Events Calendar

Brain MRI Statistical Feature Extraction for Characterizing Neurodegenerative Diseases

Speaker: Norbert Schuff, Ph.D., Dept. of Radiology and Biomedical Imaging, University of California, San Francisco

Talk Title: Brain MRI Statistical Feature Extraction for Characterizing Neurodegenerative Diseases

Series: Medical Imaging Seminar Series

Abstract: Brain lesions from neurodegenerative diseases, such as Alzheimer's disease and Parkinson's disease, are difficult to detect on MRI with the naked eye. This may explain why MRI is not yet used as a diagnostic tool for these conditions - except for ruling out other major brain diseases. It is therefore important to find effective solutions for the extraction of imaging features that can be used for diagnosing neurodegenerative diseases. I will discuss new approaches mainly anchored in information theory for extracting features from structural as well as functional brain MRI data. In particular, I will show new approaches for quantifying complexity of resting-state fMRI. Lastly, I will present initial results from MRI vascular fingerprinting - an approach for studying brain microvasculature.



Biography: I am a Professor in the Department of Radiology and Biomedical Imaging at the University of California, San Francisco. I am also Co-Director of the Neurodegenerative Diseases Research Interest Group and a researcher at the San Francisco Veterans Affairs Medical Center. I earned my PhD in Physics from the Ruprecht Karls University of Heidelberg in 1983. From 1984 to 1992, I developed NMR & MRI systems first with Bruker GmbH in Karlsruhe/Germany and later with Varian, Palo Alto, California. In 1993, I joined UCSF.

I study neurodegenerative diseases such as Alzheimer and Parkinson using MRI. My interest is to better capture abnormal brain structure and function for improving prediction, diagnosis and monitoring progression of these devastating conditions. I accomplish this by developing new methods for extracting image features using MRI physics as well as modern concepts of probability, statistical learning and information theory.


Host: Prof. Justin Haldar

Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248

Audiences: Everyone Is Invited

Contact: Talyia Veal