Cargando…

Tailored for Real-World: A Whole Slide Image Classification System Validated on Uncurated Multi-Site Data Emulating the Prospective Pathology Workload

Standard of care diagnostic procedure for suspected skin cancer is microscopic examination of hematoxylin & eosin stained tissue by a pathologist. Areas of high inter-pathologist discordance and rising biopsy rates necessitate higher efficiency and diagnostic reproducibility. We present and vali...

Descripción completa

Detalles Bibliográficos
Autores principales: Ianni, Julianna D., Soans, Rajath E., Sankarapandian, Sivaramakrishnan, Chamarthi, Ramachandra Vikas, Ayyagari, Devi, Olsen, Thomas G., Bonham, Michael J., Stavish, Coleman C., Motaparthi, Kiran, Cockerell, Clay J., Feeser, Theresa A., Lee, Jason B.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7035316/
https://www.ncbi.nlm.nih.gov/pubmed/32081956
http://dx.doi.org/10.1038/s41598-020-59985-2
_version_ 1783500042577903616
author Ianni, Julianna D.
Soans, Rajath E.
Sankarapandian, Sivaramakrishnan
Chamarthi, Ramachandra Vikas
Ayyagari, Devi
Olsen, Thomas G.
Bonham, Michael J.
Stavish, Coleman C.
Motaparthi, Kiran
Cockerell, Clay J.
Feeser, Theresa A.
Lee, Jason B.
author_facet Ianni, Julianna D.
Soans, Rajath E.
Sankarapandian, Sivaramakrishnan
Chamarthi, Ramachandra Vikas
Ayyagari, Devi
Olsen, Thomas G.
Bonham, Michael J.
Stavish, Coleman C.
Motaparthi, Kiran
Cockerell, Clay J.
Feeser, Theresa A.
Lee, Jason B.
author_sort Ianni, Julianna D.
collection PubMed
description Standard of care diagnostic procedure for suspected skin cancer is microscopic examination of hematoxylin & eosin stained tissue by a pathologist. Areas of high inter-pathologist discordance and rising biopsy rates necessitate higher efficiency and diagnostic reproducibility. We present and validate a deep learning system which classifies digitized dermatopathology slides into 4 categories. The system is developed using 5,070 images from a single lab, and tested on an uncurated set of 13,537 images from 3 test labs, using whole slide scanners manufactured by 3 different vendors. The system’s use of deep-learning-based confidence scoring as a criterion to consider the result as accurate yields an accuracy of up to 98%, and makes it adoptable in a real-world setting. Without confidence scoring, the system achieved an accuracy of 78%. We anticipate that our deep learning system will serve as a foundation enabling faster diagnosis of skin cancer, identification of cases for specialist review, and targeted diagnostic classifications.
format Online
Article
Text
id pubmed-7035316
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-70353162020-02-28 Tailored for Real-World: A Whole Slide Image Classification System Validated on Uncurated Multi-Site Data Emulating the Prospective Pathology Workload Ianni, Julianna D. Soans, Rajath E. Sankarapandian, Sivaramakrishnan Chamarthi, Ramachandra Vikas Ayyagari, Devi Olsen, Thomas G. Bonham, Michael J. Stavish, Coleman C. Motaparthi, Kiran Cockerell, Clay J. Feeser, Theresa A. Lee, Jason B. Sci Rep Article Standard of care diagnostic procedure for suspected skin cancer is microscopic examination of hematoxylin & eosin stained tissue by a pathologist. Areas of high inter-pathologist discordance and rising biopsy rates necessitate higher efficiency and diagnostic reproducibility. We present and validate a deep learning system which classifies digitized dermatopathology slides into 4 categories. The system is developed using 5,070 images from a single lab, and tested on an uncurated set of 13,537 images from 3 test labs, using whole slide scanners manufactured by 3 different vendors. The system’s use of deep-learning-based confidence scoring as a criterion to consider the result as accurate yields an accuracy of up to 98%, and makes it adoptable in a real-world setting. Without confidence scoring, the system achieved an accuracy of 78%. We anticipate that our deep learning system will serve as a foundation enabling faster diagnosis of skin cancer, identification of cases for specialist review, and targeted diagnostic classifications. Nature Publishing Group UK 2020-02-21 /pmc/articles/PMC7035316/ /pubmed/32081956 http://dx.doi.org/10.1038/s41598-020-59985-2 Text en © The Author(s) 2020 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
Ianni, Julianna D.
Soans, Rajath E.
Sankarapandian, Sivaramakrishnan
Chamarthi, Ramachandra Vikas
Ayyagari, Devi
Olsen, Thomas G.
Bonham, Michael J.
Stavish, Coleman C.
Motaparthi, Kiran
Cockerell, Clay J.
Feeser, Theresa A.
Lee, Jason B.
Tailored for Real-World: A Whole Slide Image Classification System Validated on Uncurated Multi-Site Data Emulating the Prospective Pathology Workload
title Tailored for Real-World: A Whole Slide Image Classification System Validated on Uncurated Multi-Site Data Emulating the Prospective Pathology Workload
title_full Tailored for Real-World: A Whole Slide Image Classification System Validated on Uncurated Multi-Site Data Emulating the Prospective Pathology Workload
title_fullStr Tailored for Real-World: A Whole Slide Image Classification System Validated on Uncurated Multi-Site Data Emulating the Prospective Pathology Workload
title_full_unstemmed Tailored for Real-World: A Whole Slide Image Classification System Validated on Uncurated Multi-Site Data Emulating the Prospective Pathology Workload
title_short Tailored for Real-World: A Whole Slide Image Classification System Validated on Uncurated Multi-Site Data Emulating the Prospective Pathology Workload
title_sort tailored for real-world: a whole slide image classification system validated on uncurated multi-site data emulating the prospective pathology workload
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7035316/
https://www.ncbi.nlm.nih.gov/pubmed/32081956
http://dx.doi.org/10.1038/s41598-020-59985-2
work_keys_str_mv AT iannijuliannad tailoredforrealworldawholeslideimageclassificationsystemvalidatedonuncuratedmultisitedataemulatingtheprospectivepathologyworkload
AT soansrajathe tailoredforrealworldawholeslideimageclassificationsystemvalidatedonuncuratedmultisitedataemulatingtheprospectivepathologyworkload
AT sankarapandiansivaramakrishnan tailoredforrealworldawholeslideimageclassificationsystemvalidatedonuncuratedmultisitedataemulatingtheprospectivepathologyworkload
AT chamarthiramachandravikas tailoredforrealworldawholeslideimageclassificationsystemvalidatedonuncuratedmultisitedataemulatingtheprospectivepathologyworkload
AT ayyagaridevi tailoredforrealworldawholeslideimageclassificationsystemvalidatedonuncuratedmultisitedataemulatingtheprospectivepathologyworkload
AT olsenthomasg tailoredforrealworldawholeslideimageclassificationsystemvalidatedonuncuratedmultisitedataemulatingtheprospectivepathologyworkload
AT bonhammichaelj tailoredforrealworldawholeslideimageclassificationsystemvalidatedonuncuratedmultisitedataemulatingtheprospectivepathologyworkload
AT stavishcolemanc tailoredforrealworldawholeslideimageclassificationsystemvalidatedonuncuratedmultisitedataemulatingtheprospectivepathologyworkload
AT motaparthikiran tailoredforrealworldawholeslideimageclassificationsystemvalidatedonuncuratedmultisitedataemulatingtheprospectivepathologyworkload
AT cockerellclayj tailoredforrealworldawholeslideimageclassificationsystemvalidatedonuncuratedmultisitedataemulatingtheprospectivepathologyworkload
AT feesertheresaa tailoredforrealworldawholeslideimageclassificationsystemvalidatedonuncuratedmultisitedataemulatingtheprospectivepathologyworkload
AT leejasonb tailoredforrealworldawholeslideimageclassificationsystemvalidatedonuncuratedmultisitedataemulatingtheprospectivepathologyworkload