MPCGNet: A Multiscale Feature Extraction and Progressive Feature Aggregation Network Using Coupling Gates for Polyp Segmentation

TL;DR

MPCGNet is a novel multiscale feature extraction and progressive aggregation network that employs coupling gates to improve polyp segmentation accuracy, especially for small or ambiguous polyps, in colonoscopy images.

Contribution

The paper introduces coupling gates within specialized modules to enhance noise filtering, feature importance selection, and detail restoration in polyp segmentation.

Findings

Outperforms recent networks in mDice scores on ETIS-LaribPolypDB and CVC-ColonDB datasets.

Effectively detects small-sized polyps and clarifies boundaries.

Reduces false negatives in polyp detection.

Abstract

Automatic segmentation methods of polyps is crucial for assisting doctors in colorectal polyp screening and cancer diagnosis. Despite the progress made by existing methods, polyp segmentation faces several challenges: (1) small-sized polyps are prone to being missed during identification, (2) the boundaries between polyps and the surrounding environment are often ambiguous, (3) noise in colonoscopy images, caused by uneven lighting and other factors, affects segmentation results. To address these challenges, this paper introduces coupling gates as components in specific modules to filter noise and perform feature importance selection. Three modules are proposed: the coupling gates multiscale feature extraction (CGMFE) module, which effectively extracts local features and suppresses noise; the windows cross attention (WCAD) decoder module, which restores details after capturing the precise location of polyps; and the decoder feature aggregation (DFA) module, which progressively aggregates features, further extracts them, and performs feature importance selection to reduce the loss of small-sized polyps. Experimental results demonstrate that MPCGNet outperforms recent networks, with mDice scores 2.20% and 0.68% higher than the second-best network on the ETIS-LaribPolypDB and CVC-ColonDB datasets, respectively.