DeepMedSeg- Deep Learning for Medical Image Segmentation
Faculty Mentor
Felix Hamza-Lup
Location
Savannah Ballroom
If Other was choses above, please indicate your topic area here:
biomedical, health, & computer interface
Type of Research
On-going
Session Format
Oral Presentation
College
Allen E. Paulson College of Engineering & Computing
Department
Computer Science
Abstract
Medical image segmentation—the process of partitioning digital images into distinct anatomical or pathological regions—is a critical step in clinical workflows, including tumor volume estimation, treatment planning, and disease progression monitoring. Manual segmentation by radiologists is time consuming, prone to inter-observer variability, and increasingly impractical given the rising volume of medical imaging data (MRI, CT, and Ultrasound). This project aims to develop and evaluate a deep learning framework based on Convolutional Neural Networks (CNNs), specifically the U-Net architecture, to automate the segmentation of target regions (e.g., lung nodules or brain lesions). Our goal is to achieve high-precision masks that match the accuracy of expert annotations while significantly reducing processing time.
Program Description
.
Start Date
4-21-2026 10:00 AM
End Date
4-21-2026 12:00 PM
Recommended Citation
Girón, Alejandro J.; Webster, Nicholas-Paul; Tran, Thi; and Morgan, Casey, "DeepMedSeg- Deep Learning for Medical Image Segmentation" (2026). GS4 Student Scholars Symposium. 43.
https://digitalcommons.georgiasouthern.edu/research_symposium/2026A/2026A/43
DeepMedSeg- Deep Learning for Medical Image Segmentation
Savannah Ballroom
Medical image segmentation—the process of partitioning digital images into distinct anatomical or pathological regions—is a critical step in clinical workflows, including tumor volume estimation, treatment planning, and disease progression monitoring. Manual segmentation by radiologists is time consuming, prone to inter-observer variability, and increasingly impractical given the rising volume of medical imaging data (MRI, CT, and Ultrasound). This project aims to develop and evaluate a deep learning framework based on Convolutional Neural Networks (CNNs), specifically the U-Net architecture, to automate the segmentation of target regions (e.g., lung nodules or brain lesions). Our goal is to achieve high-precision masks that match the accuracy of expert annotations while significantly reducing processing time.
