Advancing Nuclear Medicine Imaging with AI

Nuclear medicine imaging is entering a transformative era in which AI and imaging physics are tightly integrated to improve diagnostic accuracy, reduce scan burden, and enable personalized clinical decision-making. This seminar will present a unified research program that advances PET/SPECT imaging across three interconnected domains: AI-assisted diagnostics, quantitative parametric imaging, and predictive modeling. First, I will introduce physics-informed and self-supervised deep learning methods that enhance low-dose and shortened-duration PET scans while preserving diagnostic fidelity. These approaches improve image quality, mitigate motion artifacts, and support CT-free quantitative workflows, offering safer and more efficient imaging particularly for pediatric applications. Next, I will discuss advances in quantitative parametric imaging. We develop a self-supervised deep-learning framework for indirect parametric image estimation from conventionally reconstructed dynamic frames and introduce deep-learning–regularized direct 4D parametric reconstruction from raw data. These complementary methods generate quantitative tracer-kinetic maps—such as myocardial blood flow and neuroreceptor binding—that enable individualized risk assessment and therapy planning. Finally, I will highlight AI models that integrate molecular imaging, radiomics, and clinical data to predict disease progression and treatment response, with applications in Parkinson’s disease and pediatric oncology. Together, these innovations demonstrate how AI can transform nuclear medicine into a more precise, quantitative, and predictive discipline.

Dr. Jing Tang is an Associate Professor in the Department of Biomedical Engineering at the University of Cincinnati. She received her PhD in Electrical Engineering from the University of Illinois at Urbana–Champaign and completed postdoctoral training in Radiology at the Johns Hopkins University School of Medicine. Before entering academia, she served as a principal imaging physicist at Philips Healthcare, contributing to PET/CT and PET/MR technology development. Prior to joining UC, she was a tenured Associate Professor of Electrical and Computer Engineering at Oakland University.

Dr. Tang’s research integrates imaging physics and machine learning to advance PET/SPECT image formation, quantitative parametric imaging, and predictive modeling for precision health. Her work has been supported by federal and foundational grants, including an NSF CAREER Award and an ongoing NIH R01. She is certified by the American Board of Science in Nuclear Medicine and is the recipient of the 2019 Tracy Lynn Faber Memorial Award for outstanding contributions in PET image reconstruction, processing, and analysis.