Polyp Segmentation Using Wavelet-Based Cross-Band Integration for Enhanced Boundary Representation

2026-03-03

AI Summary

Colorectal polyp segmentation is often hindered by low mucosal contrast, uneven illumination, and color similarity, leading to ambiguous boundaries. This work presents the first observation that grayscale images preserve superior boundary contrast across all frequency bands in the wavelet domain compared to RGB counterparts. Building on this insight, the authors propose a novel dual-stream architecture that jointly processes grayscale and RGB inputs, enabling mutual enhancement through cross-band feature fusion and band consistency constraints. The resulting method significantly improves boundary accuracy and structural coherence, consistently outperforming state-of-the-art approaches across four benchmark datasets and demonstrating leading segmentation performance and robustness.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Accurate polyp segmentation is essential for early colorectal cancer detection, yet achieving reliable boundary localization remains challenging due to low mucosal contrast, uneven illumination, and color similarity between polyps and surrounding tissue. Conventional methods relying solely on RGB information often struggle to delineate precise boundaries due to weak contrast and ambiguous structures between polyps and surrounding mucosa. To establish a quantitative foundation for this limitation, we analyzed polyp-background contrast in the wavelet domain, revealing that grayscale representations consistently preserve higher boundary contrast than RGB images across all frequency bands. This finding suggests that boundary cues are more distinctly represented in the grayscale domain than in the color domain. Motivated by this finding, we propose a segmentation model that integrates grayscale and RGB representations through complementary frequency-consistent interaction, enhancing boundary precision while preserving structural coherence. Extensive experiments on four benchmark datasets demonstrate that the proposed approach achieves superior boundary precision and robustness compared to conventional models.

Problem

• polyp segmentation
• boundary localization
• low contrast
• color similarity
• uneven illumination

Innovation

• Wavelet-based cross-band integration
• Polyp segmentation
• Boundary representation
• Grayscale-RGB fusion
• Frequency-consistent interaction