most citedLearning with Geometric Priors in U-Net Variants for Polyp Segmentation

1 citations · 1 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV20261 cited

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

Fabian Vazquez, Jose A. Nuñez, Diego Adame +7

Accurate and robust polyp segmentation is essential for early colorectal cancer detection and for computer-aided diagnosis. While convolutional neural network-, Transformer-, and M…

q-bio.NC2025

Modeling Causal Interactions Across Brain Functional Subnetworks for Population-specific Disease Analysis

Alissen Moreno, Yingying Zhang, Qi Huang +9

Current neuroimaging studies on neurodegenerative diseases and psychological risk factors have been developed predominantly in non Hispanic White cohorts, with other populations ma…

cs.CV2025

Adapting a Segmentation Foundation Model for Medical Image Classification

Pengfei Gu, Haoteng Tang, Islam A. Ebeid +7

Recent advancements in foundation models, such as the Segment Anything Model (SAM), have shown strong performance in various vision tasks, particularly image segmentation, due to t…

eess.IV2025

Topo-VM-UNetV2: Encoding Topology into Vision Mamba UNet for Polyp Segmentation

Diego Adame, Jose A. Nunez, Fabian Vazquez +5

Convolutional neural network (CNN) and Transformer-based architectures are two dominant deep learning models for polyp segmentation. However, CNNs have limited capability for model…

eess.IV2025

White Light Specular Reflection Data Augmentation for Deep Learning Polyp Detection

Jose Angel Nuñez, Fabian Vazquez, Diego Adame +3

Colorectal cancer is one of the deadliest cancers today, but it can be prevented through early detection of malignant polyps in the colon, primarily via colonoscopies. While this m…

cs.CV2025

Exploring Transfer Learning for Deep Learning Polyp Detection in Colonoscopy Images Using YOLOv8

Fabian Vazquez, Jose Angel Nuñez, Xiaoyan Fu +2

Deep learning methods have demonstrated strong performance in objection tasks; however, their ability to learn domain-specific applications with limited training data remains a sig…