MAF-Net: Multi-branch Anchor-Free Detector for Polyp Localization and Classification in Colonoscopy

Xinzi Sun, Dechun Wang, Qilei Chen, Jing Ni, Shuijiao Chen, Xiaowei Liu, Yu Cao, Benyuan Liu
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:1162-1172, 2022.

Abstract

Colorectal polyps are abnormal tissues growing on the intima of the colon or rectum with a high risk of developing into colorectal cancer, the third leading cause of cancer death worldwide. The most common types of colorectal polyps include inflammatory, hyperplastic, and adenomatous polyps. Adenomatous polyps are the most dangerous type of polyp with the potential to become cancerous. Therefore, the prevention of colorectal cancer heavily depends on the identification and removal of adenomatous polyps. In this paper, we propose a novel framework to assist physicians to localize, identify, and remove adenomatous polyps in colonoscopy. The framework consists of an anchor-free polyp detection branch for detecting and localizing polyps and a classification branch for global feature extraction and pathology prediction. Furthermore, we propose a foreground attention module to generate local features from the foreground subnet in the detection branch, which are combined with the global feature in the classification branch to enhance the pathology prediction performance. We collect a dataset that contains 6,059 images with 6,827 object-level annotations. This dataset is the first large-scale polyp pathology dataset with both object segmentation annotations and pathology labels. Experiment results show that our proposed framework outperforms traditional CNN-based classifiers on polyp pathology classification and anchor-based detectors on polyp detection and localization.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-sun22a, title = {MAF-Net: Multi-branch Anchor-Free Detector for Polyp Localization and Classification in Colonoscopy}, author = {Sun, Xinzi and Wang, Dechun and Chen, Qilei and Ni, Jing and Chen, Shuijiao and Liu, Xiaowei and Cao, Yu and Liu, Benyuan}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {1162--1172}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/sun22a/sun22a.pdf}, url = {https://proceedings.mlr.press/v172/sun22a.html}, abstract = {Colorectal polyps are abnormal tissues growing on the intima of the colon or rectum with a high risk of developing into colorectal cancer, the third leading cause of cancer death worldwide. The most common types of colorectal polyps include inflammatory, hyperplastic, and adenomatous polyps. Adenomatous polyps are the most dangerous type of polyp with the potential to become cancerous. Therefore, the prevention of colorectal cancer heavily depends on the identification and removal of adenomatous polyps. In this paper, we propose a novel framework to assist physicians to localize, identify, and remove adenomatous polyps in colonoscopy. The framework consists of an anchor-free polyp detection branch for detecting and localizing polyps and a classification branch for global feature extraction and pathology prediction. Furthermore, we propose a foreground attention module to generate local features from the foreground subnet in the detection branch, which are combined with the global feature in the classification branch to enhance the pathology prediction performance. We collect a dataset that contains 6,059 images with 6,827 object-level annotations. This dataset is the first large-scale polyp pathology dataset with both object segmentation annotations and pathology labels. Experiment results show that our proposed framework outperforms traditional CNN-based classifiers on polyp pathology classification and anchor-based detectors on polyp detection and localization.} }
Endnote
%0 Conference Paper %T MAF-Net: Multi-branch Anchor-Free Detector for Polyp Localization and Classification in Colonoscopy %A Xinzi Sun %A Dechun Wang %A Qilei Chen %A Jing Ni %A Shuijiao Chen %A Xiaowei Liu %A Yu Cao %A Benyuan Liu %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-sun22a %I PMLR %P 1162--1172 %U https://proceedings.mlr.press/v172/sun22a.html %V 172 %X Colorectal polyps are abnormal tissues growing on the intima of the colon or rectum with a high risk of developing into colorectal cancer, the third leading cause of cancer death worldwide. The most common types of colorectal polyps include inflammatory, hyperplastic, and adenomatous polyps. Adenomatous polyps are the most dangerous type of polyp with the potential to become cancerous. Therefore, the prevention of colorectal cancer heavily depends on the identification and removal of adenomatous polyps. In this paper, we propose a novel framework to assist physicians to localize, identify, and remove adenomatous polyps in colonoscopy. The framework consists of an anchor-free polyp detection branch for detecting and localizing polyps and a classification branch for global feature extraction and pathology prediction. Furthermore, we propose a foreground attention module to generate local features from the foreground subnet in the detection branch, which are combined with the global feature in the classification branch to enhance the pathology prediction performance. We collect a dataset that contains 6,059 images with 6,827 object-level annotations. This dataset is the first large-scale polyp pathology dataset with both object segmentation annotations and pathology labels. Experiment results show that our proposed framework outperforms traditional CNN-based classifiers on polyp pathology classification and anchor-based detectors on polyp detection and localization.
APA
Sun, X., Wang, D., Chen, Q., Ni, J., Chen, S., Liu, X., Cao, Y. & Liu, B.. (2022). MAF-Net: Multi-branch Anchor-Free Detector for Polyp Localization and Classification in Colonoscopy. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:1162-1172 Available from https://proceedings.mlr.press/v172/sun22a.html.

Related Material