference was not found to be statistically significant. Feature importance results showed that lesion intensity heterogeneity received more weight than lesion volume in outcome prediction. This study suggests that predictions of functional outcome should not be based on FIV alone and that FU-DWI images capture additional prognostic information.
Collapse
|
26
|
van der Velden BH, Kuijf HJ, Gilhuijs KG, Viergever MA. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis. Med Image Anal 2022; 79:102470. [DOI: 10.1016/j.media.2022.102470] [Citation(s) in RCA: 22] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2021] [Revised: 03/15/2022] [Accepted: 05/02/2022] [Indexed: 12/11/2022]
|
27
|
Samak ZA, Clatworthy P, Mirmehdi M. FeMA: Feature matching auto-encoder for predicting ischaemic stroke evolution and treatment outcome. Comput Med Imaging Graph 2022; 99:102089. [PMID: 35738186 DOI: 10.1016/j.compmedimag.2022.102089] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2021] [Revised: 05/04/2022] [Accepted: 06/03/2022] [Indexed: 01/05/2023]
Abstract
Although, predicting ischaemic stroke evolution and treatment outcome provide important information one step towards individual treatment planning, classifying functional outcome and modelling the brain tissue evolution remains a challenge due to data complexity and visually subtle changes in the brain. We propose a novel deep learning approach, Feature Matching Auto-encoder (FeMA) that consists of two stages, predicting ischaemic stroke evolution at one week without voxel-wise annotation and predicting ischaemic stroke treatment outcome at 90 days from a baseline scan. In the first stage, we introduce feature similarity and consistency objective, and in the second stage, we show that adding stroke evolution information increase the performance of functional outcome prediction. Comparative experiments demonstrate that our proposed method is more effective to extract representative follow-up features and achieves the best results for functional outcome of stroke treatment.
Collapse
Affiliation(s)
- Zeynel A Samak
- Department of Computer Science, University of Bristol, Bristol, UK.
| | - Philip Clatworthy
- Translational Health Sciences, University of Bristol, Bristol, UK; Stroke Neurology, Southmead Hospital, North Bristol NHS Trust, Bristol, UK.
| | - Majid Mirmehdi
- Department of Computer Science, University of Bristol, Bristol, UK.
| |
Collapse
|
28
|
Mäkelä T, Öman O, Hokkinen L, Wilppu U, Salli E, Savolainen S, Kangasniemi M. Automatic CT Angiography Lesion Segmentation Compared to CT Perfusion in Ischemic Stroke Detection: a Feasibility Study. J Digit Imaging 2022; 35:551-563. [PMID: 35211838 PMCID: PMC9156593 DOI: 10.1007/s10278-022-00611-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2021] [Revised: 12/30/2021] [Accepted: 01/12/2022] [Indexed: 12/15/2022] Open
Abstract
In stroke imaging, CT angiography (CTA) is used for detecting arterial occlusions. These images could also provide information on the extent of ischemia. The study aim was to develop and evaluate a convolutional neural network (CNN)-based algorithm for detecting and segmenting acute ischemic lesions from CTA images of patients with suspected middle cerebral artery stroke. These results were compared to volumes reported by widely used CT perfusion-based RAPID software (IschemaView). A 42-layer-deep CNN was trained on 50 CTA volumes with manually delineated targets. The lower bound for predicted lesion size to reliably discern stroke from false positives was estimated. The severity of false positives and false negatives was reviewed visually to assess the clinical applicability and to further guide the method development. The CNN model corresponded to the manual segmentations with voxel-wise sensitivity 0.54 (95% confidence interval: 0.44-0.63), precision 0.69 (0.60-0.76), and Sørensen-Dice coefficient 0.61 (0.52-0.67). Stroke/nonstroke differentiation accuracy 0.88 (0.81-0.94) was achieved when only considering the predicted lesion size (i.e., regardless of location). By visual estimation, 46% of cases showed some false findings, such as CNN highlighting chronic periventricular white matter changes or beam hardening artifacts, but only in 9% the errors were severe, translating to 0.91 accuracy. The CNN model had a moderately strong correlation to RAPID-reported Tmax > 10 s volumes (Pearson's r = 0.76 (0.58-0.86)). The results suggest that detecting anterior circulation ischemic strokes from CTA using a CNN-based algorithm can be feasible when accompanied with physiological knowledge to rule out false positives.
Collapse
Affiliation(s)
- Teemu Mäkelä
- grid.7737.40000 0004 0410 2071HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, Haartmaninkatu 4, P.O. Box 340, 00290 Helsinki, Finland ,grid.7737.40000 0004 0410 2071Department of Physics, University of Helsinki, P.O. Box 64, 00014 Helsinki, Finland
| | - Olli Öman
- grid.7737.40000 0004 0410 2071HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, Haartmaninkatu 4, P.O. Box 340, 00290 Helsinki, Finland
| | - Lasse Hokkinen
- grid.7737.40000 0004 0410 2071HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, Haartmaninkatu 4, P.O. Box 340, 00290 Helsinki, Finland
| | - Ulla Wilppu
- grid.7737.40000 0004 0410 2071HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, Haartmaninkatu 4, P.O. Box 340, 00290 Helsinki, Finland
| | - Eero Salli
- grid.7737.40000 0004 0410 2071HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, Haartmaninkatu 4, P.O. Box 340, 00290 Helsinki, Finland
| | - Sauli Savolainen
- grid.7737.40000 0004 0410 2071HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, Haartmaninkatu 4, P.O. Box 340, 00290 Helsinki, Finland ,grid.7737.40000 0004 0410 2071Department of Physics, University of Helsinki, P.O. Box 64, 00014 Helsinki, Finland
| | - Marko Kangasniemi
- grid.7737.40000 0004 0410 2071HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, Haartmaninkatu 4, P.O. Box 340, 00290 Helsinki, Finland
| |
Collapse
|
29
|
Ji H, Lafata K, Mowery Y, Brizel D, Bertozzi AL, Yin FF, Wang C. Post-Radiotherapy PET Image Outcome Prediction by Deep Learning Under Biological Model Guidance: A Feasibility Study of Oropharyngeal Cancer Application. Front Oncol 2022; 12:895544. [PMID: 35646643 PMCID: PMC9135979 DOI: 10.3389/fonc.2022.895544] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2022] [Accepted: 04/11/2022] [Indexed: 01/03/2023] Open
Abstract
PurposeTo develop a method of biologically guided deep learning for post-radiation 18FDG-PET image outcome prediction based on pre-radiation images and radiotherapy dose information.MethodsBased on the classic reaction–diffusion mechanism, a novel biological model was proposed using a partial differential equation that incorporates spatial radiation dose distribution as a patient-specific treatment information variable. A 7-layer encoder–decoder-based convolutional neural network (CNN) was designed and trained to learn the proposed biological model. As such, the model could generate post-radiation 18FDG-PET image outcome predictions with breakdown biological components for enhanced explainability. The proposed method was developed using 64 oropharyngeal patients with paired 18FDG-PET studies before and after 20-Gy delivery (2 Gy/day fraction) by intensity-modulated radiotherapy (IMRT). In a two-branch deep learning execution, the proposed CNN learns specific terms in the biological model from paired 18FDG-PET images and spatial dose distribution in one branch, and the biological model generates post-20-Gy 18FDG-PET image prediction in the other branch. As in 2D execution, 718/233/230 axial slices from 38/13/13 patients were used for training/validation/independent test. The prediction image results in test cases were compared with the ground-truth results quantitatively.ResultsThe proposed method successfully generated post-20-Gy 18FDG-PET image outcome prediction with breakdown illustrations of biological model components. Standardized uptake value (SUV) mean values in 18FDG high-uptake regions of predicted images (2.45 ± 0.25) were similar to ground-truth results (2.51 ± 0.33). In 2D-based Gamma analysis, the median/mean Gamma Index (<1) passing rate of test images was 96.5%/92.8% using the 5%/5 mm criterion; such result was improved to 99.9%/99.6% when 10%/10 mm was adopted.ConclusionThe developed biologically guided deep learning method achieved post-20-Gy 18FDG-PET image outcome predictions in good agreement with ground-truth results. With the breakdown biological modeling components, the outcome image predictions could be used in adaptive radiotherapy decision-making to optimize personalized plans for the best outcome in the future.
Collapse
Affiliation(s)
- Hangjie Ji
- Department of Mathematics, North Carolina State University, Raleigh, NC, United States
| | - Kyle Lafata
- Department of Radiation Oncology, Duke University Medical Center, Durham, NC, United States
- Department of Radiology, Duke University Medical Center, Durham, NC, United States
- Department of Electrical and Computer Engineering, Duke University, Durham, NC, United States
| | - Yvonne Mowery
- Department of Radiation Oncology, Duke University Medical Center, Durham, NC, United States
| | - David Brizel
- Department of Radiation Oncology, Duke University Medical Center, Durham, NC, United States
| | - Andrea L. Bertozzi
- Mechanical and Aerospace Engineering Department, University of California, Los Angeles, Los Angeles, CA, United States
- Department of Mathematics, University of California, Los Angeles, Los Angeles, CA, United States
| | - Fang-Fang Yin
- Department of Radiation Oncology, Duke University Medical Center, Durham, NC, United States
| | - Chunhao Wang
- Department of Radiation Oncology, Duke University Medical Center, Durham, NC, United States
- *Correspondence: Chunhao Wang,
| |
Collapse
|
30
|
Zihni E, McGarry BL, Kelleher JD. Moving Toward Explainable Decisions of Artificial Intelligence Models for the Prediction of Functional Outcomes of Ischemic Stroke Patients. Digit Health 2022. [DOI: 10.36255/exon-publications-digital-health-explainable-decisions] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
|
31
|
Ramos LA, van Os H, Hilbert A, Olabarriaga SD, van der Lugt A, Roos YBWEM, van Zwam WH, van Walderveen MAA, Ernst M, Zwinderman AH, Strijkers GJ, Majoie CBLM, Wermer MJH, Marquering HA. Combination of Radiological and Clinical Baseline Data for Outcome Prediction of Patients With an Acute Ischemic Stroke. Front Neurol 2022; 13:809343. [PMID: 35432171 PMCID: PMC9010547 DOI: 10.3389/fneur.2022.809343] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2021] [Accepted: 03/08/2022] [Indexed: 11/13/2022] Open
Abstract
Background Accurate prediction of clinical outcome is of utmost importance for choices regarding the endovascular treatment (EVT) of acute stroke. Recent studies on the prediction modeling for stroke focused mostly on clinical characteristics and radiological scores available at baseline. Radiological images are composed of millions of voxels, and a lot of information can be lost when representing this information by a single value. Therefore, in this study we aimed at developing prediction models that take into account the whole imaging data combined with clinical data available at baseline. Methods We included 3,279 patients from the MR CLEAN Registry; a prospective, observational, multicenter registry of patients with ischemic stroke treated with EVT. We developed two approaches to combine the imaging data with the clinical data. The first approach was based on radiomics features, extracted from 70 atlas regions combined with the clinical data to train machine learning models. For the second approach, we trained 3D deep learning models using the whole images and the clinical data. Models trained with the clinical data only were compared with models trained with the combination of clinical and image data. Finally, we explored feature importance plots for the best models and identified many known variables and image features/brain regions that were relevant in the model decision process. Results From 3,279 patients included, 1,241 (37%) patients had a good functional outcome [modified Rankin Scale (mRS) ≤ 2] and 1,954 (60%) patients had good reperfusion [modified Thrombolysis in Cerebral Infarction (eTICI) ≥ 2b]. There was no significant improvement by combining the image data to the clinical data for mRS prediction [mean area under the receiver operating characteristic (ROC) curve (AUC) of 0.81 vs. 0.80] above using the clinical data only, regardless of the approach used. Regarding predicting reperfusion, there was a significant improvement when image and clinical features were combined (mean AUC of 0.54 vs. 0.61), with the highest AUC obtained by the deep learning approach. Conclusions The combination of radiomics and deep learning image features with clinical data significantly improved the prediction of good reperfusion. The visualization of prediction feature importance showed both known and novel clinical and imaging features with predictive values.
Collapse
Affiliation(s)
- Lucas A. Ramos
- Department of Biomedical Engineering and Physics, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, Netherlands
- Department of Clinical Epidemiology and Data Science, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, Netherlands
- *Correspondence: Lucas A. Ramos
| | - Hendrikus van Os
- Department of Neurology, Leiden University Medical Center, Leiden, Netherlands
| | - Adam Hilbert
- Department of Biomedical Engineering and Physics, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, Netherlands
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Silvia D. Olabarriaga
- Department of Clinical Epidemiology and Data Science, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, Netherlands
| | - Aad van der Lugt
- Department of Radiology and Nuclear Medicine, Erasmus Medical Center (MC) - University Medical Center, Rotterdam, Netherlands
| | - Yvo B. W. E. M. Roos
- Department of Neurology, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, Netherlands
| | - Wim H. van Zwam
- Department of Radiology, Cardiovascular Research Institute Maastricht, Maastricht University Medical Center, Maastricht, Netherlands
| | | | - Marielle Ernst
- Centre for Radiology and Endoscopy, Department of Diagnostic and Interventional Neuroradiology, University Medical Centre Hamburg-Eppendorf, Hamburg, Germany
| | - Aeiko H. Zwinderman
- Department of Clinical Epidemiology and Data Science, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, Netherlands
| | - Gustav J. Strijkers
- Department of Biomedical Engineering and Physics, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, Netherlands
| | - Charles B. L. M. Majoie
- Department of Radiology and Nuclear Medicine, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, Netherlands
| | | | - Henk A. Marquering
- Department of Biomedical Engineering and Physics, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, Netherlands
- Department of Radiology and Nuclear Medicine, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, Netherlands
| |
Collapse
|
32
|
Holswilder G, Stuart MPME, Dompeling T, Kruyt ND, Goeman JJ, van der Lugt A, Schonewille WJ, Lycklama à Nijeholt GJ, Majoie CBLM, Yo LSF, Meijer FJA, Marquering HA, Wermer MJH, van Walderveen MAA. The prognostic value of extracranial vascular characteristics on procedural duration and revascularization success in endovascularly treated acute ischemic stroke patients. Eur Stroke J 2022; 7:48-56. [PMID: 35300259 PMCID: PMC8921792 DOI: 10.1177/23969873211067662] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2021] [Accepted: 12/01/2021] [Indexed: 11/27/2022] Open
Abstract
Introduction Vascular anatomy might affect endovascular treatment success in acute ischemic stroke patients with large vessel occlusion. We investigated the prognostic value of extracranial vascular characteristics on procedural time and revascularization success in patients with large vessel occlusion in the anterior cerebral circulation. Patients and methods We included 828 patients endovascularly treated within 6.5 hours of symptom onset from the Dutch MR CLEAN-Registry. We evaluated aortic arch configuration, stenosis and tortuosity of supra-aortic arteries, and internal carotid arteries (ICAs) on pre-intervention CTA. We constructed logistic prediction models for outcome variables procedural duration (≥60 minutes) and non-successful revascularization (extended thrombolysis in cerebral infarction (eTICI) of 0–2A) using baseline characteristics and assessed the effect of extracranial vascular characteristics on model performance. Results Cervical ICA tortuosity and stenosis ≥99% improved prediction of long procedural duration compared with baseline characteristics from area under the curve of 0.61 (95% CI: 0.57–0.65) to 0.66 (95% CI: 0.62–0.70) (P < 0.001). Cervical ICA tortuosity was significantly associated with non-successful recanalization. Prediction of non-successful revascularization did not improve after including aortic arch elongation, acute take-off angle, aortic variant, origin stenosis of supra-aortic arteries, and cervical ICA tortuosity, with an area under the curve of 0.63 (95% CI: 0.59–0.67) compared with 0.59 (95% CI: 0.55–0.63) (P = 0.11). Conclusion Extracranial vascular characteristics have additional prognostic value for procedural duration, but not for revascularization success, compared with baseline characteristics. Performance of both prediction models is limited in patients treated for large vessel occlusion.
Collapse
Affiliation(s)
| | - Maaike PME Stuart
- Department of Radiology, Leiden University Medical Center, Leiden, Netherlands
| | - Tine Dompeling
- Department of Radiology, Leiden University Medical Center, Leiden, Netherlands
| | - Nyika D Kruyt
- Department of Neurology, Leiden University Medical Center, Leiden, Netherlands
| | - Jelle J Goeman
- Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, Netherlands
| | - Aad van der Lugt
- Department of Radiology, Erasmus MC University Medical Center, Rotterdam, Netherlands
| | | | | | - Charles BLM Majoie
- Department of Radiology and Nuclear Medicine, Amsterdam University Medical Center, University of Amsterdam, Amsterdam, Netherlands
| | - Lonneke SF Yo
- Department of Radiology, Catharina Hospital, Eindhoven, Netherlands
| | - Frederick JA Meijer
- Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, Netherlands
| | - Henk A Marquering
- Department of Radiology and Nuclear Medicine, Amsterdam University Medical Center, University of Amsterdam, Amsterdam, Netherlands
| | - Marieke JH Wermer
- Department of Neurology, Leiden University Medical Center, Leiden, Netherlands
| | | | | |
Collapse
|
33
|
Abstract
Predicting functional outcomes after an Ischemic Stroke (IS) is highly valuable for patients and desirable for physicians. This facilitates physicians to set reasonable goals for patients and cooperate with patients and relatives effectively, and furthermore to reach common after-stroke care decisions for recovery and make exercise plans to facilitate rehabilitation. The objective of this research is to apply three current Deep Learning (DL) approaches for 6-month IS outcome predictions, using the openly accessible International Stroke Trial (IST) dataset. Furthermore, another objective of this research is to compare these DL approaches with machine learning (ML) for performing in clinical prediction. After comparing various ML methods (Deep Forest, Random Forest, Support Vector Machine, etc.) with current DL frameworks (CNN, LSTM, Resnet), the results show that DL doesn’t outperform ML significantly. DL methods and reporting used for analyzing structured medical data should be developed and improved.
Collapse
|
34
|
Abstract
Machine learning techniques, also known as artificial intelligence (AI), is about to dramatically change workflow and diagnostic capabilities in diagnostic radiology. The interest in AI in Interventional Radiology is rapidly gathering pace. With this early interest in AI in procedural medicine, IR could lead the way to AI research and clinical applications for all interventional medical fields. This review will address an overview of machine learning, radiomics and AI in the field of interventional radiology, enumerating the possible applications of such techniques, while also describing techniques to overcome the challenge of limited data when applying these techniques in interventional radiology. Lastly, this review will address common errors in research in this field and suggest pathways for those interested in learning and becoming involved about AI.
Collapse
|
35
|
Huang J, Shlobin NA, DeCuypere M, Lam SK. Deep Learning for Outcome Prediction in Neurosurgery: A Systematic Review of Design, Reporting, and Reproducibility. Neurosurgery 2022; 90:16-38. [PMID: 34982868 DOI: 10.1227/neu.0000000000001736] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2021] [Accepted: 08/18/2021] [Indexed: 02/06/2023] Open
Abstract
Deep learning (DL) is a powerful machine learning technique that has increasingly been used to predict surgical outcomes. However, the large quantity of data required and lack of model interpretability represent substantial barriers to the validity and reproducibility of DL models. The objective of this study was to systematically review the characteristics of DL studies involving neurosurgical outcome prediction and to assess their bias and reporting quality. Literature search using the PubMed, Scopus, and Embase databases identified 1949 records of which 35 studies were included. Of these, 32 (91%) developed and validated a DL model while 3 (9%) validated a pre-existing model. The most commonly represented subspecialty areas were oncology (16 of 35, 46%), spine (8 of 35, 23%), and vascular (6 of 35, 17%). Risk of bias was low in 18 studies (51%), unclear in 5 (14%), and high in 12 (34%), most commonly because of data quality deficiencies. Adherence to transparent reporting of a multivariable prediction model for individual prognosis or diagnosis reporting standards was low, with a median of 12 transparent reporting of a multivariable prediction model for individual prognosis or diagnosis items (39%) per study not reported. Model transparency was severely limited because code was provided in only 3 studies (9%) and final models in 2 (6%). With the exception of public databases, no study data sets were readily available. No studies described DL models as ready for clinical use. The use of DL for neurosurgical outcome prediction remains nascent. Lack of appropriate data sets poses a major concern for bias. Although studies have demonstrated promising results, greater transparency in model development and reporting is needed to facilitate reproducibility and validation.
Collapse
Affiliation(s)
- Jonathan Huang
- Ann and Robert H. Lurie Children's Hospital, Division of Pediatric Neurosurgery, Department of Neurological Surgery, Feinberg School of Medicine, Northwestern University, Chicago, Illinois, USA
| | | | | | | |
Collapse
|
36
|
Abstract
The application of machine learning has rapidly evolved in medicine over the past decade. In stroke, commercially available machine learning algorithms have already been incorporated into clinical application for rapid diagnosis. The creation and advancement of deep learning techniques have greatly improved clinical utilization of machine learning tools and new algorithms continue to emerge with improved accuracy in stroke diagnosis and outcome prediction. Although imaging-based feature recognition and segmentation have significantly facilitated rapid stroke diagnosis and triaging, stroke prognostication is dependent on a multitude of patient specific as well as clinical factors and hence accurate outcome prediction remains challenging. Despite its vital role in stroke diagnosis and prognostication, it is important to recognize that machine learning output is only as good as the input data and the appropriateness of algorithm applied to any specific data set. Additionally, many studies on machine learning tend to be limited by small sample size and hence concerted efforts to collate data could improve evaluation of future machine learning tools in stroke. In the present state, machine learning technology serves as a helpful and efficient tool for rapid clinical decision making while oversight from clinical experts is still required to address specific aspects not accounted for in an automated algorithm. This article provides an overview of machine learning technology and a tabulated review of pertinent machine learning studies related to stroke diagnosis and outcome prediction.
Collapse
Affiliation(s)
- Shraddha Mainali
- Department of Neurology, Virginia Commonwealth University, Richmond, VA, United States
| | - Marin E Darsie
- Department of Emergency Medicine, University of Wisconsin Hospitals and Clinics, Madison, WI, United States.,Department of Neurological Surgery, University of Wisconsin Hospitals and Clinics, Madison, WI, United States
| | - Keaton S Smetana
- Department of Pharmacy, The Ohio State University Wexner Medical Center, Columbus, OH, United States
| |
Collapse
|
37
|
Hokkinen L, Mäkelä T, Savolainen S, Kangasniemi M. Computed tomography angiography-based deep learning method for treatment selection and infarct volume prediction in anterior cerebral circulation large vessel occlusion. Acta Radiol Open 2021; 10:20584601211060347. [PMID: 34868662 PMCID: PMC8637731 DOI: 10.1177/20584601211060347] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2021] [Accepted: 10/28/2021] [Indexed: 11/16/2022] Open
Abstract
Background Computed tomography perfusion (CTP) is the mainstay to determine possible
eligibility for endovascular thrombectomy (EVT), but there is still a need
for alternative methods in patient triage. Purpose To study the ability of a computed tomography angiography (CTA)-based
convolutional neural network (CNN) method in predicting final infarct volume
in patients with large vessel occlusion successfully treated with
endovascular therapy. Materials and Methods The accuracy of the CTA source image-based CNN in final infarct volume
prediction was evaluated against follow-up CT or MR imaging in 89 patients
with anterior circulation ischemic stroke successfully treated with EVT as
defined by Thrombolysis in Cerebral Infarction category 2b or 3 using
Pearson correlation coefficients and intraclass correlation coefficients.
Convolutional neural network performance was also compared to a commercially
available CTP-based software (RAPID, iSchemaView). Results A correlation with final infarct volumes was found for both CNN and CTP-RAPID
in patients presenting 6–24 h from symptom onset or last known well, with
r = 0.67 (p < 0.001) and
r = 0.82 (p < 0.001), respectively.
Correlations with final infarct volumes in the early time window (0–6 h)
were r = 0.43 (p = 0.002) for the CNN and
r = 0.58 (p < 0.001) for CTP-RAPID.
Compared to CTP-RAPID predictions, CNN estimated eligibility for
thrombectomy according to ischemic core size in the late time window with a
sensitivity of 0.38 and specificity of 0.89. Conclusion A CTA-based CNN method had moderate correlation with final infarct volumes in
the late time window in patients successfully treated with EVT.
Collapse
Affiliation(s)
- Lasse Hokkinen
- HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, Helsinki, Finland
| | - Teemu Mäkelä
- HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, Helsinki, Finland.,Department of Physics, University of Helsinki, Helsinki, Finland
| | - Sauli Savolainen
- HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, Helsinki, Finland.,Department of Physics, University of Helsinki, Helsinki, Finland
| | - Marko Kangasniemi
- HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, Helsinki, Finland
| |
Collapse
|
38
|
Kremers F, Venema E, Duvekot M, Yo L, Bokkers R, Lycklama À. Nijeholt G, van Es A, van der Lugt A, Majoie C, Burke J, Roozenbeek B, Lingsma H, Dippel D. Outcome Prediction Models for Endovascular Treatment of Ischemic Stroke: Systematic Review and External Validation. Stroke 2021; 53:825-836. [PMID: 34732070 PMCID: PMC8884132 DOI: 10.1161/strokeaha.120.033445] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022]
Abstract
Supplemental Digital Content is available in the text. Prediction models for outcome of patients with acute ischemic stroke who will undergo endovascular treatment have been developed to improve patient management. The aim of the current study is to provide an overview of preintervention models for functional outcome after endovascular treatment and to validate these models with data from daily clinical practice.
Collapse
Affiliation(s)
- Femke Kremers
- Neurology, Erasmus Medical Center, Erasmus MC Stroke Center, Rotterdam, the Netherlands (F.K., E.V., M.D., B.R., D.D.)
| | - Esmee Venema
- Neurology, Erasmus Medical Center, Erasmus MC Stroke Center, Rotterdam, the Netherlands (F.K., E.V., M.D., B.R., D.D.)
- Public Health, Erasmus Medical Center, Rotterdam, the Netherlands (E.V., H.L.)
| | - Martijne Duvekot
- Neurology, Erasmus Medical Center, Erasmus MC Stroke Center, Rotterdam, the Netherlands (F.K., E.V., M.D., B.R., D.D.)
- Neurology, Albert Schweitzer Hospital, Dordrecht, the Netherlands (M.D.)
| | - Lonneke Yo
- Radiology, Catharina Medical Center, Eindhoven, the Netherlands (L.Y.)
| | - Reinoud Bokkers
- Radiology, UMCG Groningen Medical Center, the Netherlands (R.B.)
| | | | - Adriaan van Es
- Radiology, Leiden Medical Center, the Netherlands (A.v.E.)
| | - Aad van der Lugt
- Radiology, Erasmus Medical Center, Rotterdam, the Netherlands (A.v.d.L.)
| | - Charles Majoie
- Radiology, Amsterdam Medical Center, the Netherlands (C.M.)
| | - James Burke
- Neurology, University of Michigan, Ann Arbor (J.B.)
| | - Bob Roozenbeek
- Neurology, Erasmus Medical Center, Erasmus MC Stroke Center, Rotterdam, the Netherlands (F.K., E.V., M.D., B.R., D.D.)
| | - Hester Lingsma
- Public Health, Erasmus Medical Center, Rotterdam, the Netherlands (E.V., H.L.)
| | - Diederik Dippel
- Neurology, Erasmus Medical Center, Erasmus MC Stroke Center, Rotterdam, the Netherlands (F.K., E.V., M.D., B.R., D.D.)
| |
Collapse
|
39
|
Abstract
Research into artificial intelligence (AI) has made tremendous progress over the past decade. In particular, the AI-powered analysis of images and signals has reached human-level performance in many applications owing to the efficiency of modern machine learning methods, in particular deep learning using convolutional neural networks. Research into the application of AI to medical imaging is now very active, especially in the field of cardiovascular imaging because of the challenges associated with acquiring and analysing images of this dynamic organ. In this Review, we discuss the clinical questions in cardiovascular imaging that AI can be used to address and the principal methodological AI approaches that have been developed to solve the related image analysis problems. Some approaches are purely data-driven and rely mainly on statistical associations, whereas others integrate anatomical and physiological information through additional statistical, geometric and biophysical models of the human heart. In a structured manner, we provide representative examples of each of these approaches, with particular attention to the underlying computational imaging challenges. Finally, we discuss the remaining limitations of AI approaches in cardiovascular imaging (such as generalizability and explainability) and how they can be overcome.
Collapse
Affiliation(s)
| | | | - Hubert Cochet
- IHU Liryc, CHU Bordeaux, Université Bordeaux, Inserm 1045, Pessac, France
| | - Pierre Jaïs
- IHU Liryc, CHU Bordeaux, Université Bordeaux, Inserm 1045, Pessac, France
| | | |
Collapse
|
40
|
Zhang H, Polson J, Nael K, Salamon N, Yoo B, Speier W, Arnold C. A Machine Learning Approach to Predict Acute Ischemic Stroke Thrombectomy Reperfusion using Discriminative MR Image Features. IEEE EMBS Int Conf Biomed Health Inform 2021; 2021:10.1109/bhi50953.2021.9508597. [PMID: 35813219 PMCID: PMC9261292 DOI: 10.1109/bhi50953.2021.9508597] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Mechanical thrombectomy (MTB) is one of the two standard treatment options for Acute Ischemic Stroke (AIS) patients. Current clinical guidelines instruct the use of pretreatment imaging to characterize a patient's cerebrovascular flow, as there are many factors that may underlie a patient's successful response to treatment. There is a critical need to leverage pretreatment imaging, taken at admission, to guide potential treatment avenues in an automated fashion. The aim of this study is to develop and validate a fully automated machine learning algorithm to predict the final modified thrombolysis in cerebral infarction (mTICI) score following MTB. A total 321 radiomics features were computed from segmented pretreatment MRI scans for 141 patients. Successful recanalization was defined as mTICI score >= 2c. Different feature selection methods and classification models were examined in this study. Our best performance model achieved 74.42±2.52% AUC, 75.56±4.44% sensitivity, and 76.75±4.55% specificity, showing a good prediction of reperfusion quality using pretreatment MRI. Results suggest that MR images can be informative to predicting patient response to MTB, and further validation with a larger cohort can determine the clinical utility.
Collapse
Affiliation(s)
- Haoyue Zhang
- Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA, USA
| | - Jennifer Polson
- Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA, USA
| | - Kambiz Nael
- Department of Radiology, University of California, Los Angeles, Los Angeles, CA, USA
| | - Noriko Salamon
- Department of Radiology, University of California, Los Angeles, Los Angeles, CA, USA
| | - Bryan Yoo
- Department of Radiology, University of California, Los Angeles, Los Angeles, CA, USA
| | - William Speier
- Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA, USA
| | - Corey Arnold
- Departments of Bioengineering, Radiology, and Pathology, University of California, Los Angeles, Los Angeles, CA, USA
| |
Collapse
|
41
|
Hokkinen L, Mäkelä T, Savolainen S, Kangasniemi M. Evaluation of a CTA-based convolutional neural network for infarct volume prediction in anterior cerebral circulation ischaemic stroke. Eur Radiol Exp 2021; 5:25. [PMID: 34164743 PMCID: PMC8222495 DOI: 10.1186/s41747-021-00225-1] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2020] [Accepted: 05/20/2021] [Indexed: 02/08/2023] Open
Abstract
BACKGROUND Computed tomography angiography (CTA) imaging is needed in current guideline-based stroke diagnosis, and infarct core size is one factor in guiding treatment decisions. We studied the efficacy of a convolutional neural network (CNN) in final infarct volume prediction from CTA and compared the results to a CT perfusion (CTP)-based commercially available software (RAPID, iSchemaView). METHODS We retrospectively selected 83 consecutive stroke cases treated with thrombolytic therapy or receiving supportive care that presented to Helsinki University Hospital between January 2018 and July 2019. We compared CNN-derived ischaemic lesion volumes to final infarct volumes that were manually segmented from follow-up CT and to CTP-RAPID ischaemic core volumes. RESULTS An overall correlation of r = 0.83 was found between CNN outputs and final infarct volumes. The strongest correlation was found in a subgroup of patients that presented more than 9 h of symptom onset (r = 0.90). A good correlation was found between the CNN outputs and CTP-RAPID ischaemic core volumes (r = 0.89) and the CNN was able to classify patients for thrombolytic therapy or supportive care with a 1.00 sensitivity and 0.94 specificity. CONCLUSIONS A CTA-based CNN software can provide good infarct core volume estimates as observed in follow-up imaging studies. CNN-derived infarct volumes had a good correlation to CTP-RAPID ischaemic core volumes.
Collapse
Affiliation(s)
- Lasse Hokkinen
- HUS Medical Imaging Centre, Radiology, University of Helsinki and Helsinki University Hospital, P.O. Box 340 (Haartmaninkatu 4), FI-00290, Helsinki, Finland.
| | - Teemu Mäkelä
- HUS Medical Imaging Centre, Radiology, University of Helsinki and Helsinki University Hospital, P.O. Box 340 (Haartmaninkatu 4), FI-00290, Helsinki, Finland.,Department of Physics, University of Helsinki, P.O. Box 64, FI-00014, Helsinki, Finland
| | - Sauli Savolainen
- HUS Medical Imaging Centre, Radiology, University of Helsinki and Helsinki University Hospital, P.O. Box 340 (Haartmaninkatu 4), FI-00290, Helsinki, Finland.,Department of Physics, University of Helsinki, P.O. Box 64, FI-00014, Helsinki, Finland
| | - Marko Kangasniemi
- HUS Medical Imaging Centre, Radiology, University of Helsinki and Helsinki University Hospital, P.O. Box 340 (Haartmaninkatu 4), FI-00290, Helsinki, Finland
| |
Collapse
|
42
|
Yeo M, Kok HK, Kutaiba N, Maingard J, Thijs V, Tahayori B, Russell J, Jhamb A, Chandra RV, Brooks M, Barras CD, Asadi H. Artificial intelligence in clinical decision support and outcome prediction - applications in stroke. J Med Imaging Radiat Oncol 2021; 65:518-528. [PMID: 34050596 DOI: 10.1111/1754-9485.13193] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2021] [Accepted: 04/29/2021] [Indexed: 01/19/2023]
Abstract
Artificial intelligence (AI) is making a profound impact in healthcare, with the number of AI applications in medicine increasing substantially over the past five years. In acute stroke, it is playing an increasingly important role in clinical decision-making. Contemporary advances have increased the amount of information - both clinical and radiological - which clinicians must consider when managing patients. In the time-critical setting of acute stroke, AI offers the tools to rapidly evaluate and consolidate available information, extracting specific predictions from rich, noisy data. It has been applied to the automatic detection of stroke lesions on imaging and can guide treatment decisions through the prediction of tissue outcomes and long-term functional outcomes. This review examines the current state of AI applications in stroke, exploring their potential to reform stroke care through clinical decision support, as well as the challenges and limitations which must be addressed to facilitate their acceptance and adoption for clinical use.
Collapse
Affiliation(s)
- Melissa Yeo
- School of Medicine, University of Melbourne, Melbourne, Victoria, Australia
| | - Hong Kuan Kok
- Interventional Radiology Service, Department of Radiology, Northern Health, Melbourne, Victoria, Australia
- School of Medicine, Faculty of Health, Deakin University, Burwood, Victoria, Australia
| | - Numan Kutaiba
- Department of Radiology, Austin Hospital, Melbourne, Victoria, Australia
| | - Julian Maingard
- School of Medicine, Faculty of Health, Deakin University, Burwood, Victoria, Australia
- Interventional Neuroradiology Unit, Monash Health, Clayton, Victoria, Australia
- Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, Victoria, Australia
| | - Vincent Thijs
- Stroke Theme, Florey Institute of Neuroscience and Mental Health, Melbourne, Victoria, Australia
- Department of Neurology, Austin Health, Melbourne, Victoria, Australia
| | - Bahman Tahayori
- Department of Biomedical Engineering, The University of Melbourne, Melbourne, Victoria, Australia
- IBM Research Australia, Melbourne, Victoria, Australia
| | - Jeremy Russell
- Department of Neurosurgery, Austin Hospital, Melbourne, Victoria, Australia
| | - Ashu Jhamb
- Department of Radiology, St Vincent's Hospital, Melbourne, Victoria, Australia
| | - Ronil V Chandra
- Interventional Neuroradiology Unit, Monash Health, Clayton, Victoria, Australia
- Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, Victoria, Australia
| | - Mark Brooks
- School of Medicine, University of Melbourne, Melbourne, Victoria, Australia
- School of Medicine, Faculty of Health, Deakin University, Burwood, Victoria, Australia
- Stroke Theme, Florey Institute of Neuroscience and Mental Health, Melbourne, Victoria, Australia
- Interventional Neuroradiology Service, Department of Radiology, Austin Hospital, Melbourne, Victoria, Australia
| | - Christen D Barras
- South Australian Institute of Health and Medical Research, Adelaide, South Australia, Australia
- School of Medicine, The University of Adelaide, Adelaide, South Australia, Australia
| | - Hamed Asadi
- School of Medicine, Faculty of Health, Deakin University, Burwood, Victoria, Australia
- Interventional Neuroradiology Unit, Monash Health, Clayton, Victoria, Australia
- Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, Victoria, Australia
- Stroke Theme, Florey Institute of Neuroscience and Mental Health, Melbourne, Victoria, Australia
- Department of Radiology, St Vincent's Hospital, Melbourne, Victoria, Australia
- Interventional Neuroradiology Service, Department of Radiology, Austin Hospital, Melbourne, Victoria, Australia
| |
Collapse
|
43
|
Shafaat O, Bernstock JD, Shafaat A, Yedavalli VS, Elsayed G, Gupta S, Sotoudeh E, Sair HI, Yousem DM, Sotoudeh H. Leveraging artificial intelligence in ischemic stroke imaging. J Neuroradiol 2021; 49:343-351. [PMID: 33984377 DOI: 10.1016/j.neurad.2021.05.001] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2021] [Revised: 05/02/2021] [Accepted: 05/03/2021] [Indexed: 11/30/2022]
Abstract
Artificial intelligence (AI) is having a disruptive and transformative effect on clinical medicine. Prompt clinical diagnosis and imaging are critical for minimizing the morbidity and mortality associated with ischemic strokes. Clinicians must understand the current strengths and limitations of AI to provide optimal patient care. Ischemic stroke is one of the medical fields that have been extensively evaluated by artificial intelligence. Presented herein is a review of artificial intelligence applied to clinical management of stroke, geared toward clinicians. In this review, we explain the basic concept of AI and machine learning. This review is without coding and mathematical details and targets the clinicians involved in stroke management without any computer or mathematics' background. Here the AI application in ischemic stroke is summarized and classified into stroke imaging (automated diagnosis of brain infarction, automated ASPECT score calculation, infarction segmentation), prognosis prediction, and patients' selection for treatment.
Collapse
Affiliation(s)
- Omid Shafaat
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 1800 Orleans St, Baltimore, MD 21287, USA.
| | - Joshua D Bernstock
- Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Hale Building, 60 Fenwood Road, Boston, MA 02115, USA.
| | - Amir Shafaat
- Department of Mechanical Engineering, Arak University of Technology, Daneshgah St, 38181-41167 Arak, Iran.
| | - Vivek S Yedavalli
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 1800 Orleans St, Baltimore, MD 21287, USA.
| | - Galal Elsayed
- Department of Neurosurgery, University of Alabama at Birmingham, 1960 6th Ave. S., Birmingham, AL 35233, USA.
| | - Saksham Gupta
- Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Hale Building, 60 Fenwood Road, Boston, MA 02115, USA.
| | - Ehsan Sotoudeh
- Department of Surgery, Iranian Hospital in Dubai, P.O.BOX: 2330, Al-Wasl Road, Dubai 2330, UAE.
| | - Haris I Sair
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 1800 Orleans St, Baltimore, MD 21287, USA; Radiology Artificial Intelligence Lab (RAIL), Malone Center for Engineering in Healthcare, Johns Hopkins University Whiting School of Engineering, 600 North Wolfe Street, Baltimore, MD 21287, USA.
| | - David M Yousem
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 1800 Orleans St, Baltimore, MD 21287, USA.
| | - Houman Sotoudeh
- Department of Radiology, University of Alabama at Birmingham, 619 19th St S, Birmingham, AL 35294, USA.
| |
Collapse
|
44
|
Kappelhof N, Ramos LA, Kappelhof M, van Os HJA, Chalos V, van Kranendonk KR, Kruyt ND, Roos YBWEM, van Zwam WH, van der Schaaf IC, van Walderveen MAA, Wermer MJH, van Oostenbrugge RJ, Lingsma H, Dippel D, Majoie CBLM, Marquering HA. Evolutionary algorithms and decision trees for predicting poor outcome after endovascular treatment for acute ischemic stroke. Comput Biol Med 2021; 133:104414. [PMID: 33962154 DOI: 10.1016/j.compbiomed.2021.104414] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2020] [Revised: 04/09/2021] [Accepted: 04/15/2021] [Indexed: 11/28/2022]
Abstract
Despite the large overall beneficial effects of endovascular treatment in patients with acute ischemic stroke, severe disability or death still occurs in almost one-third of patients. These patients, who might not benefit from treatment, have been previously identified with traditional logistic regression models, which may oversimplify relations between characteristics and outcome, or machine learning techniques, which may be difficult to interpret. We developed and evaluated a novel evolutionary algorithm for fuzzy decision trees to accurately identify patients with poor outcome after endovascular treatment, which was defined as having a modified Rankin Scale score (mRS) higher or equal to 5. The created decision trees have the benefit of being comprehensible, easily interpretable models, making its predictions easy to explain to patients and practitioners. Insights in the reason for the predicted outcome can encourage acceptance and adaptation in practice and help manage expectations after treatment. We compared our proposed method to CART, the benchmark decision tree algorithm, on classification accuracy and interpretability. The fuzzy decision tree significantly outperformed CART: using 5-fold cross-validation with on average 1090 patients in the training set and 273 patients in the test set, the fuzzy decision tree misclassified on average 77 (standard deviation of 7) patients compared to 83 (±7) using CART. The mean number of nodes (decision and leaf nodes) in the fuzzy decision tree was 11 (±2) compared to 26 (±1) for CART decision trees. With an average accuracy of 72% and much fewer nodes than CART, the developed evolutionary algorithm for fuzzy decision trees might be used to gain insights into the predictive value of patient characteristics and can contribute to the development of more accurate medical outcome prediction methods with improved clarity for practitioners and patients.
Collapse
Affiliation(s)
- N Kappelhof
- Department of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands
| | - L A Ramos
- Department of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands; Department of Clinical Epidemiology and Biostatistics, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands.
| | - M Kappelhof
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands
| | - H J A van Os
- Department of Neurology, Leiden University Medical Center, Leiden, the Netherlands
| | - V Chalos
- Department of Neurology, Erasmus MC - University Medical Center, Rotterdam, the Netherlands; Department of Public Health, Erasmus MC - University Medical Center, Rotterdam, the Netherlands; Department of Radiology and Nuclear Medicine, Erasmus MC - University Medical Center, Rotterdam, the Netherlands
| | - K R van Kranendonk
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands
| | - N D Kruyt
- Department of Neurology, Leiden University Medical Center, Leiden, the Netherlands
| | - Y B W E M Roos
- Department of Neurology, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands
| | - W H van Zwam
- Department of Radiology, Cardiovascular Research Institute Maastricht, Maastricht University Medical Center, Maastricht, the Netherlands
| | - I C van der Schaaf
- Department of Radiology, University Medical Centre, Utrecht, the Netherlands
| | - M A A van Walderveen
- Department of Radiology, Leiden University Medical Center, Leiden, the Netherlands
| | - M J H Wermer
- Department of Neurology, Leiden University Medical Center, Leiden, the Netherlands
| | - R J van Oostenbrugge
- Department of Neurology, Maastricht University Medical Center, Maastricht, the Netherlands
| | - Hester Lingsma
- Department of Public Health, Erasmus MC - University Medical Center, Rotterdam, the Netherlands
| | - Diederik Dippel
- Department of Neurology, Erasmus MC - University Medical Center, Rotterdam, the Netherlands
| | - C B L M Majoie
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands
| | - H A Marquering
- Department of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands; Department of Radiology and Nuclear Medicine, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands
| |
Collapse
|
45
|
Velagapudi L, Mouchtouris N, Schmidt RF, Vuong D, Khanna O, Sweid A, Sadler B, Al Saiegh F, Gooch MR, Jabbour P, Rosenwasser RH, Tjoumakaris S. A Machine Learning Approach to First Pass Reperfusion in Mechanical Thrombectomy: Prediction and Feature Analysis. J Stroke Cerebrovasc Dis 2021; 30:105796. [PMID: 33887664 DOI: 10.1016/j.jstrokecerebrovasdis.2021.105796] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2021] [Accepted: 03/28/2021] [Indexed: 01/06/2023] Open
Abstract
INTRODUCTION Novel machine learning (ML) methods are being investigated across medicine for their predictive capabilities while boasting increased adaptability and generalizability. In our study, we compare logistic regression with machine learning for feature importance analysis and prediction in first-pass reperfusion. METHODS We retrospectively identified cases of ischemic stroke treated with mechanical thrombectomy (MT) at our institution from 2012-2018. Significant variables used in predictive modeling were demographic characteristics, medical history, admission NIHSS, and stroke characteristics. Outcome was binarized TICI on first pass (0-2a vs 2b-3). Shapley feature importance plots were used to identify variables that strongly affected outcomes. RESULTS Accuracy for the Random Forest and SVM models were 67.1% compared to 65.8% for the logistic regression model. Brier score was lower for the Random Forest model (0.329 vs 0.342) indicating better predictive capability. Other supervised learning models performed worse than the logistic regression model, with accuracy of 56.2% for Naïve Bayes and 61.6% for XGBoost. Shapley plots for the Random Forest model showed use of aspiration, hyperlipidemia, hypertension, use of stent retriever, and time between symptom onset and catheterization as the top five predictors of first pass reperfusion. CONCLUSION Use of machine learning models, such as Random Forest, for the study of MT outcomes, is more accurate than logistic regression for our dataset, and identifies new factors that contribute to achieving first pass reperfusion. The benefits of machine learning, such as improved predictive capabilities, integration of new data, and generalizability, establish ML as the preferred model for studying outcomes in stroke.
Collapse
Affiliation(s)
- Lohit Velagapudi
- Department of Neurosurgery, Thomas Jefferson University, Philadelphia, PA, USA.
| | | | - Richard F Schmidt
- Department of Neurosurgery, Thomas Jefferson University, Philadelphia, PA, USA.
| | - David Vuong
- Digital Innovation and Consumer Experience (DICE) Group, Thomas Jefferson University, Philadelphia, PA, USA.
| | - Omaditya Khanna
- Department of Neurosurgery, Thomas Jefferson University, Philadelphia, PA, USA.
| | - Ahmad Sweid
- Department of Neurosurgery, Thomas Jefferson University, Philadelphia, PA, USA.
| | - Bryan Sadler
- Digital Innovation and Consumer Experience (DICE) Group, Thomas Jefferson University, Philadelphia, PA, USA.
| | - Fadi Al Saiegh
- Department of Neurosurgery, Thomas Jefferson University, Philadelphia, PA, USA.
| | - M Reid Gooch
- Department of Neurosurgery, Thomas Jefferson University, Philadelphia, PA, USA.
| | - Pascal Jabbour
- Department of Neurosurgery, Thomas Jefferson University, Philadelphia, PA, USA.
| | | | | |
Collapse
|
46
|
Heo TS, Kim YS, Choi JM, Jeong YS, Seo SY, Lee JH, Jeon JP, Kim C. Prediction of Stroke Outcome Using Natural Language Processing-Based Machine Learning of Radiology Report of Brain MRI. J Pers Med 2020; 10:jpm10040286. [PMID: 33339385 PMCID: PMC7766032 DOI: 10.3390/jpm10040286] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2020] [Revised: 12/09/2020] [Accepted: 12/15/2020] [Indexed: 01/28/2023] Open
Abstract
Brain magnetic resonance imaging (MRI) is useful for predicting the outcome of patients with acute ischemic stroke (AIS). Although deep learning (DL) using brain MRI with certain image biomarkers has shown satisfactory results in predicting poor outcomes, no study has assessed the usefulness of natural language processing (NLP)-based machine learning (ML) algorithms using brain MRI free-text reports of AIS patients. Therefore, we aimed to assess whether NLP-based ML algorithms using brain MRI text reports could predict poor outcomes in AIS patients. This study included only English text reports of brain MRIs examined during admission of AIS patients. Poor outcome was defined as a modified Rankin Scale score of 3-6, and the data were captured by trained nurses and physicians. We only included MRI text report of the first MRI scan during the admission. The text dataset was randomly divided into a training and test dataset with a 7:3 ratio. Text was vectorized to word, sentence, and document levels. In the word level approach, which did not consider the sequence of words, and the "bag-of-words" model was used to reflect the number of repetitions of text token. The "sent2vec" method was used in the sensation-level approach considering the sequence of words, and the word embedding was used in the document level approach. In addition to conventional ML algorithms, DL algorithms such as the convolutional neural network (CNN), long short-term memory, and multilayer perceptron were used to predict poor outcomes using 5-fold cross-validation and grid search techniques. The performance of each ML classifier was compared with the area under the receiver operating characteristic (AUROC) curve. Among 1840 subjects with AIS, 645 patients (35.1%) had a poor outcome 3 months after the stroke onset. Random forest was the best classifier (0.782 of AUROC) using a word-level approach. Overall, the document-level approach exhibited better performance than did the word- or sentence-level approaches. Among all the ML classifiers, the multi-CNN algorithm demonstrated the best classification performance (0.805), followed by the CNN (0.799) algorithm. When predicting future clinical outcomes using NLP-based ML of radiology free-text reports of brain MRI, DL algorithms showed superior performance over the other ML algorithms. In particular, the prediction of poor outcomes in document-level NLP DL was improved more by multi-CNN and CNN than by recurrent neural network-based algorithms. NLP-based DL algorithms can be used as an important digital marker for unstructured electronic health record data DL prediction.
Collapse
Affiliation(s)
- Tak Sung Heo
- Department of Convergence Software, Hallym University, Chuncheon 24252, Korea; (T.S.H.); (Y.S.K.); (J.M.C.); (Y.S.J.); (S.Y.S.)
| | - Yu Seop Kim
- Department of Convergence Software, Hallym University, Chuncheon 24252, Korea; (T.S.H.); (Y.S.K.); (J.M.C.); (Y.S.J.); (S.Y.S.)
| | - Jeong Myeong Choi
- Department of Convergence Software, Hallym University, Chuncheon 24252, Korea; (T.S.H.); (Y.S.K.); (J.M.C.); (Y.S.J.); (S.Y.S.)
| | - Yeong Seok Jeong
- Department of Convergence Software, Hallym University, Chuncheon 24252, Korea; (T.S.H.); (Y.S.K.); (J.M.C.); (Y.S.J.); (S.Y.S.)
| | - Soo Young Seo
- Department of Convergence Software, Hallym University, Chuncheon 24252, Korea; (T.S.H.); (Y.S.K.); (J.M.C.); (Y.S.J.); (S.Y.S.)
| | - Jun Ho Lee
- Department of Otorhinolaryngology and Head and Neck Surgery, Chuncheon Sacred Heart Hospital, Chuncheon 24253, Korea;
| | - Jin Pyeong Jeon
- Department of Neurosurgery, Chuncheon Sacred Heart Hospital, Chuncheon 24253, Korea;
| | - Chulho Kim
- Department of Neurology, Chuncheon Sacred Heart Hospital, Chuncheon 24253, Korea
- Correspondence: ; Tel.: +82-332-405-255; Fax: +82-332-5562-44
| |
Collapse
|
47
|
Burgos N, Bottani S, Faouzi J, Thibeau-Sutre E, Colliot O. Deep learning for brain disorders: from data processing to disease treatment. Brief Bioinform 2020; 22:1560-1576. [PMID: 33316030 DOI: 10.1093/bib/bbaa310] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2020] [Revised: 10/09/2020] [Accepted: 10/13/2020] [Indexed: 12/19/2022] Open
Abstract
In order to reach precision medicine and improve patients' quality of life, machine learning is increasingly used in medicine. Brain disorders are often complex and heterogeneous, and several modalities such as demographic, clinical, imaging, genetics and environmental data have been studied to improve their understanding. Deep learning, a subpart of machine learning, provides complex algorithms that can learn from such various data. It has become state of the art in numerous fields, including computer vision and natural language processing, and is also growingly applied in medicine. In this article, we review the use of deep learning for brain disorders. More specifically, we identify the main applications, the concerned disorders and the types of architectures and data used. Finally, we provide guidelines to bridge the gap between research studies and clinical routine.
Collapse
|
48
|
Karthik R, Menaka R, Johnson A, Anand S. Neuroimaging and deep learning for brain stroke detection - A review of recent advancements and future prospects. Comput Methods Programs Biomed 2020; 197:105728. [PMID: 32882591 DOI: 10.1016/j.cmpb.2020.105728] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/19/2020] [Accepted: 08/23/2020] [Indexed: 05/24/2023]
Abstract
BACKGROUND AND OBJECTIVE In recent years, deep learning algorithms have created a massive impact on addressing research challenges in different domains. The medical field also greatly benefits from the use of improving deep learning models which save time and produce accurate results. This research aims to emphasize the impact of deep learning models in brain stroke detection and lesion segmentation. This is achieved by discussing the state of the art approaches proposed by the recent works in this field. METHODS In this study, the advancements in stroke lesion detection and segmentation were focused. The survey analyses 113 research papers published in different academic research databases. The research articles have been filtered out based on specific criteria to obtain the most prominent insights related to stroke lesion detection and segmentation. RESULTS The features of the stroke lesion vary based on the type of imaging modality. To develop an effective method for stroke lesion detection, the features need to be carefully extracted from the input images. This review takes an attempt to categorize and discuss the different deep architectures employed for stroke lesion detection and segmentation, based on the underlying imaging modality. This further assists in understanding the relevance of the two-deep neural network components in medical image analysis namely Convolutional Neural Network (CNN) and Fully Convolutional Network (FCN). It hints at other possible deep architectures that can be proposed for better results towards stroke lesion detection. Also, the emerging trends and breakthroughs in stroke detection have been detailed in this evaluation. CONCLUSION This work concludes by examining the technical and non-technical challenges faced by researchers and indicate the future implications in stroke detection. It could support the bio-medical researchers to propose better solutions for stroke lesion detection.
Collapse
Affiliation(s)
- R Karthik
- Center for Cyber Physical Systems, Vellore Institute of Technology, Chennai, India.
| | - R Menaka
- Center for Cyber Physical Systems, Vellore Institute of Technology, Chennai, India.
| | - Annie Johnson
- School of Electronics Engineering, Vellore Institute of Technology, Chennai, India
| | - Sundar Anand
- School of Electronics Engineering, Vellore Institute of Technology, Chennai, India
| |
Collapse
|
49
|
Ramos LA, Kappelhof M, van Os HJA, Chalos V, Van Kranendonk K, Kruyt ND, Roos YBWEM, van der Lugt A, van Zwam WH, van der Schaaf IC, Zwinderman AH, Strijkers GJ, van Walderveen MAA, Wermer MJH, Olabarriaga SD, Majoie CBLM, Marquering HA. Predicting Poor Outcome Before Endovascular Treatment in Patients With Acute Ischemic Stroke. Front Neurol 2020; 11:580957. [PMID: 33178123 PMCID: PMC7593486 DOI: 10.3389/fneur.2020.580957] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2020] [Accepted: 09/07/2020] [Indexed: 12/31/2022] Open
Abstract
Background: Although endovascular treatment (EVT) has greatly improved outcomes in acute ischemic stroke, still one third of patients die or remain severely disabled after stroke. If we could select patients with poor clinical outcome despite EVT, we could prevent futile treatment, avoid treatment complications, and further improve stroke care. We aimed to determine the accuracy of poor functional outcome prediction, defined as 90-day modified Rankin Scale (mRS) score ≥5, despite EVT treatment. Methods: We included 1,526 patients from the MR CLEAN Registry, a prospective, observational, multicenter registry of ischemic stroke patients treated with EVT. We developed machine learning prediction models using all variables available at baseline before treatment. We optimized the models for both maximizing the area under the curve (AUC), reducing the number of false positives. Results: From 1,526 patients included, 480 (31%) of patients showed poor outcome. The highest AUC was 0.81 for random forest. The highest area under the precision recall curve was 0.69 for the support vector machine. The highest achieved specificity was 95% with a sensitivity of 34% for neural networks, indicating that all models contained false positives in their predictions. From 921 mRS 0–4 patients, 27–61 (3–6%) were incorrectly classified as poor outcome. From 480 poor outcome patients in the registry, 99–163 (21–34%) were correctly identified by the models. Conclusions: All prediction models showed a high AUC. The best-performing models correctly identified 34% of the poor outcome patients at a cost of misclassifying 4% of non-poor outcome patients. Further studies are necessary to determine whether these accuracies are reproducible before implementation in clinical practice.
Collapse
Affiliation(s)
- Lucas A Ramos
- Department of Biomedical Engineering and Physics, University of Amsterdam, Amsterdam, Netherlands.,Department of Clinical Epidemiology and Biostatistics, University of Amsterdam, Amsterdam, Netherlands
| | - Manon Kappelhof
- Department of Radiology and Nuclear Medicine, University of Amsterdam, Amsterdam, Netherlands
| | | | - Vicky Chalos
- Department of Neurology, Erasmus MC - University Medical Center, Rotterdam, Netherlands.,Department of Public Health, Erasmus MC - University Medical Center, Rotterdam, Netherlands.,Department of Radiology and Nuclear Medicine, Erasmus MC - University Medical Center, Rotterdam, Netherlands
| | - Katinka Van Kranendonk
- Department of Radiology and Nuclear Medicine, University of Amsterdam, Amsterdam, Netherlands
| | - Nyika D Kruyt
- Department of Neurology, Leiden University Medical Center, Leiden, Netherlands
| | - Yvo B W E M Roos
- Department of Neurology, Amsterdam UMC, University of Amsterdam, Amsterdam, Netherlands
| | - Aad van der Lugt
- Department of Radiology and Nuclear Medicine, Erasmus MC - University Medical Center, Rotterdam, Netherlands
| | - Wim H van Zwam
- Department of Radiology, Cardiovascular Research Institute Maastricht, Maastricht University Medical Center, Maastricht, Netherlands
| | | | - Aeilko H Zwinderman
- Department of Clinical Epidemiology and Biostatistics, University of Amsterdam, Amsterdam, Netherlands
| | - Gustav J Strijkers
- Department of Biomedical Engineering and Physics, University of Amsterdam, Amsterdam, Netherlands.,Department of Radiology and Nuclear Medicine, University of Amsterdam, Amsterdam, Netherlands
| | | | - Mariekke J H Wermer
- Department of Neurology, Leiden University Medical Center, Leiden, Netherlands
| | - Silvia D Olabarriaga
- Department of Clinical Epidemiology and Biostatistics, University of Amsterdam, Amsterdam, Netherlands
| | - Charles B L M Majoie
- Department of Radiology and Nuclear Medicine, University of Amsterdam, Amsterdam, Netherlands
| | - Henk A Marquering
- Department of Biomedical Engineering and Physics, University of Amsterdam, Amsterdam, Netherlands.,Department of Radiology and Nuclear Medicine, University of Amsterdam, Amsterdam, Netherlands
| |
Collapse
|
50
|
Segato A, Marzullo A, Calimeri F, De Momi E. Artificial intelligence for brain diseases: A systematic review. APL Bioeng 2020; 4:041503. [PMID: 33094213 PMCID: PMC7556883 DOI: 10.1063/5.0011697] [Citation(s) in RCA: 43] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2020] [Accepted: 09/09/2020] [Indexed: 12/15/2022] Open
Abstract
Artificial intelligence (AI) is a major branch of computer science that is fruitfully used for analyzing complex medical data and extracting meaningful relationships in datasets, for several clinical aims. Specifically, in the brain care domain, several innovative approaches have achieved remarkable results and open new perspectives in terms of diagnosis, planning, and outcome prediction. In this work, we present an overview of different artificial intelligent techniques used in the brain care domain, along with a review of important clinical applications. A systematic and careful literature search in major databases such as Pubmed, Scopus, and Web of Science was carried out using "artificial intelligence" and "brain" as main keywords. Further references were integrated by cross-referencing from key articles. 155 studies out of 2696 were identified, which actually made use of AI algorithms for different purposes (diagnosis, surgical treatment, intra-operative assistance, and postoperative assessment). Artificial neural networks have risen to prominent positions among the most widely used analytical tools. Classic machine learning approaches such as support vector machine and random forest are still widely used. Task-specific algorithms are designed for solving specific problems. Brain images are one of the most used data types. AI has the possibility to improve clinicians' decision-making ability in neuroscience applications. However, major issues still need to be addressed for a better practical use of AI in the brain. To this aim, it is important to both gather comprehensive data and build explainable AI algorithms.
Collapse
Affiliation(s)
- Alice Segato
- Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan 20133, Italy
| | - Aldo Marzullo
- Department of Mathematics and Computer Science, University of Calabria, Rende 87036, Italy
| | - Francesco Calimeri
- Department of Mathematics and Computer Science, University of Calabria, Rende 87036, Italy
| | - Elena De Momi
- Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan 20133, Italy
| |
Collapse
|