ASGNet: Adaptive Spectrum Guidance Network for Automatic Polyp Segmentation

2026-04-16

AI Summary

This work addresses the challenge of polyp segmentation in colonoscopy images, where diverse morphologies, complex backgrounds, and frequent occlusions hinder accurate delineation. Existing methods often rely on local spatial cues, limiting their ability to capture complete polyp structures. To overcome this, we propose ASGNet, which introduces an adaptive spectral guidance mechanism that effectively integrates global spectral features with spatial information. The architecture incorporates a spectral-guided non-local perception module, a multi-source semantic extractor, and a dense cross-layer interaction decoder. By transcending conventional reliance on local correlations, ASGNet significantly enhances boundary precision and structural completeness. Extensive experiments demonstrate its superiority over 21 state-of-the-art methods across five benchmark datasets, with both quantitative metrics and qualitative results confirming its effectiveness.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Local Search

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Early identification and removal of polyps can reduce the risk of developing colorectal cancer. However, the diverse morphologies, complex backgrounds and often concealed nature of polyps make polyp segmentation in colonoscopy images highly challenging. Despite the promising performance of existing deep learning-based polyp segmentation methods, their perceptual capabilities remain biased toward local regions, mainly because of the strong spatial correlations between neighboring pixels in the spatial domain. This limitation makes it difficult to capture the complete polyp structures, ultimately leading to sub-optimal segmentation results. In this paper, we propose a novel adaptive spectrum guidance network, called ASGNet, which addresses the limitations of spatial perception by integrating spectral features with global attributes. Specifically, we first design a spectrum-guided non-local perception module that jointly aggregates local and global information, therefore enhancing the discriminability of polyp structures, and refining their boundaries. Moreover, we introduce a multi-source semantic extractor that integrates rich high-level semantic information to assist in the preliminary localization of polyps. Furthermore, we construct a dense cross-layer interaction decoder that effectively integrates diverse information from different layers and strengthens it to generate high-quality representations for accurate polyp segmentation. Extensive quantitative and qualitative results demonstrate the superiority of our ASGNet approach over 21 state-of-the-art methods across five widely-used polyp segmentation benchmarks. The code will be publicly available at: https://github.com/CSYSI/ASGNet.

Problem

• polyp segmentation
• colonoscopy images
• spatial perception
• global attributes
• morphological diversity

Innovation

• spectrum-guided non-local perception
• multi-source semantic extractor
• dense cross-layer interaction decoder
• polyp segmentation
• global spectral features