MicroAUNet：结合知识蒸馏的边界增强多尺度融合用于结肠镜息肉图像分割
MicroAUNet: Boundary-Enhanced Multi-scale Fusion with Knowledge Distillation for Colonoscopy Polyp Image Segmentation
- Shanghai Jiao Tong University（上海交通大学）
- University of New South Wales（新南威尔士大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文针对结肠镜息肉分割模型边界模糊或复杂度高的问题，提出轻量型MicroAUNet，结合深度可分离空洞卷积与通道-空间注意力块，辅以渐进式两阶段知识蒸馏，在低复杂度下实现先进分割准确率，适用于实时临床应用。
AI中文摘要：
早期准确分割结肠息肉对降低结肠癌死亡率至关重要，已被学术界和工业界广泛研究。但当前基于深度学习的息肉分割模型要么因分割输出中息肉边界模糊影响临床决策，要么依赖高计算复杂度的庞大架构，导致实时结肠内镜应用的推理速度不足。为解决该问题，本文提出MicroAUNet，一种基于注意力的轻量型分割网络，其将深度可分离空洞卷积与单路径参数共享的通道-空间注意力块结合，以有效增强多尺度边界特征。在此基础上，引入渐进式两阶段知识蒸馏方案，从高容量教师模型中迁移语义和边界线索。在基准数据集上的大量实验表明，该模型在极低模型复杂度下达到了先进的准确率，说明MicroAUNet适用于实时临床息肉分割，代码已公开。
英文摘要：
Early and accurate segmentation of colorectal polyps is critical for reducing colorectal cancer mortality, which has been extensively explored by academia and industry. However, current deep learning-based polyp segmentation models either compromise clinical decision-making by providing ambiguous polyp margins in segmentation outputs or rely on heavy architectures with high computational complexity, resulting in insufficient inference speeds for real-time colorectal endoscopic applications. To address this problem, we propose MicroAUNet, a lightweight attention-based segmentation network, which synergistically combines depthwise-separable dilated convolutions with a single-path, parameter-shared channel-spatial attention block to effectively strengthen multi-scale boundary features. On the basis of it, a progressive two-stage knowledge-distillation scheme is introduced to transfer semantic and boundary cues from a high-capacity teacher. Extensive experiments on benchmarks also demonstrate the state-of-the-art accuracy under extremely low model complexity, indicating that MicroAUNet is suitable for real-time clinical polyp segmentation. The code is publicly available at https://github.com/JeremyXSC/MicroAUNet.
