1
|
Compte R, Granville Smith I, Isaac A, Danckert N, McSweeney T, Liantis P, Williams FMK. Are current machine learning applications comparable to radiologist classification of degenerate and herniated discs and Modic change? A systematic review and meta-analysis. EUROPEAN SPINE JOURNAL : OFFICIAL PUBLICATION OF THE EUROPEAN SPINE SOCIETY, THE EUROPEAN SPINAL DEFORMITY SOCIETY, AND THE EUROPEAN SECTION OF THE CERVICAL SPINE RESEARCH SOCIETY 2023; 32:3764-3787. [PMID: 37150769 PMCID: PMC10164619 DOI: 10.1007/s00586-023-07718-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/28/2022] [Revised: 02/08/2023] [Accepted: 04/09/2023] [Indexed: 05/09/2023]
Abstract
INTRODUCTION Low back pain is the leading contributor to disability burden globally. It is commonly due to degeneration of the lumbar intervertebral discs (LDD). Magnetic resonance imaging (MRI) is the current best tool to visualize and diagnose LDD, but places high time demands on clinical radiologists. Automated reading of spine MRIs could improve speed, accuracy, reliability and cost effectiveness in radiology departments. The aim of this review and meta-analysis was to determine if current machine learning algorithms perform well identifying disc degeneration, herniation, bulge and Modic change compared to radiologists. METHODS A PRISMA systematic review protocol was developed and four electronic databases and reference lists were searched. Strict inclusion and exclusion criteria were defined. A PROBAST risk of bias and applicability analysis was performed. RESULTS 1350 articles were extracted. Duplicates were removed and title and abstract searching identified original research articles that used machine learning (ML) algorithms to identify disc degeneration, herniation, bulge and Modic change from MRIs. 27 studies were included in the review; 25 and 14 studies were included multi-variate and bivariate meta-analysis, respectively. Studies used machine learning algorithms to assess LDD, disc herniation, bulge and Modic change. Models using deep learning, support vector machine, k-nearest neighbors, random forest and naïve Bayes algorithms were included. Meta-analyses found no differences in algorithm or classification performance. When algorithms were tested in replication or external validation studies, they did not perform as well as when assessed in developmental studies. Data augmentation improved algorithm performance when compared to models used with smaller datasets, there were no performance differences between augmented data and large datasets. DISCUSSION This review highlights several shortcomings of current approaches, including few validation attempts or use of large sample sizes. To the best of the authors' knowledge, this is the first systematic review to explore this topic. We suggest the utilization of deep learning coupled with semi- or unsupervised learning approaches. Use of all information contained in MRI data will improve accuracy. Clear and complete reporting of study design, statistics and results will improve the reliability and quality of published literature.
Collapse
Affiliation(s)
- Roger Compte
- Department of Twin Research, King's College London, St Thomas' Hospital Campus, 4th Floor South Wing, Block D, Westminster Bridge Road, London, SE1 7EH, UK.
| | - Isabelle Granville Smith
- Department of Twin Research, King's College London, St Thomas' Hospital Campus, 4th Floor South Wing, Block D, Westminster Bridge Road, London, SE1 7EH, UK.
| | - Amanda Isaac
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Nathan Danckert
- Department of Twin Research, King's College London, St Thomas' Hospital Campus, 4th Floor South Wing, Block D, Westminster Bridge Road, London, SE1 7EH, UK
| | - Terence McSweeney
- Research Unit of Health Sciences and Technology, University of Oulu, Oulu, Finland
| | - Panagiotis Liantis
- Guy's and St Thomas' National Health Services Foundation Trust, London, UK
| | - Frances M K Williams
- Department of Twin Research, King's College London, St Thomas' Hospital Campus, 4th Floor South Wing, Block D, Westminster Bridge Road, London, SE1 7EH, UK
| |
Collapse
|
2
|
Hu Y, Huang ZA, Liu R, Xue X, Sun X, Song L, Tan KC. Source Free Semi-Supervised Transfer Learning for Diagnosis of Mental Disorders on fMRI Scans. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023; 45:13778-13795. [PMID: 37486851 DOI: 10.1109/tpami.2023.3298332] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/26/2023]
Abstract
The high prevalence of mental disorders gradually poses a huge pressure on the public healthcare services. Deep learning-based computer-aided diagnosis (CAD) has emerged to relieve the tension in healthcare institutions by detecting abnormal neuroimaging-derived phenotypes. However, training deep learning models relies on sufficient annotated datasets, which can be costly and laborious. Semi-supervised learning (SSL) and transfer learning (TL) can mitigate this challenge by leveraging unlabeled data within the same institution and advantageous information from source domain, respectively. This work is the first attempt to propose an effective semi-supervised transfer learning (SSTL) framework dubbed S3TL for CAD of mental disorders on fMRI data. Within S3TL, a secure cross-domain feature alignment method is developed to generate target-related source model in SSL. Subsequently, we propose an enhanced dual-stage pseudo-labeling approach to assign pseudo-labels for unlabeled samples in target domain. Finally, an advantageous knowledge transfer method is conducted to improve the generalization capability of the target model. Comprehensive experimental results demonstrate that S3TL achieves competitive accuracies of 69.14%, 69.65%, and 72.62% on ABIDE-I, ABIDE-II, and ADHD-200 datasets, respectively. Furthermore, the simulation experiments also demonstrate the application potential of S3TL through model interpretation analysis and federated learning extension.
Collapse
|
3
|
Chen X, Li B, Jia H, Feng F, Duan F, Sun Z, Caiafa CF, Solé-Casals J. Graph Empirical Mode Decomposition-Based Data Augmentation Applied to Gifted Children MRI Analysis. Front Neurosci 2022; 16:866735. [PMID: 35864986 PMCID: PMC9295389 DOI: 10.3389/fnins.2022.866735] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2022] [Accepted: 05/27/2022] [Indexed: 12/05/2022] Open
Abstract
Gifted children and normal controls can be distinguished by analyzing the structural connectivity (SC) extracted from MRI data. Previous studies have improved classification accuracy by extracting several features of the brain regions. However, the limited size of the database may lead to degradation when training deep neural networks as classification models. To this end, we propose to use a data augmentation method by adding artificial samples generated using graph empirical mode decomposition (GEMD). We decompose the training samples by GEMD to obtain the intrinsic mode functions (IMFs). Then, the IMFs are randomly recombined to generate the new artificial samples. After that, we use the original training samples and the new artificial samples to enlarge the training set. To evaluate the proposed method, we use a deep neural network architecture called BrainNetCNN to classify the SCs of MRI data with and without data augmentation. The results show that the data augmentation with GEMD can improve the average classification performance from 55.7 to 78%, while we get a state-of-the-art classification accuracy of 93.3% by using GEMD in some cases. Our results demonstrate that the proposed GEMD augmentation method can effectively increase the limited number of samples in the gifted children dataset, improving the classification accuracy. We also found that the classification accuracy is improved when specific features extracted from brain regions are used, achieving 93.1% for some feature selection methods.
Collapse
Affiliation(s)
- Xuning Chen
- Department of Artificial Intelligence, Nankai University, Tianjin, China
| | - Binghua Li
- Department of Artificial Intelligence, Nankai University, Tianjin, China
| | - Hao Jia
- Department of Artificial Intelligence, Nankai University, Tianjin, China
| | - Fan Feng
- Department of Artificial Intelligence, Nankai University, Tianjin, China
| | - Feng Duan
- Department of Artificial Intelligence, Nankai University, Tianjin, China
- *Correspondence: Feng Duan
| | - Zhe Sun
- Computational Engineering Applications Unit, Head Office for Information Systems and Cybersecurity, RIKEN, Saitama, Japan
- Zhe Sun
| | - Cesar F. Caiafa
- Department of Artificial Intelligence, Nankai University, Tianjin, China
- Instituto Argentino de Radioastronomía, Consejo Nacional de Investigaciones Científicas y Técnicas – Centro Científico Tecnológico La Plata/Comisión de Investigaciones Científicas – Provincia de Buenos Aires/Universidad Nacional de La Plata, Villa Elisa, Argentina
| | - Jordi Solé-Casals
- Department of Artificial Intelligence, Nankai University, Tianjin, China
- Department of Psychiatry, University of Cambridge, Cambridge, United Kingdom
- Data and Signal Processing Research Group, University of Vic-Central University of Catalonia, Vic, Spain
- Jordi Solé-Casals
| |
Collapse
|
4
|
Faragallah OS, El-Hoseny H, El-Shafai W, El-Rahman WA, El-Sayed HS, El-Rabaie ESM, El-Samie FEA, Geweid GGN. A Comprehensive Survey Analysis for Present Solutions of Medical Image Fusion and Future Directions. IEEE ACCESS 2021; 9:11358-11371. [DOI: 10.1109/access.2020.3048315] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/01/2023]
Affiliation(s)
- Osama S. Faragallah
- Department of Information Technology, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia
| | - Heba El-Hoseny
- Department of Electronics and Electrical Communication Engineering, Al-Obour High Institute for Engineering and Technology, Al-Obour, Egypt
| | - Walid El-Shafai
- Department of Electronics and Communication Engineering, Faculty of Electronic Engineering, Menofia University, Menouf, Egypt
| | - Wael Abd El-Rahman
- Department of Electrical Engineering, Faculty of Engineering, Benha University, Benha, Egypt
| | - Hala S. El-Sayed
- Department of Electrical Engineering, Faculty of Engineering, Menoufia University, Shebeen El-Kom, Egypt
| | - El-Sayed M. El-Rabaie
- Department of Electronics and Communication Engineering, Faculty of Electronic Engineering, Menofia University, Menouf, Egypt
| | - Fathi E. Abd El-Samie
- Department of Electronics and Communication Engineering, Faculty of Electronic Engineering, Menofia University, Menouf, Egypt
| | - Gamal G. N. Geweid
- Department of Electrical Engineering, Faculty of Engineering, Benha University, Benha, Egypt
| |
Collapse
|
5
|
Koppe G, Meyer-Lindenberg A, Durstewitz D. Deep learning for small and big data in psychiatry. Neuropsychopharmacology 2021; 46:176-190. [PMID: 32668442 PMCID: PMC7689428 DOI: 10.1038/s41386-020-0767-z] [Citation(s) in RCA: 60] [Impact Index Per Article: 20.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/01/2020] [Revised: 07/04/2020] [Accepted: 07/06/2020] [Indexed: 02/06/2023]
Abstract
Psychiatry today must gain a better understanding of the common and distinct pathophysiological mechanisms underlying psychiatric disorders in order to deliver more effective, person-tailored treatments. To this end, it appears that the analysis of 'small' experimental samples using conventional statistical approaches has largely failed to capture the heterogeneity underlying psychiatric phenotypes. Modern algorithms and approaches from machine learning, particularly deep learning, provide new hope to address these issues given their outstanding prediction performance in other disciplines. The strength of deep learning algorithms is that they can implement very complicated, and in principle arbitrary predictor-response mappings efficiently. This power comes at a cost, the need for large training (and test) samples to infer the (sometimes over millions of) model parameters. This appears to be at odds with the as yet rather 'small' samples available in psychiatric human research to date (n < 10,000), and the ambition of predicting treatment at the single subject level (n = 1). Here, we aim at giving a comprehensive overview on how we can yet use such models for prediction in psychiatry. We review how machine learning approaches compare to more traditional statistical hypothesis-driven approaches, how their complexity relates to the need of large sample sizes, and what we can do to optimally use these powerful techniques in psychiatric neuroscience.
Collapse
Affiliation(s)
- Georgia Koppe
- Department of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Square J5, 68159, Mannheim, Germany.
- Department of Psychiatry and Psychotherapy, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Square J5, 68159, Mannheim, Germany.
| | - Andreas Meyer-Lindenberg
- Department of Psychiatry and Psychotherapy, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Square J5, 68159, Mannheim, Germany.
| | - Daniel Durstewitz
- Department of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Square J5, 68159, Mannheim, Germany.
| |
Collapse
|