MSEANet: Multi-Scale Selective Edge Aware Network for Polyp Segmentation

Abstract

The colonoscopy procedure heavily relies on the operator’s expertise, underscoring the importance of automated polyp segmentation techniques in enhancing the efficiency and accuracy of colorectal cancer diagnosis. Nevertheless, achieving precise segmentation remains a significant challenge due to the high visual similarity between polyps and their backgrounds, blurred boundaries, and complex localization. To address these challenges, a Multi-scale Selective Edge-Aware Network has been proposed to facilitate polyp segmentation. The model consists of three key components: (1) an Edge Feature Extractor (EFE) that captures polyp edge features with precision during the initial encoding phase, (2) the Cross-layer Context Fusion (CCF) block designed to extract and integrate multi-scale contextual information from diverse receptive fields, and (3) the Selective Edge Aware (SEA) module that enhances sensitivity to high-frequency edge details during the decoding phase, thereby improving edge preservation and segmentation accuracy. The effectiveness of our model has been rigorously validated on the Kvasir-SEG, Kvasir-Sessile, and BKAI datasets, achieving mean Dice scores of 91.92%, 82.10%, and 92.24%, respectively, on the test sets.

Keywords

• polyp segmentation
• context fusion
• edge aware
• high-frequency information
• deep learning