Mamba Guided Boundary Prior Matters: A New Perspective for Generalized Polyp Segmentation

2025-07-02

AI Summary

Colonoscopy polyp segmentation remains challenging due to highly variable morphologies, ambiguous boundaries, and low contrast with surrounding tissues; existing CNN- and Transformer-based methods suffer from limited boundary awareness and poor generalizability. To address these issues, we propose a Mamba-enhanced segmentation framework featuring: (i) a Mamba-guided boundary prior mechanism and a novel 1D–2D Mamba module to explicitly model boundary structures; (ii) boundary distillation to strengthen edge feature learning; and (iii) synergistic integration of Segment Anything Model (SAM) with CNN–Transformer backbones, leveraging Mamba’s efficiency in capturing long-range dependencies. Evaluated on five public benchmarks, our method achieves state-of-the-art performance—particularly improving segmentation accuracy and robustness for polyps with indistinct boundaries—while demonstrating strong clinical applicability.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Polyp segmentation in colonoscopy images is crucial for early detection and diagnosis of colorectal cancer. However, this task remains a significant challenge due to the substantial variations in polyp shape, size, and color, as well as the high similarity between polyps and surrounding tissues, often compounded by indistinct boundaries. While existing encoder-decoder CNN and transformer-based approaches have shown promising results, they struggle with stable segmentation performance on polyps with weak or blurry boundaries. These methods exhibit limited abilities to distinguish between polyps and non-polyps and capture essential boundary cues. Moreover, their generalizability still falls short of meeting the demands of real-time clinical applications. To address these limitations, we propose SAM-MaGuP, a groundbreaking approach for robust polyp segmentation. By incorporating a boundary distillation module and a 1D-2D Mamba adapter within the Segment Anything Model (SAM), SAM-MaGuP excels at resolving weak boundary challenges and amplifies feature learning through enriched global contextual interactions. Extensive evaluations across five diverse datasets reveal that SAM-MaGuP outperforms state-of-the-art methods, achieving unmatched segmentation accuracy and robustness. Our key innovations, a Mamba-guided boundary prior and a 1D-2D Mamba block, set a new benchmark in the field, pushing the boundaries of polyp segmentation to new heights.

Problem

• Polyp segmentation challenges due to shape, size, and color variations
• Existing methods struggle with weak or blurry polyp boundaries
• Limited generalizability for real-time clinical polyp segmentation applications

Innovation

• Boundary distillation module enhances weak edges
• 1D-2D Mamba adapter boosts contextual learning
• SAM-MaGuP integrates Mamba-guided boundary prior