Abstract
Colonoscopy is acknowledged as the foremost technique for detecting polyps and facilitating early screening and prevention of colorectal cancer. In clinical settings, the segmentation of polyps from colonoscopy images holds paramount importance as it furnishes critical diagnostic and surgical information. Nevertheless, the precise segmentation of colon polyp images is still a challenging task owing to the varied sizes and morphological features of colon polyps and the indistinct boundary between polyps and mucosa. In this study, we present a novel network architecture named ECTransNet to address the challenges in polyp segmentation. Specifically, we propose an edge complementary module that effectively fuses the differences between features with multiple resolutions. This enables the network to exchange features across different levels and results in a substantial improvement in the edge fineness of the polyp segmentation. Additionally, we utilize a feature aggregation decoder that leverages residual blocks to adaptively fuse high-order to low-order features. This strategy restores local edges in low-order features while preserving the spatial information of targets in high-order features, ultimately enhancing the segmentation accuracy. According to extensive experiments conducted on ECTransNet, the results demonstrate that this method outperforms most state-of-the-art approaches on five publicly available datasets. Specifically, our method achieved mDice scores of 0.901 and 0.923 on the Kvasir-SEG and CVC-ClinicDB datasets, respectively. On the Endoscene, CVC-ColonDB, and ETIS datasets, we obtained mDice scores of 0.907, 0.766, and 0.728, respectively.