Author ORCID Identifier

0000-0002-6949-7014

Defense Date

2025

Document Type

Dissertation

Degree Name

Doctor of Philosophy

Department

Biomedical Engineering

First Advisor

Jennifer Jordan

Abstract

The advancement in cancer survivorship faces a potential setback as cardiovascular complications emerge as a prominent cause of non-cancer-related mortality among survivors. Anthracycline-induced cardiotoxicity (AIC), one such complication, is related to structural and functional changes in the heart, including damage to cardiomyocytes, nonfocal fibrosis, and is reported to affect up to 34% of anthracycline-treated cancer survivors. Monitoring AIC through repeated LVEF assessment detects meaningful dysfunction only after significant myocardial injury has already occurred. It has been postulated that the harm caused by anthracyclines may outweigh the benefits in some patients, necessitating methods to identify those at higher risk of adverse cardiovascular outcomes who might benefit from early cardioprotective interventions. Prior efforts incorporating pretreatment clinical variables (e.g., baseline LVEF, BMI, hypertension, age) have shown limited predictive value.

This dissertation investigates myocardial tissue architecture as a source of preclinical biomarkers for AIC. Specifically, we explore radiomic texture features (RTFs) extracted from cardiovascular magnetic resonance (CMR) T1 mapping to improve risk prediction. First, we assess the reliability of RTFs under varying imaging and preprocessing conditions, identifying features robust to pipeline variation. We develop a deep learning–based LV myocardium segmentation model to reduce operator variability and improve feature extraction efficiency, and integrate robust RTFs with clinical variables to build machine-learning models for pretreatment AIC risk prediction.

Together, these studies establish a framework for robust radiomics-based risk stratification in patients treated with anthracyclines. By enabling early identification of individuals at elevated CV risk, this work supports more personalized cancer treatment planning, targeted surveillance, and timely cardioprotective intervention, ultimately promoting safer chemotherapy delivery and improved long-term survivorship.

Rights

© The Author

Is Part Of

VCU University Archives

Is Part Of

VCU Theses and Dissertations

Date of Submission

12-12-2025

Available for download on Saturday, December 12, 2026

Share

COinS