Title:

Exploiting the Medical Data Structure for Biomedical Imaging Enhancement

Abstract:

With the the ever-increasing amount of medical image data (CT, MRI, PET, ultrasound, etc.) in the hospital and medical centers across the world, exploitation of the large-scale medical data would provide invaluable information for the medical image processing and analysis. The quality of medical image is a great challenge at low radiation dose and short acquisition time. Learning-based medical image enhancement is an inter-disciplinary field that bridges machine learning, computer vision, health informatics and medical imaging. It offers flexible and effective approaches to exploit the inherent structure of the massive medical image data. 

In this talk, I will introduce our work on smart medical imaging learning and enhancement in three parts. First, I will focus on how to develop a general, efficient and learning-based sparse deconvolution algorithm to achieve robust parameter map estimation and accurate detection of brain deficits in acute stroke and SAH patients. In particular, I will present how to utilize the complementary information in the high-dose repository of CT perfusion maps and learn a compact and adaptive dictionary for low-dose enhancement to handle low-contrast tissue and complex structural details. Second, I will show how this algorithm can be applied to cerebral blood flow and permeability estimation in CTP and fast arterial spin labeling MR perfusion, with extension to tissue-specific approach to preserve the low-contrast white and gray matter. Third, more recently development of robust tensor total variation algorithm for low-dose CT perfusion will be presented. The work presented is based on collaboration with radiologists and clinical experts in the Radiology Department of Weill Cornell Medical College, the MRI Center of Cornell University and North Shore LIJ. 

Bio:

Dr. Ruogu Fang is an Assistant Professor of the School of Computing and Information Sciences at Florida International University. Dr. Fang received her Ph.D. from Cornell University in 2014. Her research interests span over medical image analysis, health informatics, machine learning and computer vision. Dr. Fang is the recipient of numerous honors and awards, including the Best Paper Award at International Conference on Image Processing, Best PhD Poster Presentation at Cornell Engineering Research Conference, Hsien Wu and Daisy Yen Wu Memorial Award, Irwin and Joan Jacobs Fellowship, Li & Fung Scholarship. She served as the Co-Chair of the International Workshop on Sparsity Techniques in Medical Imaging, and the guest editor of the Journal Computerized Medical Imaging and Graphics.

Prof. Fang’s SMILE Group aims to explore intelligent approaches to bridge the data and medical informatics. The focus is on computing and analytics of functional imaging, such as cerebral blood flow estimation in CT perfusion, deconvolution in low-dose radiation CT imaging and fast arterial spin labeling MRI. These are critical imaging and analytics foundations for future ultra-low-radiation, high-speed and high-resolution medical imaging.