Author Type

Graduate Student

Date of Award

Fall 11-28-2025

Document Type

Thesis

Publication Status

Version of Record

Submission Date

December 2025

Department

Physics

College Granting Degree

Charles E. Schmidt College of Science

Degree Name

Master of Science (MS)

Thesis/Dissertation Advisor [Chair]

Wazir Muhammad

Abstract

Breast cancer is a major health burden, and clinicians need accurate tumor segmentation to deliver radiation therapy precisely and efficiently. This thesis benchmarks two three-dimensional (3D) deep learning architectures U-Net and SegResNet for automated segmentation of breast tumors on dynamic contrast-enhanced MRI. This work uses the MAMA-MIA benchmark, a (large-scale multicenter dataset for developing and evaluating artificial intelligence (AI) models for breast cancer imaging). MAMA-MIA consist of 1,506 breat cancer subjects. We applied a standardized Medical Open Network for AI (MONAI) preprocessing and training pipeline to build and evaluate deep-learning models for medical imaging. Models were assessed with the Dice Similarity Coefficient (DSC), Intersection over Union (IoU), overall accuracy, and the 95th-percentile Hausdorff distance (HD95), alongside qualitative visualizations and Bland–Altman analyses. U-Net achieved DSC 0.7334, IoU 0.5791, accuracy 0.9984, HD95 33.13 mm, loss 0.0836, and 333.6 s/epoch over 60 epochs. SegResNet achieved DSC 0.7132, IoU 0.5542, accuracy 0.9981, HD95 37.58 mm, loss 0.0915, and 546.1 s/epoch over 60 epochs. Our results show that, U-Net achieved higher overlap and boundary metrics than SegResNet. These findings are preliminary and limited to tumor masks on this dataset; no external validation, user study, or clinical deployment was performed.

Available for download on Tuesday, December 07, 2027

Share

COinS