Cargando…
Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent
With the increasing ability to routinely and rapidly digitize whole slide images with slide scanners, there has been interest in developing computerized image analysis algorithms for automated detection of disease extent from digital pathology images. The manual identification of presence and extent...
Autores principales: | , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5394452/ https://www.ncbi.nlm.nih.gov/pubmed/28418027 http://dx.doi.org/10.1038/srep46450 |
_version_ | 1783229732056203264 |
---|---|
author | Cruz-Roa, Angel Gilmore, Hannah Basavanhally, Ajay Feldman, Michael Ganesan, Shridar Shih, Natalie N.C. Tomaszewski, John González, Fabio A. Madabhushi, Anant |
author_facet | Cruz-Roa, Angel Gilmore, Hannah Basavanhally, Ajay Feldman, Michael Ganesan, Shridar Shih, Natalie N.C. Tomaszewski, John González, Fabio A. Madabhushi, Anant |
author_sort | Cruz-Roa, Angel |
collection | PubMed |
description | With the increasing ability to routinely and rapidly digitize whole slide images with slide scanners, there has been interest in developing computerized image analysis algorithms for automated detection of disease extent from digital pathology images. The manual identification of presence and extent of breast cancer by a pathologist is critical for patient management for tumor staging and assessing treatment response. However, this process is tedious and subject to inter- and intra-reader variability. For computerized methods to be useful as decision support tools, they need to be resilient to data acquired from different sources, different staining and cutting protocols and different scanners. The objective of this study was to evaluate the accuracy and robustness of a deep learning-based method to automatically identify the extent of invasive tumor on digitized images. Here, we present a new method that employs a convolutional neural network for detecting presence of invasive tumor on whole slide images. Our approach involves training the classifier on nearly 400 exemplars from multiple different sites, and scanners, and then independently validating on almost 200 cases from The Cancer Genome Atlas. Our approach yielded a Dice coefficient of 75.86%, a positive predictive value of 71.62% and a negative predictive value of 96.77% in terms of pixel-by-pixel evaluation compared to manually annotated regions of invasive ductal carcinoma. |
format | Online Article Text |
id | pubmed-5394452 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2017 |
publisher | Nature Publishing Group |
record_format | MEDLINE/PubMed |
spelling | pubmed-53944522017-04-20 Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent Cruz-Roa, Angel Gilmore, Hannah Basavanhally, Ajay Feldman, Michael Ganesan, Shridar Shih, Natalie N.C. Tomaszewski, John González, Fabio A. Madabhushi, Anant Sci Rep Article With the increasing ability to routinely and rapidly digitize whole slide images with slide scanners, there has been interest in developing computerized image analysis algorithms for automated detection of disease extent from digital pathology images. The manual identification of presence and extent of breast cancer by a pathologist is critical for patient management for tumor staging and assessing treatment response. However, this process is tedious and subject to inter- and intra-reader variability. For computerized methods to be useful as decision support tools, they need to be resilient to data acquired from different sources, different staining and cutting protocols and different scanners. The objective of this study was to evaluate the accuracy and robustness of a deep learning-based method to automatically identify the extent of invasive tumor on digitized images. Here, we present a new method that employs a convolutional neural network for detecting presence of invasive tumor on whole slide images. Our approach involves training the classifier on nearly 400 exemplars from multiple different sites, and scanners, and then independently validating on almost 200 cases from The Cancer Genome Atlas. Our approach yielded a Dice coefficient of 75.86%, a positive predictive value of 71.62% and a negative predictive value of 96.77% in terms of pixel-by-pixel evaluation compared to manually annotated regions of invasive ductal carcinoma. Nature Publishing Group 2017-04-18 /pmc/articles/PMC5394452/ /pubmed/28418027 http://dx.doi.org/10.1038/srep46450 Text en Copyright © 2017, The Author(s) http://creativecommons.org/licenses/by/4.0/ This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ |
spellingShingle | Article Cruz-Roa, Angel Gilmore, Hannah Basavanhally, Ajay Feldman, Michael Ganesan, Shridar Shih, Natalie N.C. Tomaszewski, John González, Fabio A. Madabhushi, Anant Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent |
title | Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent |
title_full | Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent |
title_fullStr | Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent |
title_full_unstemmed | Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent |
title_short | Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent |
title_sort | accurate and reproducible invasive breast cancer detection in whole-slide images: a deep learning approach for quantifying tumor extent |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5394452/ https://www.ncbi.nlm.nih.gov/pubmed/28418027 http://dx.doi.org/10.1038/srep46450 |
work_keys_str_mv | AT cruzroaangel accurateandreproducibleinvasivebreastcancerdetectioninwholeslideimagesadeeplearningapproachforquantifyingtumorextent AT gilmorehannah accurateandreproducibleinvasivebreastcancerdetectioninwholeslideimagesadeeplearningapproachforquantifyingtumorextent AT basavanhallyajay accurateandreproducibleinvasivebreastcancerdetectioninwholeslideimagesadeeplearningapproachforquantifyingtumorextent AT feldmanmichael accurateandreproducibleinvasivebreastcancerdetectioninwholeslideimagesadeeplearningapproachforquantifyingtumorextent AT ganesanshridar accurateandreproducibleinvasivebreastcancerdetectioninwholeslideimagesadeeplearningapproachforquantifyingtumorextent AT shihnatalienc accurateandreproducibleinvasivebreastcancerdetectioninwholeslideimagesadeeplearningapproachforquantifyingtumorextent AT tomaszewskijohn accurateandreproducibleinvasivebreastcancerdetectioninwholeslideimagesadeeplearningapproachforquantifyingtumorextent AT gonzalezfabioa accurateandreproducibleinvasivebreastcancerdetectioninwholeslideimagesadeeplearningapproachforquantifyingtumorextent AT madabhushianant accurateandreproducibleinvasivebreastcancerdetectioninwholeslideimagesadeeplearningapproachforquantifyingtumorextent |