Speaker: Kyung Sung, PhD
Topic: Quantitative Perfusion MRI and Beyond
The Department of Medical Imaging in pleased to have Kyung Sung, PhD, presenting at our Grand Rounds on Tuesday, December 5th, at 12:00 pm in the Arizona Health Sciences Center, Room 5403.
Dr. Sung is an Assistant Professor of Radiological Sciences, Bioengineering and Biomedical Physics IDP at Magnetic Resonance Research Labs at the David Geffen School of Medicine at UCLA.
Dr. Sung received his MS and PhD degrees in Electrical Engineering from the University of Southern California, Los Angeles, in 2005 and 2008, respectively. From 2008 to 2012, he finished his postdoctoral training at Stanford in the Department of Radiology and joined the University of California, Los Angeles (UCLA) Department of Radiological Sciences in 2012 as an Assistant Professor. His research interest is to develop fast and reliable MRI methods that can provide improved diagnostic contrast and useful information. In particular, his group (http://mrrl.ucla.edu/meet-our-team/sung-lab/) is currently focused on developing advanced quantitative MRI techniques for early diagnosis, treatment guidance, and therapeutic response assessment for oncologic applications.
Abstract: Quantitative perfusion MRI continues to gain clinical acceptance as a preferred imaging technique for non-invasive detection and characterization of cancer and other perfusion abnormalities. In this talk, Dr. Sung will outline some of their recent developments in both contrast-enhanced and non-contrast-enhanced perfusion MRI, which can provide more robust and reproducible measures of tissue perfusion. The presentation will 1) give an overview of improved data acquisition, image reconstruction, and post-processing methods for both dynamic contrast-enhanced (DCE) MRI and arterial spin labeling (ASL), and 2) demonstrate results in prostate cancer detection and characterization and characterization of ischemic placenta disease at early gestation.
In addition, Dr. Sung will present an introduction to quantitative MRI-driven deep learning algorithms for improved cancer detection and classification. Deep learning (DL) has recently garnered great attention because of its superior performance in image recognition and classification. One of the main promises of DL is to replace handcrafted imaging features with efficient algorithms for hierarchical feature extraction. Many studies have shown DL is a powerful engine for producing “actionable results” in unstructured big data. He will describe their recently developed magnetic resonance imaging (MRI)-driven deep learning methods to effectively distinguish between indolent and clinically significant prostate cancer. This will mainly highlight 1) unique challenges of quantitative MRI data in DL frameworks, 2) construction of DL frameworks through pre-trained convolutional neural networks (CNNs) and generative adversarial networks (GANs), and 3) application of the proposed DL frameworks to the computerized analysis of prostate MRI.
Arizona Health Sciences Center, Room 5403