Cargando…
Automatic detection and segmentation of adenomatous colorectal polyps during colonoscopy using Mask R-CNN
Colorectal cancer (CRC) is one of the main alimentary tract system malignancies affecting people worldwide. Adenomatous polyps are precursors of CRC, and therefore, preventing the development of these lesions may also prevent subsequent malignancy. However, the adenoma detection rate (ADR), a measur...
Autores principales: | , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
De Gruyter
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7968546/ https://www.ncbi.nlm.nih.gov/pubmed/33817247 http://dx.doi.org/10.1515/biol-2020-0055 |
_version_ | 1783666082381299712 |
---|---|
author | Meng, Jie Xue, Linyan Chang, Ying Zhang, Jianguang Chang, Shilong Liu, Kun Liu, Shuang Wang, Bangmao Yang, Kun |
author_facet | Meng, Jie Xue, Linyan Chang, Ying Zhang, Jianguang Chang, Shilong Liu, Kun Liu, Shuang Wang, Bangmao Yang, Kun |
author_sort | Meng, Jie |
collection | PubMed |
description | Colorectal cancer (CRC) is one of the main alimentary tract system malignancies affecting people worldwide. Adenomatous polyps are precursors of CRC, and therefore, preventing the development of these lesions may also prevent subsequent malignancy. However, the adenoma detection rate (ADR), a measure of the ability of a colonoscopist to identify and remove precancerous colorectal polyps, varies significantly among endoscopists. Here, we attempt to use a convolutional neural network (CNN) to generate a unique computer-aided diagnosis (CAD) system by exploring in detail the multiple-scale performance of deep neural networks. We applied this system to 3,375 hand-labeled images from the screening colonoscopies of 1,197 patients; of whom, 3,045 were assigned to the training dataset and 330 to the testing dataset. The images were diagnosed simply as either an adenomatous or non-adenomatous polyp. When applied to the testing dataset, our CNN-CAD system achieved a mean average precision of 89.5%. We conclude that the proposed framework could increase the ADR and decrease the incidence of interval CRCs, although further validation through large multicenter trials is required. |
format | Online Article Text |
id | pubmed-7968546 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | De Gruyter |
record_format | MEDLINE/PubMed |
spelling | pubmed-79685462021-04-01 Automatic detection and segmentation of adenomatous colorectal polyps during colonoscopy using Mask R-CNN Meng, Jie Xue, Linyan Chang, Ying Zhang, Jianguang Chang, Shilong Liu, Kun Liu, Shuang Wang, Bangmao Yang, Kun Open Life Sci Topical Issue on Computing and Artificial Techniques for Life Science Applications Colorectal cancer (CRC) is one of the main alimentary tract system malignancies affecting people worldwide. Adenomatous polyps are precursors of CRC, and therefore, preventing the development of these lesions may also prevent subsequent malignancy. However, the adenoma detection rate (ADR), a measure of the ability of a colonoscopist to identify and remove precancerous colorectal polyps, varies significantly among endoscopists. Here, we attempt to use a convolutional neural network (CNN) to generate a unique computer-aided diagnosis (CAD) system by exploring in detail the multiple-scale performance of deep neural networks. We applied this system to 3,375 hand-labeled images from the screening colonoscopies of 1,197 patients; of whom, 3,045 were assigned to the training dataset and 330 to the testing dataset. The images were diagnosed simply as either an adenomatous or non-adenomatous polyp. When applied to the testing dataset, our CNN-CAD system achieved a mean average precision of 89.5%. We conclude that the proposed framework could increase the ADR and decrease the incidence of interval CRCs, although further validation through large multicenter trials is required. De Gruyter 2020-08-14 /pmc/articles/PMC7968546/ /pubmed/33817247 http://dx.doi.org/10.1515/biol-2020-0055 Text en © 2020 Jie Meng et al., published by De Gruyter http://creativecommons.org/licenses/by/4.0 This work is licensed under the Creative Commons Attribution 4.0 International License. |
spellingShingle | Topical Issue on Computing and Artificial Techniques for Life Science Applications Meng, Jie Xue, Linyan Chang, Ying Zhang, Jianguang Chang, Shilong Liu, Kun Liu, Shuang Wang, Bangmao Yang, Kun Automatic detection and segmentation of adenomatous colorectal polyps during colonoscopy using Mask R-CNN |
title | Automatic detection and segmentation of adenomatous colorectal polyps during colonoscopy using Mask R-CNN |
title_full | Automatic detection and segmentation of adenomatous colorectal polyps during colonoscopy using Mask R-CNN |
title_fullStr | Automatic detection and segmentation of adenomatous colorectal polyps during colonoscopy using Mask R-CNN |
title_full_unstemmed | Automatic detection and segmentation of adenomatous colorectal polyps during colonoscopy using Mask R-CNN |
title_short | Automatic detection and segmentation of adenomatous colorectal polyps during colonoscopy using Mask R-CNN |
title_sort | automatic detection and segmentation of adenomatous colorectal polyps during colonoscopy using mask r-cnn |
topic | Topical Issue on Computing and Artificial Techniques for Life Science Applications |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7968546/ https://www.ncbi.nlm.nih.gov/pubmed/33817247 http://dx.doi.org/10.1515/biol-2020-0055 |
work_keys_str_mv | AT mengjie automaticdetectionandsegmentationofadenomatouscolorectalpolypsduringcolonoscopyusingmaskrcnn AT xuelinyan automaticdetectionandsegmentationofadenomatouscolorectalpolypsduringcolonoscopyusingmaskrcnn AT changying automaticdetectionandsegmentationofadenomatouscolorectalpolypsduringcolonoscopyusingmaskrcnn AT zhangjianguang automaticdetectionandsegmentationofadenomatouscolorectalpolypsduringcolonoscopyusingmaskrcnn AT changshilong automaticdetectionandsegmentationofadenomatouscolorectalpolypsduringcolonoscopyusingmaskrcnn AT liukun automaticdetectionandsegmentationofadenomatouscolorectalpolypsduringcolonoscopyusingmaskrcnn AT liushuang automaticdetectionandsegmentationofadenomatouscolorectalpolypsduringcolonoscopyusingmaskrcnn AT wangbangmao automaticdetectionandsegmentationofadenomatouscolorectalpolypsduringcolonoscopyusingmaskrcnn AT yangkun automaticdetectionandsegmentationofadenomatouscolorectalpolypsduringcolonoscopyusingmaskrcnn |