2025/11/03 by Yuanmei Zhang, Wang, Ziyi, Dorna Esrafilzadeh +6
Computer Science · Medicine · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Block (permutation group theory) #COVID-19 diagnosis using AI #Code (set theory) #Colorectal Cancer Screening and Detection #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image (mathematics) #Image segmentation #Inference #Pattern recognition (psychology) #Segmentation
paper · pdf · doi:10.48550/arxiv.2511.01143
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/11/03 · openalex created_date 2025/11/06 · openalex updated_date 2026/07/28
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 light-weighted attention-based segmentation network that combines depthwise-separable dilated convolutions with a single-path, parameter-shared channel-spatial attention block to 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.