Title: Ultrasound imaging and quantification of tissue microstructure via acoustic modeling and machine learning
Abstract: Over the last decade, ultrasound devices have become increasingly portable, widely available, and data-rich due to system advances and decreased cost. These developments have created an unmet need to translate the wealth of ultrasound data into valuable diagnostic information to benefit healthcare. From a physical point of view, raw ultrasound signals contain rich information about tissue microstructure and properties. However, much of the information is encoded in the ultrasound signals in a convoluted way and is not readily available from standard clinical B-mode images. Effectively extracting the information buried in ultrasound signals will tremendously benefit medical imaging and diagnostics.
In this talk, I will discuss technical developments and clinical applications of physics-based and data-driven approaches to extract tissue microstructure and properties from ultrasound signals. For the physics-based approach, I will present theoretical and computational work in elucidating the fundamental mechanisms of acoustic scattering in biological tissues. I will discuss how an improved understanding of scattering physics has led to novel quantitative ultrasound imaging biomarkers extracted from ultrasound signals. For the data-driven approach, I will present deep learning methods to extract tissue properties from ultrasound signals. I will discuss deep learning model development, generalizability, and interpretability. For both approaches, I will showcase several applications including liver fat quantification, solid tumor classification, and transcranial brain imaging. Finally, I will conclude with exciting future directions and collaborative opportunities in the technical development and clinical applications of ultrasound imaging.
Biography: Aiguo Han is a Research Assistant Professor with the Department of Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign. He received the B.S. degree in Acoustics from Nanjing University, Nanjing, China, in 2008, and the M.S. and Ph.D. degrees in Electrical and Computer Engineering from the University of Illinois at Urbana-Champaign in 2011 and 2014, respectively. His research interests include quantitative ultrasound imaging, transcranial ultrasound imaging, and machine learning in ultrasound imaging and diagnostics. Dr. Han is a recipient of the American Institute of Ultrasound in Medicine New Investigator Award (2016), National Center for Supercomputing Applications Faculty Fellowship (2021), and NIH/NIBIB Trailblazer Award (2022). He is a Fellow of the American Institute of Ultrasound in Medicine.