BME PhD Preliminary Exam Announcement for Youngjun Lee (R. Surowiec, advisor) Everyone is invited to attend the public presentation beginning at 3:30 PM. Research Title: AI-Radiomics in CKD Date: March 31, 2025 Time: 3:30 PM Location: MJIS 2001 Thesis Committee Members: Rachel Surowiec (Advisor, Committee Chair) Craig Goergen Fang Huang Stuart Warden (Outside BME) Abstract: Understanding CKD-Related Bone Fragility Through AI-Driven Radiomics Chronic kidney disease (CKD) affects nearly 40 million individuals in the U.S., increasing their fracture risk up to 17-fold compared to non-CKD counterparts. Conventional imaging, primarily dual-energy X-ray absorptiometry (DXA), is insufficient for detecting CKD-related cortical bone deterioration, which is characterized by increased porosity, mineral/water imbalances, and alternation of bone microarchitecture. To address this challenge, my research integrates high-resolution peripheral quantitative computed tomography (HR-pQCT) and AI-driven radiomics analysis to improve the assessment of cortical bone in CKD patients. This study aims to establish a radiomics-based framework for early CKD bone screening. The first objective is to identify unique radiomic features associated with CKD-related cortical bone deterioration using HR-pQCT imaging and the radiomics approach. The second objective is to apply machine learning classifiers to enhance classification accuracy between CKD and non-CKD cortical bone, improving early detection. Additionally, we investigate how bone composition-mineral, collagen, and water content-contributes to bone texture variations, providing deep insights to discover any of new connection in radiomics between bone composition components and CKD-related bone deterioration. By leveraging AI-driven radiomics, this research has the potential to enhance diagnostic precision, enabling early intervention and personalized treatment strategies for CKD patients. The outcomes of this study could help establish radiomics-driven biomarkers for bone health assessment, bridging the gap between computational imaging and clinical applications. -- Bmeroundtable-list mailing list Bmeroundtable-list@ecn.purdue.edu https://engineering.purdue.edu/ECN/mailman/listinfo/bmeroundtable-list