Polyp segmentation with consistency training and continuous update of pseudo-labelopen access
- Authors
- Park, Hyun-Cheol; Poudel, Sahadev; Ghimire, Raman; Lee, Sang-Woong
- Issue Date
- Aug-2022
- Publisher
- NATURE PORTFOLIO
- Citation
- SCIENTIFIC REPORTS, v.12, no.1
- Journal Title
- SCIENTIFIC REPORTS
- Volume
- 12
- Number
- 1
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/85658
- DOI
- 10.1038/s41598-022-17843-3
- ISSN
- 2045-2322
- Abstract
- Polyp segmentation has accomplished massive triumph over the years in the field of supervised learning. However, obtaining a vast number of labeled datasets is commonly challenging in the medical domain. To solve this problem, we employ semi-supervised methods and suitably take advantage of unlabeled data to improve the performance of polyp image segmentation. First, we propose an encoder-decoder-based method well suited for the polyp with varying shape, size, and scales. Second, we utilize the teacher-student concept of training the model, where the teacher model is the student model's exponential average. Third, to leverage the unlabeled dataset, we enforce a consistency technique and force the teacher model to generate a similar output on the different perturbed versions of the given input. Finally, we propose a method that upgrades the traditional pseudo-label method by learning the model with continuous update of pseudo-label. We show the efficacy of our proposed method on different polyp datasets, and hence attaining better results in semi-supervised settings. Extensive experiments demonstrate that our proposed method can propagate the unlabeled dataset's essential information to improve performance.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - IT융합대학 > 소프트웨어학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/85658)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.