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

Bas H M van der Velden; Hugo J Kuijf; Kenneth G A Gilhuijs; Max A Viergever

doi:10.1016/j.media.2022.102470

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

Bas H M van der Velden, Hugo J Kuijf, Kenneth G A Gilhuijs, Max A Viergever

Research output: Contribution to journal › Review article › peer-review

12 Downloads (Pure)

Abstract

With an increase in deep learning-based methods, the call for explainability of such methods grows, especially 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 methods. 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.

Original language	English
Article number	102470
Pages (from-to)	1-21
Journal	Medical Image Analysis
Volume	79
DOIs	https://doi.org/10.1016/j.media.2022.102470
Publication status	Published - Jul 2022

Keywords

Artificial Intelligence
Deep Learning
Humans
Deep learning
Survey
Medical image analysis
Explainable artificial intelligence
Interpretable deep learning

Access to Document

10.1016/j.media.2022.102470Licence: CC BY

1-s2.0-S1361841522001177-mainFinal published version, 1.79 MBLicence: CC BY

Cite this

@article{0afb00e3eb87462595c2c6bd2d2f7ede,

title = "Explainable artificial intelligence (XAI) in deep learning-based medical image analysis",

abstract = "With an increase in deep learning-based methods, the call for explainability of such methods grows, especially 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 methods. 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.",

keywords = "Artificial Intelligence, Deep Learning, Humans, Deep learning, Survey, Medical image analysis, Explainable artificial intelligence, Interpretable deep learning",

author = "{van der Velden}, {Bas H M} and Kuijf, {Hugo J} and Gilhuijs, {Kenneth G A} and Viergever, {Max A}",

note = "Funding Information: This work was partially funded by the Dutch Cancer Society (KWF) Grant No.: 10755. We have no conflicts of interest. Publisher Copyright: {\textcopyright} 2022 The Authors",

year = "2022",

month = jul,

doi = "10.1016/j.media.2022.102470",

language = "English",

volume = "79",

pages = "1--21",

journal = "Medical Image Analysis",

issn = "1361-8415",

publisher = "Elsevier",

}

TY - JOUR

T1 - Explainable artificial intelligence (XAI) in deep learning-based medical image analysis

AU - van der Velden, Bas H M

AU - Kuijf, Hugo J

AU - Gilhuijs, Kenneth G A

AU - Viergever, Max A

PY - 2022/7

Y1 - 2022/7

N2 - With an increase in deep learning-based methods, the call for explainability of such methods grows, especially 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 methods. 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.

AB - With an increase in deep learning-based methods, the call for explainability of such methods grows, especially 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 methods. 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.

KW - Artificial Intelligence

KW - Deep Learning

KW - Humans

KW - Deep learning

KW - Survey

KW - Medical image analysis

KW - Explainable artificial intelligence

KW - Interpretable deep learning

UR - http://www.scopus.com/inward/record.url?scp=85130346900&partnerID=8YFLogxK

U2 - 10.1016/j.media.2022.102470

DO - 10.1016/j.media.2022.102470

M3 - Review article

C2 - 35576821

SN - 1361-8415

VL - 79

SP - 1

EP - 21

JO - Medical Image Analysis

JF - Medical Image Analysis

M1 - 102470

ER -

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

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this