Cargando…
A fast and effective detection framework for whole-slide histopathology image analysis
Pathologists generally pan, focus, zoom and scan tissue biopsies either under microscopes or on digital images for diagnosis. With the rapid development of whole-slide digital scanners for histopathology, computer-assisted digital pathology image analysis has attracted increasing clinical attention....
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8115773/ https://www.ncbi.nlm.nih.gov/pubmed/33979398 http://dx.doi.org/10.1371/journal.pone.0251521 |
_version_ | 1783691256687230976 |
---|---|
author | Ruan, Jun Zhu, Zhikui Wu, Chenchen Ye, Guanglu Zhou, Jingfan Yue, Junqiu |
author_facet | Ruan, Jun Zhu, Zhikui Wu, Chenchen Ye, Guanglu Zhou, Jingfan Yue, Junqiu |
author_sort | Ruan, Jun |
collection | PubMed |
description | Pathologists generally pan, focus, zoom and scan tissue biopsies either under microscopes or on digital images for diagnosis. With the rapid development of whole-slide digital scanners for histopathology, computer-assisted digital pathology image analysis has attracted increasing clinical attention. Thus, the working style of pathologists is also beginning to change. Computer-assisted image analysis systems have been developed to help pathologists perform basic examinations. This paper presents a novel lightweight detection framework for automatic tumor detection in whole-slide histopathology images. We develop the Double Magnification Combination (DMC) classifier, which is a modified DenseNet-40 to make patch-level predictions with only 0.3 million parameters. To improve the detection performance of multiple instances, we propose an improved adaptive sampling method with superpixel segmentation and introduce a new heuristic factor, local sampling density, as the convergence condition of iterations. In postprocessing, we use a CNN model with 4 convolutional layers to regulate the patch-level predictions based on the predictions of adjacent sampling points and use linear interpolation to generate a tumor probability heatmap. The entire framework was trained and validated using the dataset from the Camelyon16 Grand Challenge and Hubei Cancer Hospital. In our experiments, the average AUC was 0.95 in the test set for pixel-level detection. |
format | Online Article Text |
id | pubmed-8115773 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-81157732021-05-24 A fast and effective detection framework for whole-slide histopathology image analysis Ruan, Jun Zhu, Zhikui Wu, Chenchen Ye, Guanglu Zhou, Jingfan Yue, Junqiu PLoS One Research Article Pathologists generally pan, focus, zoom and scan tissue biopsies either under microscopes or on digital images for diagnosis. With the rapid development of whole-slide digital scanners for histopathology, computer-assisted digital pathology image analysis has attracted increasing clinical attention. Thus, the working style of pathologists is also beginning to change. Computer-assisted image analysis systems have been developed to help pathologists perform basic examinations. This paper presents a novel lightweight detection framework for automatic tumor detection in whole-slide histopathology images. We develop the Double Magnification Combination (DMC) classifier, which is a modified DenseNet-40 to make patch-level predictions with only 0.3 million parameters. To improve the detection performance of multiple instances, we propose an improved adaptive sampling method with superpixel segmentation and introduce a new heuristic factor, local sampling density, as the convergence condition of iterations. In postprocessing, we use a CNN model with 4 convolutional layers to regulate the patch-level predictions based on the predictions of adjacent sampling points and use linear interpolation to generate a tumor probability heatmap. The entire framework was trained and validated using the dataset from the Camelyon16 Grand Challenge and Hubei Cancer Hospital. In our experiments, the average AUC was 0.95 in the test set for pixel-level detection. Public Library of Science 2021-05-12 /pmc/articles/PMC8115773/ /pubmed/33979398 http://dx.doi.org/10.1371/journal.pone.0251521 Text en © 2021 Ruan et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Ruan, Jun Zhu, Zhikui Wu, Chenchen Ye, Guanglu Zhou, Jingfan Yue, Junqiu A fast and effective detection framework for whole-slide histopathology image analysis |
title | A fast and effective detection framework for whole-slide histopathology image analysis |
title_full | A fast and effective detection framework for whole-slide histopathology image analysis |
title_fullStr | A fast and effective detection framework for whole-slide histopathology image analysis |
title_full_unstemmed | A fast and effective detection framework for whole-slide histopathology image analysis |
title_short | A fast and effective detection framework for whole-slide histopathology image analysis |
title_sort | fast and effective detection framework for whole-slide histopathology image analysis |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8115773/ https://www.ncbi.nlm.nih.gov/pubmed/33979398 http://dx.doi.org/10.1371/journal.pone.0251521 |
work_keys_str_mv | AT ruanjun afastandeffectivedetectionframeworkforwholeslidehistopathologyimageanalysis AT zhuzhikui afastandeffectivedetectionframeworkforwholeslidehistopathologyimageanalysis AT wuchenchen afastandeffectivedetectionframeworkforwholeslidehistopathologyimageanalysis AT yeguanglu afastandeffectivedetectionframeworkforwholeslidehistopathologyimageanalysis AT zhoujingfan afastandeffectivedetectionframeworkforwholeslidehistopathologyimageanalysis AT yuejunqiu afastandeffectivedetectionframeworkforwholeslidehistopathologyimageanalysis AT ruanjun fastandeffectivedetectionframeworkforwholeslidehistopathologyimageanalysis AT zhuzhikui fastandeffectivedetectionframeworkforwholeslidehistopathologyimageanalysis AT wuchenchen fastandeffectivedetectionframeworkforwholeslidehistopathologyimageanalysis AT yeguanglu fastandeffectivedetectionframeworkforwholeslidehistopathologyimageanalysis AT zhoujingfan fastandeffectivedetectionframeworkforwholeslidehistopathologyimageanalysis AT yuejunqiu fastandeffectivedetectionframeworkforwholeslidehistopathologyimageanalysis |