ORCID

https://orcid.org/0009-0008-4769-2370

Year

2023

Season

Spring

Paper Type

Master's Thesis

College

College of Computing, Engineering & Construction

Degree Name

Master of Science in Computer and Information Sciences (MS)

Department

Computing

NACO controlled Corporate Body

University of North Florida. School of Computing

Committee Chairperson

Dr. Xudong Liu

Second Advisor

Dr. Indika Kahanda

Rights Statement

http://rightsstatements.org/vocab/InC/1.0/

Third Advisor

Dr. Robert Maxwell

Abstract

Breast density screenings are an accepted means to determine a patient's predisposed risk of breast cancer development. Although the direct correlation is not fully understood, breast cancer risk increases with higher levels of mammographic breast density. Radiologists visually assess a patient's breast density using mammogram images and assign a density score based on four breast density categories outlined by the Breast Imaging and Reporting Data Systems (BI-RADS). There have been efforts to develop automated tools that assist radiologists with increasing workloads and to help reduce the intra- and inter-rater variability between radiologists. In this thesis, I explored two deep-learning-based approaches on breast density classification. First, I developed and experimented with algorithms using deep learning models (such as Inception V3 and ViT) to classify patients according to BI-RADS using various types of digital mammograms. Second, with the need to provide not only such classification but also a quantitative measure of breast density to help standardize assessments across radiologists, I applied a deep learning based semantic segmentation model, DeepLabV3, to predict density percentages which then were used to provide a linear and probability scale.

Share

COinS
 

Accessibility Statement

This item was created or digitized before April 24, 2027, or is a reproduction of legacy material created before that date. It is preserved in its original, unmodified state specifically for research, reference, or historical recordkeeping. In accordance with the ADA Title II Final Rule, the Library provides accessible versions of archival materials by request. If you are experiencing difficulty accessing the information on the site due to a disability, please submit a request through the following form for assistance.