skip to main content
10.1145/3631991.3632036acmotherconferencesArticle/Chapter ViewAbstractPublication PageswsseConference Proceedingsconference-collections
research-article

M3C-Polyp: Mixed Momentum Model Committee for Improved Semi-Supervised Learning in Polyp Segmentation

Published: 26 December 2023 Publication History

Abstract

We propose a novel approach for semi-supervised learning (SSL) in polyp segmentation using a Mixed Momentum Model Committee. Our method addresses limited labeled data and uncertainty estimation challenges. The committee M3C consists of K momentum models derived from a teacher model T, enabling effective pseudo-label generation and uncertainty estimation at the pixel level. Experiments on five benchmark datasets, including Kvarsir, CVC-ClinicDB, ETIS-LaribPolypDB, CVC-ColonDB, and CVC-300, show the superiority of our method, achieving an average Dice score of 0.862 compared to the supervised baseline (0.826). Notably, our approach outperforms the supervised method on out-of-domain datasets. The proposed Mixed Momentum Model Committee advances SSL for polyp segmentation, offering improved accuracy and uncertainty estimation. The findings have significant implications for clinical applications, aiding in accurate diagnosis and treatment of colorectal polyps.

References

[1]
Nikita Araslanov and Stefan Roth. 2021. Self-supervised augmentation consistency for adapting semantic segmentation. In Proceedings of the IEEE/CVF CVPR. 15384–15394.
[2]
David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, and Colin A Raffel. 2019. Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems 32 (2019).
[3]
Nguyen Thanh Duc, Nguyen Thi Oanh, Nguyen Thi Thuy, Tran Minh Triet, and Viet Sang Dinh. 2022. Colonformer: An efficient transformer based method for colon polyp segmentation. IEEE Access 10 (2022), 80575–80586.
[4]
Deng-Ping Fan, Ge-Peng Ji, Tao Zhou, Geng Chen, Huazhu Fu, Jianbing Shen, and Ling Shao. 2020. Pranet: Parallel reverse attention network for polyp segmentation. In International conference on medical image computing and computer-assisted intervention. Springer, 263–273.
[5]
Deng-Ping Fan, Ge-Peng Ji, Tao Zhou, Geng Chen, Huazhu Fu, Jianbing Shen, and Ling Shao. 2020. Pranet: Parallel reverse attention network for polyp segmentation. In International conference on medical image computing and computer-assisted intervention. Springer, 263–273.
[6]
Yuqi Fang, Cheng Chen, Yixuan Yuan, and Kai-yu Tong. 2019. Selective feature aggregation network with area-boundary constraints for polyp segmentation. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part I 22. Springer, 302–310.
[7]
Chien-Hsiang Huang, Hung-Yu Wu, and Youn-Long Lin. 2021. Hardnet-mseg: A simple encoder-decoder polyp segmentation neural network that achieves over 0.9 mean dice and 86 fps. arXiv preprint arXiv:2101.07172 (2021).
[8]
Xin Lai, Zhuotao Tian, Li Jiang, Shu Liu, Hengshuang Zhao, Liwei Wang, and Jiaya Jia. 2021. Semi-supervised semantic segmentation with directional context-aware consistency. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1205–1214.
[9]
Yiwen Li, Gratianus Wesley Putra Data, Yunguan Fu, Yipeng Hu, and Victor Adrian Prisacariu. 2021. Few-shot semantic segmentation with self-supervision from pseudo-classes. arXiv preprint arXiv:2110.11742 (2021).
[10]
Xiangde Luo, Jieneng Chen, Tao Song, and Guotai Wang. 2021. Semi-supervised medical image segmentation through dual-task consistency. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. 8801–8809.
[11]
Kristian Miok, Dong Nguyen-Doan, Daniela Zaharie, and Marko Robnik-Šikonja. 2019. Generating data using Monte Carlo dropout. In 2019 IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP). IEEE, 509–515.
[12]
Toan Van Pham, Sang Viet Dinh, Linh Bao Doan, Thanh Tung Nguyen, Quang Hung Nguyen, and Duc Trung Tran. 2022. Improve polyp semi-supervised segmentation with prioritizing the reliability of unlabeled images. In Proceedings of the 11th International Conference on Software and Information Engineering. 35–40.
[13]
Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 234–241.
[14]
Toan Pham Van, Linh Bao Doan, Thanh Tung Nguyen, Duc Trung Tran, Quan Van Nguyen, and Dinh Viet Sang. 2022. Online pseudo labeling for polyp segmentation with momentum networks. In 2022 14th International Conference on Knowledge and Systems Engineering (KSE). IEEE, 1–6.
[15]
Yuchao Wang, Haochen Wang, Yujun Shen, Jingjing Fei, Wei Li, Guoqiang Jin, Liwei Wu, Rui Zhao, and Xinyi Le. 2022. Semi-supervised semantic segmentation using unreliable pseudo-labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4248–4257.
[16]
Jun Wei, Yiwen Hu, Ruimao Zhang, Zhen Li, S Kevin Zhou, and Shuguang Cui. 2021. Shallow attention network for polyp segmentation. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I 24. Springer, 699–708.
[17]
Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, and Yang Gao. 2022. St++: Make self-training work better for semi-supervised semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4268–4277.
[18]
Yunyang Zhang, Zhiqiang Gong, Xiaoyu Zhao, Xiaohu Zheng, and Wen Yao. 2022. Semi-supervised Semantic Segmentation with Uncertainty-Guided Self Cross Supervision. In Proceedings of the Asian Conference on Computer Vision. 4631–4647.
[19]
Xiaoqi Zhao, Lihe Zhang, and Huchuan Lu. 2021. Automatic polyp segmentation via multi-scale subtraction network. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I 24. Springer, 120–130.
[20]
Zongwei Zhou, Md Mahfuzur Rahman Siddiquee, Nima Tajbakhsh, and Jianming Liang. 2019. Unet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE transactions on medical imaging 39, 6 (2019), 1856–1867.

Index Terms

  1. M3C-Polyp: Mixed Momentum Model Committee for Improved Semi-Supervised Learning in Polyp Segmentation

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    WSSE '23: Proceedings of the 2023 5th World Symposium on Software Engineering
    September 2023
    352 pages
    ISBN:9798400708053
    DOI:10.1145/3631991
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 26 December 2023

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Medical Imaging
    2. Mixed Momentum Model Committee
    3. Polyp Segmentation
    4. Pseudo-Labels
    5. Semi-Supervised Learning
    6. Uncertainty Estimation

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    WSSE 2023

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 23
      Total Downloads
    • Downloads (Last 12 months)23
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 26 Jan 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media