Explainable artificial intelligence (XAI) in deep learning-based medical image analysis

被引:575
作者
Van der Velden, Bas H. M. [1 ]
Kuijf, Hugo J. [1 ]
Gilhuijs, Kenneth G. A. [1 ]
Viergever, Max A. [1 ]
机构
[1] Univ Med Ctr Utrecht, Image Sci Inst, Q02 4-45,POB 85500,, NL-3508 GA Utrecht, Netherlands
关键词
Explainable artificial intelligence; Interpretable deep learning; Medical image analysis; Deep learning; Survey; CONVOLUTIONAL NEURAL-NETWORK; BLACK-BOX; CLASSIFICATION; CANCER; LOCALIZATION; SEGMENTATION; INFORMATION; PREDICTION; DIAGNOSIS; DISEASES;
D O I
10.1016/j.media.2022.102470
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
With an increase in deep learning-based methods, the call for explainability of such methods grows, es-pecially in high-stakes decision making areas such as medical image analysis. This survey presents an overview of explainable artificial intelligence (XAI) used in deep learning-based medical image analysis. A framework of XAI criteria is introduced to classify deep learning-based medical image analysis meth-ods. Papers on XAI techniques in medical image analysis are then surveyed and categorized according to the framework and according to anatomical location. The paper concludes with an outlook of future opportunities for XAI in medical image analysis. (c) 2022 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )
引用
收藏
页数:21
相关论文
共 289 条
[1]  
Abbasi-Asl R., 2017, ARXIV PREPRINT ARXIV
[2]   SLIC Superpixels Compared to State-of-the-Art Superpixel Methods [J].
Achanta, Radhakrishna ;
Shaji, Appu ;
Smith, Kevin ;
Lucchi, Aurelien ;
Fua, Pascal ;
Suesstrunk, Sabine .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (11) :2274-2281
[3]   Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) [J].
Adadi, Amina ;
Berrada, Mohammed .
IEEE ACCESS, 2018, 6 :52138-52160
[4]  
Adebayo J, 2018, ADV NEUR IN, V31
[5]  
Ahmad A, 2019, I S BIOMED IMAGING, P372, DOI [10.1109/isbi.2019.8759313, 10.1109/ISBI.2019.8759313]
[6]  
Ahmad M, 2019, I S BIOMED IMAGING, P573, DOI [10.1109/ISBI.2019.8759417, 10.1109/isbi.2019.8759417]
[7]   Predicting Breast Cancer by Applying Deep Learning to Linked Health Records and Mammograms [J].
Akselrod-Ballin, Ayelet ;
Chorev, Michal ;
Shoshan, Yoel ;
Spiro, Adam ;
Hazan, Alon ;
Melamed, Roie ;
Barkan, Ella ;
Herzel, Esma ;
Naor, Shaked ;
Karavani, Ehud ;
Koren, Gideon ;
Goldscbmidt, Yaara ;
Shalev, Varda ;
Rosen-Zvi, Michal ;
Guindy, Michal .
RADIOLOGY, 2019, 292 (02) :331-342
[8]   Automatic Caption Generation for Medical Images [J].
Allaouzi, Imane ;
Ben Ahmed, M. ;
Benamrou, B. ;
Ouardouz, M. .
PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON SMART CITY APPLICATIONS (SCA'18), 2018,
[9]  
[Anonymous], 2018, PROC INT C LEARN REP
[10]  
[Anonymous], 2014, COMPUT RES REPOSITOR