Cargando…

Automated acquisition of explainable knowledge from unannotated histopathology images

Deep learning algorithms have been successfully used in medical image classification. In the next stage, the technology of acquiring explainable knowledge from medical images is highly desired. Here we show that deep learning algorithm enables automated acquisition of explainable features from diagn...

Descripción completa

Detalles Bibliográficos
Autores principales: Yamamoto, Yoichiro, Tsuzuki, Toyonori, Akatsuka, Jun, Ueki, Masao, Morikawa, Hiromu, Numata, Yasushi, Takahara, Taishi, Tsuyuki, Takuji, Tsutsumi, Kotaro, Nakazawa, Ryuto, Shimizu, Akira, Maeda, Ichiro, Tsuchiya, Shinichi, Kanno, Hiroyuki, Kondo, Yukihiro, Fukumoto, Manabu, Tamiya, Gen, Ueda, Naonori, Kimura, Go
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6920352/
https://www.ncbi.nlm.nih.gov/pubmed/31852890
http://dx.doi.org/10.1038/s41467-019-13647-8
_version_ 1783480934821003264
author Yamamoto, Yoichiro
Tsuzuki, Toyonori
Akatsuka, Jun
Ueki, Masao
Morikawa, Hiromu
Numata, Yasushi
Takahara, Taishi
Tsuyuki, Takuji
Tsutsumi, Kotaro
Nakazawa, Ryuto
Shimizu, Akira
Maeda, Ichiro
Tsuchiya, Shinichi
Kanno, Hiroyuki
Kondo, Yukihiro
Fukumoto, Manabu
Tamiya, Gen
Ueda, Naonori
Kimura, Go
author_facet Yamamoto, Yoichiro
Tsuzuki, Toyonori
Akatsuka, Jun
Ueki, Masao
Morikawa, Hiromu
Numata, Yasushi
Takahara, Taishi
Tsuyuki, Takuji
Tsutsumi, Kotaro
Nakazawa, Ryuto
Shimizu, Akira
Maeda, Ichiro
Tsuchiya, Shinichi
Kanno, Hiroyuki
Kondo, Yukihiro
Fukumoto, Manabu
Tamiya, Gen
Ueda, Naonori
Kimura, Go
author_sort Yamamoto, Yoichiro
collection PubMed
description Deep learning algorithms have been successfully used in medical image classification. In the next stage, the technology of acquiring explainable knowledge from medical images is highly desired. Here we show that deep learning algorithm enables automated acquisition of explainable features from diagnostic annotation-free histopathology images. We compare the prediction accuracy of prostate cancer recurrence using our algorithm-generated features with that of diagnosis by expert pathologists using established criteria on 13,188 whole-mount pathology images consisting of over 86 billion image patches. Our method not only reveals findings established by humans but also features that have not been recognized, showing higher accuracy than human in prognostic prediction. Combining both our algorithm-generated features and human-established criteria predicts the recurrence more accurately than using either method alone. We confirm robustness of our method using external validation datasets including 2276 pathology images. This study opens up fields of machine learning analysis for discovering uncharted knowledge.
format Online
Article
Text
id pubmed-6920352
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-69203522019-12-20 Automated acquisition of explainable knowledge from unannotated histopathology images Yamamoto, Yoichiro Tsuzuki, Toyonori Akatsuka, Jun Ueki, Masao Morikawa, Hiromu Numata, Yasushi Takahara, Taishi Tsuyuki, Takuji Tsutsumi, Kotaro Nakazawa, Ryuto Shimizu, Akira Maeda, Ichiro Tsuchiya, Shinichi Kanno, Hiroyuki Kondo, Yukihiro Fukumoto, Manabu Tamiya, Gen Ueda, Naonori Kimura, Go Nat Commun Article Deep learning algorithms have been successfully used in medical image classification. In the next stage, the technology of acquiring explainable knowledge from medical images is highly desired. Here we show that deep learning algorithm enables automated acquisition of explainable features from diagnostic annotation-free histopathology images. We compare the prediction accuracy of prostate cancer recurrence using our algorithm-generated features with that of diagnosis by expert pathologists using established criteria on 13,188 whole-mount pathology images consisting of over 86 billion image patches. Our method not only reveals findings established by humans but also features that have not been recognized, showing higher accuracy than human in prognostic prediction. Combining both our algorithm-generated features and human-established criteria predicts the recurrence more accurately than using either method alone. We confirm robustness of our method using external validation datasets including 2276 pathology images. This study opens up fields of machine learning analysis for discovering uncharted knowledge. Nature Publishing Group UK 2019-12-18 /pmc/articles/PMC6920352/ /pubmed/31852890 http://dx.doi.org/10.1038/s41467-019-13647-8 Text en © The Author(s) 2019 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.
spellingShingle Article
Yamamoto, Yoichiro
Tsuzuki, Toyonori
Akatsuka, Jun
Ueki, Masao
Morikawa, Hiromu
Numata, Yasushi
Takahara, Taishi
Tsuyuki, Takuji
Tsutsumi, Kotaro
Nakazawa, Ryuto
Shimizu, Akira
Maeda, Ichiro
Tsuchiya, Shinichi
Kanno, Hiroyuki
Kondo, Yukihiro
Fukumoto, Manabu
Tamiya, Gen
Ueda, Naonori
Kimura, Go
Automated acquisition of explainable knowledge from unannotated histopathology images
title Automated acquisition of explainable knowledge from unannotated histopathology images
title_full Automated acquisition of explainable knowledge from unannotated histopathology images
title_fullStr Automated acquisition of explainable knowledge from unannotated histopathology images
title_full_unstemmed Automated acquisition of explainable knowledge from unannotated histopathology images
title_short Automated acquisition of explainable knowledge from unannotated histopathology images
title_sort automated acquisition of explainable knowledge from unannotated histopathology images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6920352/
https://www.ncbi.nlm.nih.gov/pubmed/31852890
http://dx.doi.org/10.1038/s41467-019-13647-8
work_keys_str_mv AT yamamotoyoichiro automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT tsuzukitoyonori automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT akatsukajun automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT uekimasao automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT morikawahiromu automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT numatayasushi automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT takaharataishi automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT tsuyukitakuji automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT tsutsumikotaro automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT nakazawaryuto automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT shimizuakira automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT maedaichiro automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT tsuchiyashinichi automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT kannohiroyuki automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT kondoyukihiro automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT fukumotomanabu automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT tamiyagen automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT uedanaonori automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages
AT kimurago automatedacquisitionofexplainableknowledgefromunannotatedhistopathologyimages