Interpretability of Machine Learning Methods Applied to Neuroimaging
Sorbonne Université（索邦大学）；Institut du Cerveau - Paris Brain Institute - ICM（巴黎大脑研究所（ICM））；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；Inserm（法国国家健康与医学研究院）；AP-HP（巴黎公共援助医院集团）；Hôpital de la Pitié-Salpêtrière（皮蒂耶-萨尔佩特里埃医院）
Elina Thibeau-Sutre, Sasha Collin, Ninon Burgos, Olivier Colliot
Deep learning methods have become very popular for the processing of natural images, and were then successfully adapted to the neuroimaging field. As these methods are non-transparent, interpretability methods are needed to validate them and ensure their reliability. Indeed, it has been shown that deep learning models may obtain high performance even when using irrelevant features, by exploiting biases in the training set. Such undesirable situations can potentially be detected by using interpretability methods. Recently, many methods have been proposed to interpret neural networks. However, this domain is not mature yet. Machine learning users face two major issues when aiming to interpret their models: which method to choose, and how to assess its reliability? Here, we aim at providing answers to these questions by presenting the most common interpretability methods and metrics developed to assess their reliability, as well as their applications and benchmarks in the neuroimaging context. Note that this is not an exhaustive survey: we aimed to focus on the studies which we found to be the most representative and relevant.
Looking deeper into interpretable deep learning in neuroimaging: a comprehensive survey
Georgia State University（佐治亚州立大学）；Georgia Institute of Technology（佐治亚理工学院）；Emory University（埃默里大学）；Tri-institutional Center for Translational Research in Neuroimaging and Data Science（三机构神经影像与数据科学转化研究中心）
A Reproducible Framework for Bias-Resistant Machine Learning on Small-Sample Neuroimaging Data
Department of Electrical and Computer Engineering, University of Houston（电子与计算机工程系，休斯顿大学）；Department of Information Science Technology, University of Houston（信息科学与技术系，休斯顿大学）；Department of Neurology, College of Medicine, University of Florida（神经病学系，医学院，佛罗里达大学）
Feature visualization for convolutional neural network models trained on neuroimaging data
Charité – Universitätsmedizin Berlin（柏林夏里特医学院）；Freie Universität Berlin（柏林自由大学）；Humboldt-Universität zu Berlin（柏林洪堡大学）；Berlin Institute of Health（柏林健康研究所）；Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）
Analyzing Neuroimaging Data Through Recurrent Deep Learning Models
Technische Universität Berlin（柏林工业大学）；Freie Universität Berlin（柏林自由大学）；Korea University（高丽大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）
Decomposing 3D Neuroimaging into 2+1D Processing for Schizophrenia Recognition
Nanyang Technological University（南洋理工大学）；NTU Institute for Health Technologies（南洋理工大学健康技术研究所）；National University of Singapore（新加坡国立大学）；Yong Loo Lin School of Medicine（杨潞龄医学院）；Institute of Mental Health (IMH)（心理健康研究所（IMH））
A sensitivity analysis to quantify the impact of neuroimaging preprocessing strategies on subsequent statistical analyses
Neurobiology Research Unit, Rigshospitalet（神经生物学研究单位，哥本哈根大学医院）；Section of Biostatistics, University of Copenhagen（生物统计学系，哥本哈根大学）；Molecular Imaging Branch, National Institute of Mental Health (NIMH)（分子成像分支，国家心理健康研究所）；Department of Computer Science, University of Copenhagen（计算机科学系，哥本哈根大学）
Autism Spectrum Disorder Classification with Interpretability in Children based on Structural MRI Features Extracted using Contrastive Variational Autoencoder
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Shenzhen Key Laboratory of Intelligent Bioinformatics（深圳市智能生物信息学重点实验室）；Center for High Performance Computing, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院高性能计算中心）
