Cargando…

Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations

Colorectal cancer (CRC) is one of the most common types of cancer with a high mortality rate. Colonoscopy is the preferred procedure for CRC screening and has proven to be effective in reducing CRC mortality. Thus, a reliable computer-aided polyp detection and classification system can significantly...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Kaidong, Fathan, Mohammad I., Patel, Krushi, Zhang, Tianxiao, Zhong, Cuncong, Bansal, Ajay, Rastogi, Amit, Wang, Jean S., Wang, Guanghui
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8370621/
https://www.ncbi.nlm.nih.gov/pubmed/34403452
http://dx.doi.org/10.1371/journal.pone.0255809
_version_ 1783739485159161856
author Li, Kaidong
Fathan, Mohammad I.
Patel, Krushi
Zhang, Tianxiao
Zhong, Cuncong
Bansal, Ajay
Rastogi, Amit
Wang, Jean S.
Wang, Guanghui
author_facet Li, Kaidong
Fathan, Mohammad I.
Patel, Krushi
Zhang, Tianxiao
Zhong, Cuncong
Bansal, Ajay
Rastogi, Amit
Wang, Jean S.
Wang, Guanghui
author_sort Li, Kaidong
collection PubMed
description Colorectal cancer (CRC) is one of the most common types of cancer with a high mortality rate. Colonoscopy is the preferred procedure for CRC screening and has proven to be effective in reducing CRC mortality. Thus, a reliable computer-aided polyp detection and classification system can significantly increase the effectiveness of colonoscopy. In this paper, we create an endoscopic dataset collected from various sources and annotate the ground truth of polyp location and classification results with the help of experienced gastroenterologists. The dataset can serve as a benchmark platform to train and evaluate the machine learning models for polyp classification. We have also compared the performance of eight state-of-the-art deep learning-based object detection models. The results demonstrate that deep CNN models are promising in CRC screening. This work can serve as a baseline for future research in polyp detection and classification.
format Online
Article
Text
id pubmed-8370621
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-83706212021-08-18 Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations Li, Kaidong Fathan, Mohammad I. Patel, Krushi Zhang, Tianxiao Zhong, Cuncong Bansal, Ajay Rastogi, Amit Wang, Jean S. Wang, Guanghui PLoS One Research Article Colorectal cancer (CRC) is one of the most common types of cancer with a high mortality rate. Colonoscopy is the preferred procedure for CRC screening and has proven to be effective in reducing CRC mortality. Thus, a reliable computer-aided polyp detection and classification system can significantly increase the effectiveness of colonoscopy. In this paper, we create an endoscopic dataset collected from various sources and annotate the ground truth of polyp location and classification results with the help of experienced gastroenterologists. The dataset can serve as a benchmark platform to train and evaluate the machine learning models for polyp classification. We have also compared the performance of eight state-of-the-art deep learning-based object detection models. The results demonstrate that deep CNN models are promising in CRC screening. This work can serve as a baseline for future research in polyp detection and classification. Public Library of Science 2021-08-17 /pmc/articles/PMC8370621/ /pubmed/34403452 http://dx.doi.org/10.1371/journal.pone.0255809 Text en © 2021 Li 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
Li, Kaidong
Fathan, Mohammad I.
Patel, Krushi
Zhang, Tianxiao
Zhong, Cuncong
Bansal, Ajay
Rastogi, Amit
Wang, Jean S.
Wang, Guanghui
Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations
title Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations
title_full Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations
title_fullStr Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations
title_full_unstemmed Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations
title_short Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations
title_sort colonoscopy polyp detection and classification: dataset creation and comparative evaluations
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8370621/
https://www.ncbi.nlm.nih.gov/pubmed/34403452
http://dx.doi.org/10.1371/journal.pone.0255809
work_keys_str_mv AT likaidong colonoscopypolypdetectionandclassificationdatasetcreationandcomparativeevaluations
AT fathanmohammadi colonoscopypolypdetectionandclassificationdatasetcreationandcomparativeevaluations
AT patelkrushi colonoscopypolypdetectionandclassificationdatasetcreationandcomparativeevaluations
AT zhangtianxiao colonoscopypolypdetectionandclassificationdatasetcreationandcomparativeevaluations
AT zhongcuncong colonoscopypolypdetectionandclassificationdatasetcreationandcomparativeevaluations
AT bansalajay colonoscopypolypdetectionandclassificationdatasetcreationandcomparativeevaluations
AT rastogiamit colonoscopypolypdetectionandclassificationdatasetcreationandcomparativeevaluations
AT wangjeans colonoscopypolypdetectionandclassificationdatasetcreationandcomparativeevaluations
AT wangguanghui colonoscopypolypdetectionandclassificationdatasetcreationandcomparativeevaluations