Theses and Dissertations
Date of Award
5-1-2026
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Computer Science
First Advisor
Pengfei Gu
Second Advisor
Bin Fu
Third Advisor
Haoteng Tang
Abstract
Medical image segmentation is a fundamental task in computer-aided diagnosis because it enables precise delineation of anatomical structures and pathological regions from clinical images. While convolutional neural networks and Transformer-based models have achieved strong performance on many medical segmentation benchmarks, CNNs struggle to model long-range dependencies and Transformers often incur high computational complexity for high-resolution medical images. Recently, state space models have emerged as an efficient alternative for dense prediction tasks due to their ability to capture long-range dependencies with linear complexity. However, existing Mamba-based segmentation models still rely on pixel-wise raster scanning that disrupts spatial locality and use simple summation to fuse directional features.
This thesis proposes Patch-MoE Mamba, a patch-ordered mixture-of-experts state space architecture that preserves spatial locality through hierarchical patch-based scanning and adaptively fuses directional representations using an MoE-based fusion module. Experiments across seven medical segmentation benchmarks demonstrate strong and consistent performance.
Recommended Citation
Adame, D. (2026). Accurate Polyp Segmentation With Visual Mamba [Master's thesis, The University of Texas Rio Grande Valley]. ScholarWorks @ UTRGV. https://scholarworks.utrgv.edu/etd/1960
Comments
Copyright 2026 Diego Adame. All Rights Reserved. https://proquest.com/docview/3371493408