Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy

Abstract Probe-based confocal laser endomicroscopy (pCLE) allows for real-time diagnosis of dysplasia and cancer in Barrett’s esophagus (BE) but is limited by low sensitivity. Even the gold standard of histopathology is hindered by poor agreement between pathologists. We deployed deep-learning-based...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shan Guleria, Tilak U. Shah, J. Vincent Pulido, Matthew Fasullo, Lubaina Ehsan, Robert Lippman, Rasoul Sali, Pritesh Mutha, Lin Cheng, Donald E. Brown, Sana Syed
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/df6765aa6ac34a5dbce4e8afc7071d66
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:df6765aa6ac34a5dbce4e8afc7071d66
record_format	dspace
spelling	oai:doaj.org-article:df6765aa6ac34a5dbce4e8afc7071d662021-12-02T15:54:10ZDeep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy10.1038/s41598-021-84510-42045-2322https://doaj.org/article/df6765aa6ac34a5dbce4e8afc7071d662021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-84510-4https://doaj.org/toc/2045-2322Abstract Probe-based confocal laser endomicroscopy (pCLE) allows for real-time diagnosis of dysplasia and cancer in Barrett’s esophagus (BE) but is limited by low sensitivity. Even the gold standard of histopathology is hindered by poor agreement between pathologists. We deployed deep-learning-based image and video analysis in order to improve diagnostic accuracy of pCLE videos and biopsy images. Blinded experts categorized biopsies and pCLE videos as squamous, non-dysplastic BE, or dysplasia/cancer, and deep learning models were trained to classify the data into these three categories. Biopsy classification was conducted using two distinct approaches—a patch-level model and a whole-slide-image-level model. Gradient-weighted class activation maps (Grad-CAMs) were extracted from pCLE and biopsy models in order to determine tissue structures deemed relevant by the models. 1970 pCLE videos, 897,931 biopsy patches, and 387 whole-slide images were used to train, test, and validate the models. In pCLE analysis, models achieved a high sensitivity for dysplasia (71%) and an overall accuracy of 90% for all classes. For biopsies at the patch level, the model achieved a sensitivity of 72% for dysplasia and an overall accuracy of 90%. The whole-slide-image-level model achieved a sensitivity of 90% for dysplasia and 94% overall accuracy. Grad-CAMs for all models showed activation in medically relevant tissue regions. Our deep learning models achieved high diagnostic accuracy for both pCLE-based and histopathologic diagnosis of esophageal dysplasia and its precursors, similar to human accuracy in prior studies. These machine learning approaches may improve accuracy and efficiency of current screening protocols.Shan GuleriaTilak U. ShahJ. Vincent PulidoMatthew FasulloLubaina EhsanRobert LippmanRasoul SaliPritesh MuthaLin ChengDonald E. BrownSana SyedNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Shan Guleria Tilak U. Shah J. Vincent Pulido Matthew Fasullo Lubaina Ehsan Robert Lippman Rasoul Sali Pritesh Mutha Lin Cheng Donald E. Brown Sana Syed Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy
description	Abstract Probe-based confocal laser endomicroscopy (pCLE) allows for real-time diagnosis of dysplasia and cancer in Barrett’s esophagus (BE) but is limited by low sensitivity. Even the gold standard of histopathology is hindered by poor agreement between pathologists. We deployed deep-learning-based image and video analysis in order to improve diagnostic accuracy of pCLE videos and biopsy images. Blinded experts categorized biopsies and pCLE videos as squamous, non-dysplastic BE, or dysplasia/cancer, and deep learning models were trained to classify the data into these three categories. Biopsy classification was conducted using two distinct approaches—a patch-level model and a whole-slide-image-level model. Gradient-weighted class activation maps (Grad-CAMs) were extracted from pCLE and biopsy models in order to determine tissue structures deemed relevant by the models. 1970 pCLE videos, 897,931 biopsy patches, and 387 whole-slide images were used to train, test, and validate the models. In pCLE analysis, models achieved a high sensitivity for dysplasia (71%) and an overall accuracy of 90% for all classes. For biopsies at the patch level, the model achieved a sensitivity of 72% for dysplasia and an overall accuracy of 90%. The whole-slide-image-level model achieved a sensitivity of 90% for dysplasia and 94% overall accuracy. Grad-CAMs for all models showed activation in medically relevant tissue regions. Our deep learning models achieved high diagnostic accuracy for both pCLE-based and histopathologic diagnosis of esophageal dysplasia and its precursors, similar to human accuracy in prior studies. These machine learning approaches may improve accuracy and efficiency of current screening protocols.
format	article
author	Shan Guleria Tilak U. Shah J. Vincent Pulido Matthew Fasullo Lubaina Ehsan Robert Lippman Rasoul Sali Pritesh Mutha Lin Cheng Donald E. Brown Sana Syed
author_facet	Shan Guleria Tilak U. Shah J. Vincent Pulido Matthew Fasullo Lubaina Ehsan Robert Lippman Rasoul Sali Pritesh Mutha Lin Cheng Donald E. Brown Sana Syed
author_sort	Shan Guleria
title	Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy
title_short	Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy
title_full	Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy
title_fullStr	Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy
title_full_unstemmed	Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy
title_sort	deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/df6765aa6ac34a5dbce4e8afc7071d66
work_keys_str_mv	AT shanguleria deeplearningsystemsdetectdysplasiawithhumanlikeaccuracyusinghistopathologyandprobebasedconfocallaserendomicroscopy AT tilakushah deeplearningsystemsdetectdysplasiawithhumanlikeaccuracyusinghistopathologyandprobebasedconfocallaserendomicroscopy AT jvincentpulido deeplearningsystemsdetectdysplasiawithhumanlikeaccuracyusinghistopathologyandprobebasedconfocallaserendomicroscopy AT matthewfasullo deeplearningsystemsdetectdysplasiawithhumanlikeaccuracyusinghistopathologyandprobebasedconfocallaserendomicroscopy AT lubainaehsan deeplearningsystemsdetectdysplasiawithhumanlikeaccuracyusinghistopathologyandprobebasedconfocallaserendomicroscopy AT robertlippman deeplearningsystemsdetectdysplasiawithhumanlikeaccuracyusinghistopathologyandprobebasedconfocallaserendomicroscopy AT rasoulsali deeplearningsystemsdetectdysplasiawithhumanlikeaccuracyusinghistopathologyandprobebasedconfocallaserendomicroscopy AT priteshmutha deeplearningsystemsdetectdysplasiawithhumanlikeaccuracyusinghistopathologyandprobebasedconfocallaserendomicroscopy AT lincheng deeplearningsystemsdetectdysplasiawithhumanlikeaccuracyusinghistopathologyandprobebasedconfocallaserendomicroscopy AT donaldebrown deeplearningsystemsdetectdysplasiawithhumanlikeaccuracyusinghistopathologyandprobebasedconfocallaserendomicroscopy AT sanasyed deeplearningsystemsdetectdysplasiawithhumanlikeaccuracyusinghistopathologyandprobebasedconfocallaserendomicroscopy
_version_	1718385481700343808

Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy

Ejemplares similares