Imaging Studies of Early Brain Development: Challenges and Opportunities by NYU Prof. Guido GERIG

Title: Imaging Studies of Early Brain Development: Challenges and Opportunities

Abstract

Clinical assessment routinely uses terms such as development, growth trajectory, aging, degeneration, disease progress, recovery or prediction. This terminology inherently carries the aspect of dynamic processes, suggesting that measurement of dynamic spatiotemporal changes may provide information not available from single snapshots in time or from cross-sectional studies. Image processing of temporal series of 3-D data embedding time-varying anatomical objects and functional measures requires a new class of analysis methods that make use of the inherent subject-specific dependency of repeated acquisitions. This talk will discuss progress in the development of advanced 4-D image and shape analysis methodologies, now applied to complex, high-dimensional data such as images or image-derived shapes and structures. We will demonstrate that statistical concepts of longitudinal data analysis such as linear and nonlinear mixed-effect modeling, commonly applied to univariate or low-dimensional data, can be extended to structures and shapes modeled from longitudinal image data. Such methods naturally also lead to new tools for construction of normative longitudinal models of early brain development. Most relevant to clinical studies, we will also discuss inclusion of subject’s covariates such as sex and diagnostic scores into our longitudinal image analysis frameworks.
The rapidly increasing role of learning-based techniques, enabled by the availability of large publicly shared image databases for training of networks, will be discussed related to crucial aspects of longitudinal imaging such as image harmonization, image data curation and synthesis, inter-subject multi-modality registration and longitudinal tissue segmentation. We will demonstrate results from ongoing clinical studies of infants at risk for mental illness, including analysis of early brain growth in autism, Fragile-X and Down’s syndromes, and infants born to substance-using mothers.

About the speaker

Guido Gerig is Institute Professor and former Chair at the NYU Tandon School of Engineering in the Departments of Computer Science and Engineering and Biomedical Engineering, where he is also a member of the NYU VIDA center (visualization, imaging and data analysis). Guido Gerig was previously USTAR Professor of Computer Science at the University of Utah (2007-2015), Taylor Grandy Professor of Computer Science and Psychiatry at the University of North Carolina at Chapel Hill (1998-2007), and Assistant Professor at ETH Zurich (1993-1998). Guido Gerig has been named IEEE Fellow (class of 2019) and is also a Fellow of the American Institute for Medical and Biological Engineering (AIMBE). His main research is in computer vision and medical image analysis with driving problems from medicine, tackled in close multidisciplinary collaboration between medicine, engineering, and statistics. His research supports a number of clinical imaging research studies with novel, innovative image analysis methodologies related to segmentation, registration, spatiotemporal modeling, shape analysis, and imaging statistics. Guido Gerig and is author/co-author on over 500 articles, most at high-impact events related to computer science and clinical research.