EPPS: Advanced Polyp Segmentation via Edge Information Injection and Selective Feature Decoupling

TL;DR

EPPS is a novel deep learning model that enhances polyp segmentation in colonoscopy images by injecting edge information and selectively decoupling features to improve accuracy and robustness.

Contribution

The paper introduces EPPS, which combines edge extraction, edge information injection, and feature decoupling to address ambiguous edges and irrelevant features in polyp segmentation.

Findings

EPPS outperforms state-of-the-art methods on three benchmarks.

Edge information injection improves segmentation accuracy.

Selective feature decoupling reduces noise influence.

Abstract

Accurate segmentation of polyps in colonoscopy images is essential for early-stage diagnosis and management of colorectal cancer. Despite advancements in deep learning for polyp segmentation, enduring limitations persist. The edges of polyps are typically ambiguous, making them difficult to discern from the background, and the model performance is often compromised by the influence of irrelevant or unimportant features. To alleviate these challenges, we propose a novel model named Edge-Prioritized Polyp Segmentation (EPPS). Specifically, we incorporate an Edge Mapping Engine (EME) aimed at accurately extracting the edges of polyps. Subsequently, an Edge Information Injector (EII) is devised to augment the mask prediction by injecting the captured edge information into Decoder blocks. Furthermore, we introduce a component called Selective Feature Decoupler (SFD) to suppress the influence of noise and extraneous features on the model. Extensive experiments on 3 widely used polyp segmentation benchmarks demonstrate the superior performance of our method compared with other state-of-the-art approaches.