Surface-based techniques for brain shape analysis
Our world consists of various 3D objects with their shape characteristics. 3D shape analysis is a subfield of computer science to explore the inherent geometric attributes of 3D objects. In the application domain, brain shape analysis is one of the popular approaches in neuroimaging studies of brain development and atrophy to understand behavioral or cognitive functions. Despite its importance, the human brain might not be understood well by standard 3D shape analysis techniques due to the anatomical variability accompanied by a complicated, dynamic folding process. In this talk, I will review the challenges in brain shape analysis and introduce my recent surface-based techniques, including brain shape registration and segmentation. I will also discuss how to employ data-driven approaches effectively on insufficient neuroimaging data.
Ilwoo Lyu is an assistant professor of Computer Science and Engineering and the Graduate School of Artificial Intelligence at Ulsan National Institute of Science and Technology (UNIST). Prior to joining UNIST, he was a research assistant professor of Electrical Engineering and Computer Science at Vanderbilt University. He received his Ph.D. in Computer Science from the University of North Carolina at Chapel Hill in 2017, MS and BS in Computer Science from Korea Advanced Institute of Science and Technology. His research interest intersects computer vision, machine learning, and medical image analysis. His research focus is particularly on developing novel algorithms for 3D shape analysis of the brain.