Ali Gholipour
Assistant Professor in Radiology
Harvard Medical School
Member, Computational Radiology Laboratory
Boston Children's Hospital

"Motion-Robust Super-resolution Magnetic Resonance Imaging of Early Brain Development"

Monday, March 21, 4:00 PM
Packard Lab room 466

Abstract:  Advances in medical imaging have enabled in-vivo analysis of early development and shaped new sciences such as fetal medicine and fetal neurology that were nonexistent a few decades ago. The impact of these technologies has been enormous leading to life-saving interventions and therapies before and after birth. New medical and surgical procedures have significantly increased the survival rate of prematurely born infants and infants with severe congenital anomalies and there is a critical need to minimize and reverse neurodevelopmental alteration in survivors. The analysis of early brain growth is crucial because of the complex long-term effects of neurodevelopmental impairment.

Magnetic Resonance Imaging (MRI) offers a variety of techniques to evaluate the structure and function of the brain and its connections; but MRI acquisitions are lengthy and extremely susceptible to subject motion. This, in particular, poses a significant challenge in imaging fetuses and neonates whose motion during MRI scans is very difficult if not impossible to control. By developing innovative techniques in signal and image processing and machine learning, and utilizing the latest advances in MRI hardware and software, we have developed motion-robust MRI techniques that enable the reconstruction and analysis of 3D and 4D images of the fetal and neonatal brain despite intermittent motion during acquisitions. In particular, we have developed innovative image registration and super-resolution image reconstruction techniques that simultaneously correct the motion and increase the spatial resolution and signal-to-noise ratio of MRI scans of the fetal and neonatal brain. This technology has enabled significant new advances in fetal and neonatal neuroimaging and developmental neuroscience, and helped us to fill the gaps in tools and resources that are critically needed for in-vivo analysis of early brain development. We will discuss this technology and some of its innovative applications in this talk.

Bio:  Ali Gholipour is an Assistant Professor in Radiology at Harvard Medical School and a member of the Computational Radiology Laboratory (CRL) at Boston Children's Hospital. He received a PhD degree in Electrical Engineering from the University of Texas at Dallas in 2008, and the M.Sc. and B.Sc. degrees both in Electrical Engineering from the University of Tehran in 2003 and 2001, respectively. During his PhD he collaborated with the Neuroradiology division of the University of Texas Southwestern Medical Center, where he conducted research on medical imaging, in particular on the development of new techniques for enhanced brain functional localization. His earlier research work involved robotics, control, and intelligent prediction of complex systems.‬‬‬‬‬‬‬‬‬‬‬‬‬‬

Dr. Gholipour’s current research is focused on image registration, image reconstruction, sparse representations, and inverse problems with applications in motion-robust high-resolution fetal and pediatric MRI. Through novel technology development in this area and collaboration with neurologists, neonatologists, and geneticists he has been looking at the mechanism of brain maturation, neurodevelopmental disorders, congenital anomalies, and the analysis of brain functional and structural connectivity. His main research interests are machine learning, imaging, and image processing with applications in medicine, bioinformatics, and neuroscience.

© 2014-2016 Computer Science and Engineering, P.C. Rossin College of Engineering & Applied Science, Lehigh University, Bethlehem PA 18015.