Interpretable artificial intelligence in radiology and radiation oncology

被引：5

作者：

Cui, Sunan ^{[1
]}

Traverso, Alberto ^{[2
]}

Niraula, Dipesh ^{[3
]}

Zou, Jiaren ^{[4
]}

Luo, Yi ^{[3
]}

Owen, Dawn ^{[5
]}

El Naqa, Issam ^{[3
]}

Wei, Lise ^{[4
]}

机构：

[1] Univ Washington, Dept Radiat Oncol, Seattle, WA USA

[2] Dept Radiotherapy, Maastro Clin, Maastricht, Netherlands

[3] H Lee Moffitt Canc Ctr & Res Inst, Dept Machine Learning, Tampa, FL USA

[4] Univ Michigan, Dept Radiat Oncol, Ann Arbor, MI 48109 USA

[5] Mayo Clin, Dept Radiat Oncol, Rochester, MN USA

来源：

BRITISH JOURNAL OF RADIOLOGY | 2023年 / 96卷 / 1150期

关键词：

PREDICTION; CARE;

D O I：

10.1259/bjr.20230142

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

Artificial intelligence has been introduced to clinical practice, especially radiology and radiation oncology, from image segmentation, diagnosis, treatment planning and prognosis. It is not only crucial to have an accurate artificial intelligence model, but also to understand the internal logic and gain the trust of the experts. This review is intended to provide some insights into core concepts of the interpretability, the state- of- the- art methods for understanding the machine learning models, the evaluation of these methods, identifying some challenges and limits of them, and gives some examples of medical applications.

引用

页数：10

共 85 条

[1] Data-driven identification of prognostic tumor subpopulations using spatially mapped t-SNE of mass spectrometry imaging data
Abdelmoula, Walid M.
Balluff, Benjamin
Englert, Sonja
Dijkstra, Jouke
Reinders, Marcel J. T.
Walch, Axel
McDonnell, Liam A.
Lelieveldt, Boudewijn P. F.
[J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2016, 113 (43) : 12244 - 12249
[2] Explainability for artificial intelligence in healthcare: a multidisciplinary perspective
Amann, Julia
Blasimme, Alessandro
Vayena, Effy
Frey, Dietmar
Madai, Vince I.
[J]. BMC MEDICAL INFORMATICS AND DECISION MAKING, 2020, 20 (01)
[3] Ancona M., 2019, EXPLAINABLE INTERPRE, P169, DOI [DOI 10.1007/978-3-030-28954-6_9, 10.1007/978-3-030-28954-6_9, DOI 10.1007/978-3-030, DOI 10.1007/978-3-030-28954]
[4] On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, Sebastian
Binder, Alexander
Montavon, Gregoire
Klauschen, Frederick
Mueller, Klaus-Robert
Samek, Wojciech
[J]. PLOS ONE, 2015, 10 (07):
[5] Balasubramanian M, 2002, SCIENCE, V295
[6] Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency
Barragan-Montero, Ana
Bibal, Adrien
Dastarac, Margerie Huet
Draguet, Camille
Valdes, Gilmer
Nguyen, Dan
Willems, Siri
Vandewinckele, Liesbeth
Holmstrom, Mats
Lofman, Fredrik
Souris, Kevin
Sterpin, Edmond
Lee, John A.
[J]. PHYSICS IN MEDICINE AND BIOLOGY, 2022, 67 (11)
[7] Dimensionality reduction for visualizing single-cell data using UMAP
Becht, Etienne
McInnes, Leland
Healy, John
Dutertre, Charles-Antoine
Kwok, Immanuel W. H.
Ng, Lai Guan
Ginhoux, Florent
Newell, Evan W.
[J]. NATURE BIOTECHNOLOGY, 2019, 37 (01) : 38 - +
[8] Been K, 2018, C COMP VIS PATT REC
[9] Evaluation of Importance Estimators in Deep Learning Classifiers for Computed Tomography
Brocki, Lennart
Marchadour, Wistan
Maison, Jonas
Badic, Bogdan
Papadimitroulas, Panagiotis
Hatt, Mathieu
Vermet, Franck
Chung, Neo Christopher
[J]. EXPLAINABLE AND TRANSPARENT AI AND MULTI-AGENT SYSTEMS, EXTRAAMAS 2022, 2022, 13283 : 3 - 18
[10] Machine learning applications in radiation oncology: Current use and needs to support clinical implementation
Brouwer, Charlotte L.
Dinkla, Anna M.
Vandewinckele, Liesbeth
Crijns, Wouter
Claessens, Michael
Verellen, Dirk
van Elmpt, Wouter
[J]. PHYSICS & IMAGING IN RADIATION ONCOLOGY, 2020, 16 : 144 - 148

← 1 2 3 4 5 6 7 8 9 →