A review of uncertainty estimation and its application in medical imaging

The use of AI systems in healthcare for the early screening of diseases is of great clinical importance. Deep learning has shown great promise in medical imaging, but the reliability and trustworthiness of AI systems limit their deployment in real clinical scenes, where patient safety is at stake. U...

Full description

Saved in:
Bibliographic Details
Main Authors: Ke Zou, Zhihao Chen, Xuedong Yuan, Xiaojing Shen, Meng Wang, Huazhu Fu
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2023-06-01
Series:Meta-Radiology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2950162823000036
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846169996172984320
author Ke Zou
Zhihao Chen
Xuedong Yuan
Xiaojing Shen
Meng Wang
Huazhu Fu
author_facet Ke Zou
Zhihao Chen
Xuedong Yuan
Xiaojing Shen
Meng Wang
Huazhu Fu
author_sort Ke Zou
collection DOAJ
description The use of AI systems in healthcare for the early screening of diseases is of great clinical importance. Deep learning has shown great promise in medical imaging, but the reliability and trustworthiness of AI systems limit their deployment in real clinical scenes, where patient safety is at stake. Uncertainty estimation plays a pivotal role in producing a confidence evaluation along with the prediction of the deep model. This is particularly important in medical imaging, where the uncertainty in the model's predictions can be used to identify areas of concern or to provide additional information to the clinician. In this paper, we review the various types of uncertainty in deep learning, including aleatoric uncertainty and epistemic uncertainty. We further discuss how they can be estimated in medical imaging. More importantly, we review recent advances in deep learning models that incorporate uncertainty estimation in medical imaging. Finally, we discuss the challenges and future directions in uncertainty estimation in deep learning for medical imaging. We hope this review will ignite further interest in the community and provide researchers with an up-to-date reference regarding applications of uncertainty estimation models in medical imaging.
format Article
id doaj-art-24a868886fcc47648c6e86c8b42354d7
institution Kabale University
issn 2950-1628
language English
publishDate 2023-06-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Meta-Radiology
spelling doaj-art-24a868886fcc47648c6e86c8b42354d72024-11-12T05:22:35ZengKeAi Communications Co., Ltd.Meta-Radiology2950-16282023-06-0111100003A review of uncertainty estimation and its application in medical imagingKe Zou0Zhihao Chen1Xuedong Yuan2Xiaojing Shen3Meng Wang4Huazhu Fu5National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, China; The College of Computer Science, Sichuan University, Chengdu 610065, ChinaCollege of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaNational Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, China; The College of Computer Science, Sichuan University, Chengdu 610065, ChinaNational Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, China; Department of Mathematics, Sichuan University, Chengdu 610065, ChinaInstitute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A∗STAR), Singapore 138632, Republic of SingaporeInstitute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A∗STAR), Singapore 138632, Republic of Singapore; Corresponding author.The use of AI systems in healthcare for the early screening of diseases is of great clinical importance. Deep learning has shown great promise in medical imaging, but the reliability and trustworthiness of AI systems limit their deployment in real clinical scenes, where patient safety is at stake. Uncertainty estimation plays a pivotal role in producing a confidence evaluation along with the prediction of the deep model. This is particularly important in medical imaging, where the uncertainty in the model's predictions can be used to identify areas of concern or to provide additional information to the clinician. In this paper, we review the various types of uncertainty in deep learning, including aleatoric uncertainty and epistemic uncertainty. We further discuss how they can be estimated in medical imaging. More importantly, we review recent advances in deep learning models that incorporate uncertainty estimation in medical imaging. Finally, we discuss the challenges and future directions in uncertainty estimation in deep learning for medical imaging. We hope this review will ignite further interest in the community and provide researchers with an up-to-date reference regarding applications of uncertainty estimation models in medical imaging.http://www.sciencedirect.com/science/article/pii/S2950162823000036Deep learningUncertainty estimationMedical image analysis
spellingShingle Ke Zou
Zhihao Chen
Xuedong Yuan
Xiaojing Shen
Meng Wang
Huazhu Fu
A review of uncertainty estimation and its application in medical imaging
Meta-Radiology
Deep learning
Uncertainty estimation
Medical image analysis
title A review of uncertainty estimation and its application in medical imaging
title_full A review of uncertainty estimation and its application in medical imaging
title_fullStr A review of uncertainty estimation and its application in medical imaging
title_full_unstemmed A review of uncertainty estimation and its application in medical imaging
title_short A review of uncertainty estimation and its application in medical imaging
title_sort review of uncertainty estimation and its application in medical imaging
topic Deep learning
Uncertainty estimation
Medical image analysis
url http://www.sciencedirect.com/science/article/pii/S2950162823000036
work_keys_str_mv AT kezou areviewofuncertaintyestimationanditsapplicationinmedicalimaging
AT zhihaochen areviewofuncertaintyestimationanditsapplicationinmedicalimaging
AT xuedongyuan areviewofuncertaintyestimationanditsapplicationinmedicalimaging
AT xiaojingshen areviewofuncertaintyestimationanditsapplicationinmedicalimaging
AT mengwang areviewofuncertaintyestimationanditsapplicationinmedicalimaging
AT huazhufu areviewofuncertaintyestimationanditsapplicationinmedicalimaging
AT kezou reviewofuncertaintyestimationanditsapplicationinmedicalimaging
AT zhihaochen reviewofuncertaintyestimationanditsapplicationinmedicalimaging
AT xuedongyuan reviewofuncertaintyestimationanditsapplicationinmedicalimaging
AT xiaojingshen reviewofuncertaintyestimationanditsapplicationinmedicalimaging
AT mengwang reviewofuncertaintyestimationanditsapplicationinmedicalimaging
AT huazhufu reviewofuncertaintyestimationanditsapplicationinmedicalimaging