Cargando…

A survey on the interpretability of deep learning in medical diagnosis

Deep learning has demonstrated remarkable performance in the medical domain, with accuracy that rivals or even exceeds that of human experts. However, it has a significant problem that these models are “black-box” structures, which means they are opaque, non-intuitive, and difficult for people to un...

Descripción completa

Detalles Bibliográficos
Autores principales: Teng, Qiaoying, Liu, Zhe, Song, Yuqing, Han, Kai, Lu, Yang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Berlin Heidelberg 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9243744/
https://www.ncbi.nlm.nih.gov/pubmed/35789785
http://dx.doi.org/10.1007/s00530-022-00960-4
_version_ 1784738380617089024
author Teng, Qiaoying
Liu, Zhe
Song, Yuqing
Han, Kai
Lu, Yang
author_facet Teng, Qiaoying
Liu, Zhe
Song, Yuqing
Han, Kai
Lu, Yang
author_sort Teng, Qiaoying
collection PubMed
description Deep learning has demonstrated remarkable performance in the medical domain, with accuracy that rivals or even exceeds that of human experts. However, it has a significant problem that these models are “black-box” structures, which means they are opaque, non-intuitive, and difficult for people to understand. This creates a barrier to the application of deep learning models in clinical practice due to lack of interpretability, trust, and transparency. To overcome this problem, several studies on interpretability have been proposed. Therefore, in this paper, we comprehensively review the interpretability of deep learning in medical diagnosis based on the current literature, including some common interpretability methods used in the medical domain, various applications with interpretability for disease diagnosis, prevalent evaluation metrics, and several disease datasets. In addition, the challenges of interpretability and future research directions are also discussed here. To the best of our knowledge, this is the first time that various applications of interpretability methods for disease diagnosis have been summarized.
format Online
Article
Text
id pubmed-9243744
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Springer Berlin Heidelberg
record_format MEDLINE/PubMed
spelling pubmed-92437442022-06-30 A survey on the interpretability of deep learning in medical diagnosis Teng, Qiaoying Liu, Zhe Song, Yuqing Han, Kai Lu, Yang Multimed Syst Regular Article Deep learning has demonstrated remarkable performance in the medical domain, with accuracy that rivals or even exceeds that of human experts. However, it has a significant problem that these models are “black-box” structures, which means they are opaque, non-intuitive, and difficult for people to understand. This creates a barrier to the application of deep learning models in clinical practice due to lack of interpretability, trust, and transparency. To overcome this problem, several studies on interpretability have been proposed. Therefore, in this paper, we comprehensively review the interpretability of deep learning in medical diagnosis based on the current literature, including some common interpretability methods used in the medical domain, various applications with interpretability for disease diagnosis, prevalent evaluation metrics, and several disease datasets. In addition, the challenges of interpretability and future research directions are also discussed here. To the best of our knowledge, this is the first time that various applications of interpretability methods for disease diagnosis have been summarized. Springer Berlin Heidelberg 2022-06-25 2022 /pmc/articles/PMC9243744/ /pubmed/35789785 http://dx.doi.org/10.1007/s00530-022-00960-4 Text en © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Regular Article
Teng, Qiaoying
Liu, Zhe
Song, Yuqing
Han, Kai
Lu, Yang
A survey on the interpretability of deep learning in medical diagnosis
title A survey on the interpretability of deep learning in medical diagnosis
title_full A survey on the interpretability of deep learning in medical diagnosis
title_fullStr A survey on the interpretability of deep learning in medical diagnosis
title_full_unstemmed A survey on the interpretability of deep learning in medical diagnosis
title_short A survey on the interpretability of deep learning in medical diagnosis
title_sort survey on the interpretability of deep learning in medical diagnosis
topic Regular Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9243744/
https://www.ncbi.nlm.nih.gov/pubmed/35789785
http://dx.doi.org/10.1007/s00530-022-00960-4
work_keys_str_mv AT tengqiaoying asurveyontheinterpretabilityofdeeplearninginmedicaldiagnosis
AT liuzhe asurveyontheinterpretabilityofdeeplearninginmedicaldiagnosis
AT songyuqing asurveyontheinterpretabilityofdeeplearninginmedicaldiagnosis
AT hankai asurveyontheinterpretabilityofdeeplearninginmedicaldiagnosis
AT luyang asurveyontheinterpretabilityofdeeplearninginmedicaldiagnosis
AT tengqiaoying surveyontheinterpretabilityofdeeplearninginmedicaldiagnosis
AT liuzhe surveyontheinterpretabilityofdeeplearninginmedicaldiagnosis
AT songyuqing surveyontheinterpretabilityofdeeplearninginmedicaldiagnosis
AT hankai surveyontheinterpretabilityofdeeplearninginmedicaldiagnosis
AT luyang surveyontheinterpretabilityofdeeplearninginmedicaldiagnosis