Cargando…

Explainability of deep learning models in medical video analysis: a survey

Deep learning methods have proven to be effective for multiple diagnostic tasks in medicine and have been performing significantly better in comparison to other traditional machine learning methods. However, the black-box nature of deep neural networks has restricted their use in real-world applicat...

Descripción completa

Detalles Bibliográficos
Autores principales: Kolarik, Michal, Sarnovsky, Martin, Paralic, Jan, Babic, Frantisek
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10280416/
https://www.ncbi.nlm.nih.gov/pubmed/37346619
http://dx.doi.org/10.7717/peerj-cs.1253
_version_ 1785060789580726272
author Kolarik, Michal
Sarnovsky, Martin
Paralic, Jan
Babic, Frantisek
author_facet Kolarik, Michal
Sarnovsky, Martin
Paralic, Jan
Babic, Frantisek
author_sort Kolarik, Michal
collection PubMed
description Deep learning methods have proven to be effective for multiple diagnostic tasks in medicine and have been performing significantly better in comparison to other traditional machine learning methods. However, the black-box nature of deep neural networks has restricted their use in real-world applications, especially in healthcare. Therefore, explainability of the machine learning models, which focuses on providing of the comprehensible explanations of model outputs, may affect the possibility of adoption of such models in clinical use. There are various studies reviewing approaches to explainability in multiple domains. This article provides a review of the current approaches and applications of explainable deep learning for a specific area of medical data analysis—medical video processing tasks. The article introduces the field of explainable AI and summarizes the most important requirements for explainability in medical applications. Subsequently, we provide an overview of existing methods, evaluation metrics and focus more on those that can be applied to analytical tasks involving the processing of video data in the medical domain. Finally we identify some of the open research issues in the analysed area.
format Online
Article
Text
id pubmed-10280416
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-102804162023-06-21 Explainability of deep learning models in medical video analysis: a survey Kolarik, Michal Sarnovsky, Martin Paralic, Jan Babic, Frantisek PeerJ Comput Sci Bioinformatics Deep learning methods have proven to be effective for multiple diagnostic tasks in medicine and have been performing significantly better in comparison to other traditional machine learning methods. However, the black-box nature of deep neural networks has restricted their use in real-world applications, especially in healthcare. Therefore, explainability of the machine learning models, which focuses on providing of the comprehensible explanations of model outputs, may affect the possibility of adoption of such models in clinical use. There are various studies reviewing approaches to explainability in multiple domains. This article provides a review of the current approaches and applications of explainable deep learning for a specific area of medical data analysis—medical video processing tasks. The article introduces the field of explainable AI and summarizes the most important requirements for explainability in medical applications. Subsequently, we provide an overview of existing methods, evaluation metrics and focus more on those that can be applied to analytical tasks involving the processing of video data in the medical domain. Finally we identify some of the open research issues in the analysed area. PeerJ Inc. 2023-03-14 /pmc/articles/PMC10280416/ /pubmed/37346619 http://dx.doi.org/10.7717/peerj-cs.1253 Text en ©2023 Kolarik et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Bioinformatics
Kolarik, Michal
Sarnovsky, Martin
Paralic, Jan
Babic, Frantisek
Explainability of deep learning models in medical video analysis: a survey
title Explainability of deep learning models in medical video analysis: a survey
title_full Explainability of deep learning models in medical video analysis: a survey
title_fullStr Explainability of deep learning models in medical video analysis: a survey
title_full_unstemmed Explainability of deep learning models in medical video analysis: a survey
title_short Explainability of deep learning models in medical video analysis: a survey
title_sort explainability of deep learning models in medical video analysis: a survey
topic Bioinformatics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10280416/
https://www.ncbi.nlm.nih.gov/pubmed/37346619
http://dx.doi.org/10.7717/peerj-cs.1253
work_keys_str_mv AT kolarikmichal explainabilityofdeeplearningmodelsinmedicalvideoanalysisasurvey
AT sarnovskymartin explainabilityofdeeplearningmodelsinmedicalvideoanalysisasurvey
AT paralicjan explainabilityofdeeplearningmodelsinmedicalvideoanalysisasurvey
AT babicfrantisek explainabilityofdeeplearningmodelsinmedicalvideoanalysisasurvey