Learning with Geometric Priors in U-Net Variants for Polyp Segmentation

Authors

• Fabian Vazquez, The University of Texas Rio Grande Valley
• Jose A. Nuñez, The University of Texas Rio Grande Valley
• Diego Adame, The University of Texas Rio Grande Valley
• Alissen Moreno, The University of Texas Rio Grande Valley
• Augustin Zhan
• Huimin Li, The University of Texas Rio Grande Valley
• Jinghao Yang, The University of Texas Rio Grande ValleyFollow
• Haoteng Tang, The University of Texas Rio Grande Valley
• Bin Fu, The University of Texas Rio Grande ValleyFollow
• Pengfei Gu, The University of Texas Rio Grande Valley

Document Type

Conference Proceeding

Publication Date

5-20-2026

Abstract

Accurate and robust polyp segmentation is essential for early colorectal cancer detection and for computer-aided diagnosis. While convolutional neural network-, Transformer-, and Mamba-based U-Net variants have achieved strong performance, they still struggle to capture geometric and structural cues, especially in low-contrast or cluttered colonoscopy scenes. To address this challenge, we propose a novel Geometric Prior-guided Module (GPM) that injects explicit geometric priors into U-Net-based architectures for polyp segmentation. Specifically, we fine-tune the Visual Geometry Grounded Transformer (VGGT) on a simulated ColonDepth dataset to estimate depth maps of polyp images tailored to the endoscopic domain. These depth maps are then processed by GPM to encode geometric priors into the encoder's feature maps, where they are further refined using spatial and channel attention mechanisms that emphasize both local spatial and global channel information. GPM is plug-and-play and can be seamlessly integrated into diverse U-Net variants. Extensive experiments on five public polyp segmentation datasets demonstrate consistent gains over three strong baselines. Code and the generated depth maps are available at: https://github.com/fvazqu/GPM-PolypSeg

Comments

Copyright IEEE.

Recommended Citation

Vazquez, Fabian, Jose A. Nuñez, Diego Adame, Alissen Moreno, Augustin Zhan, Huimin Li, Jinghao Yang, Haoteng Tang, Bin Fu, and Pengfei Gu. "Learning with Geometric Priors in U-Net Variants for Polyp Segmentation." In 2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI), pp. 1-5. IEEE, 2026. https://doi.org/10.1109/ISBI61048.2026.11515449

Publication Title

2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)

DOI

https://doi.org/10.1109/ISBI61048.2026.11515449