Yet Another Automated Gleason Grading System (YAAGGS) by weakly supervised deep learning

Abstract The Gleason score contributes significantly in predicting prostate cancer outcomes and selecting the appropriate treatment option, which is affected by well-known inter-observer variations. We present a novel deep learning-based automated Gleason grading system that does not require extensi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yechan Mun, Inyoung Paik, Su-Jin Shin, Tae-Yeong Kwak, Hyeyoon Chang
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/08a6d46ceef34a1fb3100d3ff605886b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:08a6d46ceef34a1fb3100d3ff605886b
record_format	dspace
spelling	oai:doaj.org-article:08a6d46ceef34a1fb3100d3ff605886b2021-12-02T17:40:49ZYet Another Automated Gleason Grading System (YAAGGS) by weakly supervised deep learning10.1038/s41746-021-00469-62398-6352https://doaj.org/article/08a6d46ceef34a1fb3100d3ff605886b2021-06-01T00:00:00Zhttps://doi.org/10.1038/s41746-021-00469-6https://doaj.org/toc/2398-6352Abstract The Gleason score contributes significantly in predicting prostate cancer outcomes and selecting the appropriate treatment option, which is affected by well-known inter-observer variations. We present a novel deep learning-based automated Gleason grading system that does not require extensive region-level manual annotations by experts and/or complex algorithms for the automatic generation of region-level annotations. A total of 6664 and 936 prostate needle biopsy single-core slides (689 and 99 cases) from two institutions were used for system discovery and validation, respectively. Pathological diagnoses were converted into grade groups and used as the reference standard. The grade group prediction accuracy of the system was 77.5% (95% confidence interval (CI): 72.3–82.7%), the Cohen’s kappa score (κ) was 0.650 (95% CI: 0.570–0.730), and the quadratic-weighted kappa score (κ quad) was 0.897 (95% CI: 0.815–0.979). When trained on 621 cases from one institution and validated on 167 cases from the other institution, the system’s accuracy reached 67.4% (95% CI: 63.2–71.6%), κ 0.553 (95% CI: 0.495–0.610), and the κ quad 0.880 (95% CI: 0.822–0.938). In order to evaluate the impact of the proposed method, performance comparison with several baseline methods was also performed. While limited by case volume and a few more factors, the results of this study can contribute to the potential development of an artificial intelligence system to diagnose other cancers without extensive region-level annotations.Yechan MunInyoung PaikSu-Jin ShinTae-Yeong KwakHyeyoon ChangNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 4, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Yechan Mun Inyoung Paik Su-Jin Shin Tae-Yeong Kwak Hyeyoon Chang Yet Another Automated Gleason Grading System (YAAGGS) by weakly supervised deep learning
description	Abstract The Gleason score contributes significantly in predicting prostate cancer outcomes and selecting the appropriate treatment option, which is affected by well-known inter-observer variations. We present a novel deep learning-based automated Gleason grading system that does not require extensive region-level manual annotations by experts and/or complex algorithms for the automatic generation of region-level annotations. A total of 6664 and 936 prostate needle biopsy single-core slides (689 and 99 cases) from two institutions were used for system discovery and validation, respectively. Pathological diagnoses were converted into grade groups and used as the reference standard. The grade group prediction accuracy of the system was 77.5% (95% confidence interval (CI): 72.3–82.7%), the Cohen’s kappa score (κ) was 0.650 (95% CI: 0.570–0.730), and the quadratic-weighted kappa score (κ quad) was 0.897 (95% CI: 0.815–0.979). When trained on 621 cases from one institution and validated on 167 cases from the other institution, the system’s accuracy reached 67.4% (95% CI: 63.2–71.6%), κ 0.553 (95% CI: 0.495–0.610), and the κ quad 0.880 (95% CI: 0.822–0.938). In order to evaluate the impact of the proposed method, performance comparison with several baseline methods was also performed. While limited by case volume and a few more factors, the results of this study can contribute to the potential development of an artificial intelligence system to diagnose other cancers without extensive region-level annotations.
format	article
author	Yechan Mun Inyoung Paik Su-Jin Shin Tae-Yeong Kwak Hyeyoon Chang
author_facet	Yechan Mun Inyoung Paik Su-Jin Shin Tae-Yeong Kwak Hyeyoon Chang
author_sort	Yechan Mun
title	Yet Another Automated Gleason Grading System (YAAGGS) by weakly supervised deep learning
title_short	Yet Another Automated Gleason Grading System (YAAGGS) by weakly supervised deep learning
title_full	Yet Another Automated Gleason Grading System (YAAGGS) by weakly supervised deep learning
title_fullStr	Yet Another Automated Gleason Grading System (YAAGGS) by weakly supervised deep learning
title_full_unstemmed	Yet Another Automated Gleason Grading System (YAAGGS) by weakly supervised deep learning
title_sort	yet another automated gleason grading system (yaaggs) by weakly supervised deep learning
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/08a6d46ceef34a1fb3100d3ff605886b
work_keys_str_mv	AT yechanmun yetanotherautomatedgleasongradingsystemyaaggsbyweaklysuperviseddeeplearning AT inyoungpaik yetanotherautomatedgleasongradingsystemyaaggsbyweaklysuperviseddeeplearning AT sujinshin yetanotherautomatedgleasongradingsystemyaaggsbyweaklysuperviseddeeplearning AT taeyeongkwak yetanotherautomatedgleasongradingsystemyaaggsbyweaklysuperviseddeeplearning AT hyeyoonchang yetanotherautomatedgleasongradingsystemyaaggsbyweaklysuperviseddeeplearning
_version_	1718379687212744704

Yet Another Automated Gleason Grading System (YAAGGS) by weakly supervised deep learning

Ejemplares similares