Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images.
The primary screening by automated computational pathology algorithms of the presence or absence of adenocarcinoma in biopsy specimens (e.g., endoscopic biopsy, transbronchial lung biopsy, and needle biopsy) of possible primary organs (e.g., stomach, colon, lung, and breast) and radical lymph node d...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2022-01-01
|
Series: | PLoS ONE |
Online Access: | https://doi.org/10.1371/journal.pone.0275378 |
_version_ | 1797978055296155648 |
---|---|
author | Masayuki Tsuneki Fahdi Kanavati |
author_facet | Masayuki Tsuneki Fahdi Kanavati |
author_sort | Masayuki Tsuneki |
collection | DOAJ |
description | The primary screening by automated computational pathology algorithms of the presence or absence of adenocarcinoma in biopsy specimens (e.g., endoscopic biopsy, transbronchial lung biopsy, and needle biopsy) of possible primary organs (e.g., stomach, colon, lung, and breast) and radical lymph node dissection specimen is very useful and should be a powerful tool to assist surgical pathologists in routine histopathological diagnostic workflow. In this paper, we trained multi-organ deep learning models to classify adenocarcinoma in biopsy and radical lymph node dissection specimens whole slide images (WSIs). We evaluated the models on five independent test sets (stomach, colon, lung, breast, lymph nodes) to demonstrate the feasibility in multi-organ and lymph nodes specimens from different medical institutions, achieving receiver operating characteristic areas under the curves (ROC-AUCs) in the range of 0.91 -0.98. |
first_indexed | 2024-04-11T05:16:56Z |
format | Article |
id | doaj.art-05c702d7f8a94967b50c3b352868f4b8 |
institution | Directory Open Access Journal |
issn | 1932-6203 |
language | English |
last_indexed | 2024-04-11T05:16:56Z |
publishDate | 2022-01-01 |
publisher | Public Library of Science (PLoS) |
record_format | Article |
series | PLoS ONE |
spelling | doaj.art-05c702d7f8a94967b50c3b352868f4b82022-12-24T05:33:04ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-011711e027537810.1371/journal.pone.0275378Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images.Masayuki TsunekiFahdi KanavatiThe primary screening by automated computational pathology algorithms of the presence or absence of adenocarcinoma in biopsy specimens (e.g., endoscopic biopsy, transbronchial lung biopsy, and needle biopsy) of possible primary organs (e.g., stomach, colon, lung, and breast) and radical lymph node dissection specimen is very useful and should be a powerful tool to assist surgical pathologists in routine histopathological diagnostic workflow. In this paper, we trained multi-organ deep learning models to classify adenocarcinoma in biopsy and radical lymph node dissection specimens whole slide images (WSIs). We evaluated the models on five independent test sets (stomach, colon, lung, breast, lymph nodes) to demonstrate the feasibility in multi-organ and lymph nodes specimens from different medical institutions, achieving receiver operating characteristic areas under the curves (ROC-AUCs) in the range of 0.91 -0.98.https://doi.org/10.1371/journal.pone.0275378 |
spellingShingle | Masayuki Tsuneki Fahdi Kanavati Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images. PLoS ONE |
title | Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images. |
title_full | Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images. |
title_fullStr | Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images. |
title_full_unstemmed | Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images. |
title_short | Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images. |
title_sort | weakly supervised learning for multi organ adenocarcinoma classification in whole slide images |
url | https://doi.org/10.1371/journal.pone.0275378 |
work_keys_str_mv | AT masayukitsuneki weaklysupervisedlearningformultiorganadenocarcinomaclassificationinwholeslideimages AT fahdikanavati weaklysupervisedlearningformultiorganadenocarcinomaclassificationinwholeslideimages |