文献类型：期刊文献

英文题名：MBDA-Net: Multi-source boundary-aware prototype alignment domain adaptation for polyp segmentation

作者：Yan, Jiawei[1];Zhu, Hongqing[1];Hou, Tong[1];Chen, Ning[1];Lu, Weiping[2];Wang, Ying[3];Huang, Bingcang[2]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Gongli Hosp Shanghai Pudong New Area, Dept Radiol, Shanghai 200135, Peoples R China;[3]Gongli Hosp Shanghai Pudong New Area, Key Lab Artificial Intelligence AI Based Managemen, Sino French Cooperat Cent Lab, Shanghai Hlth Commiss, Shanghai 200135, Peoples R China

年份：2024

卷号：96

外文期刊名：BIOMEDICAL SIGNAL PROCESSING AND CONTROL

收录：;EI(收录号：20243016756410);WOS:【SCI-EXPANDED(收录号:WOS:001278593900001)】；

基金：The authors would like to thank the anonymous reviewers and the associate editor for their insightful comments that significantly improved the quality of this paper. This work was supported by the National Nature Science Foundation of China under Grant 61872143, 82372029, 61771196. Discipline Construction of Pudong New Area Health Commission, China (PWGw2020-01, PWZxk2022-03) . Joint Re-search Project of Pudong New Area Health and Family Planning Com-mission, China (PW2021D-14) . Shanghai Pudong New Area Health Commission, China (PW2022A-31) .

语种：英文

外文关键词：Polyp segmentation; Multi-source domain adaptation; Prototype alignment; Boundary-aware; Transformer

摘要：Accurate segmentation of polyps in colonoscopy images is important for the prevention and treatment of colorectal cancer. However, samples collected from different centers often possess diverse distributions, leading to poor generalization when a segmentation model trained in one center is directly employed in another. This paper proposes a multi-source boundary-aware prototype alignment domain adaptation network (MBDA-Net) to improve the performance of cross-center colonoscopy image segmentation. Specifically, we first design an image translation (IT) module based on the discrete cosine transform (DCT) to reduce the distribution gap between source and target domains by translating source domain styles into target domain styles. Then we propose a mutual perception prototype alignment (MPPA) module containing prototype inference, prototype interaction and adaptive mutual feature fusion. By learning relationships between prototypes and features among multiple domains, one can obtain mutual perception features that fuse prototype information from multiple domains. In order to fully exploit the supervised information of the source domains and optimize the prediction boundaries, we develop a boundary-aware learning (BAL) module to align the boundaries of the source domain predictions and ground truths. Moreover, to mitigate the foreground-background imbalance present in small-sized polyp images and reduce the biased predictions of the model, this study proposes a double normalization strategy (DNS) during the inference stage to improve the detection rate of small polyps. Experimental results on three challenging public datasets show that the proposed MBDA-Net outperforms existing methods on cross-center colonoscopy image segmentation, achieving state-of-the-art performance.