报告题目：Infant brain MR image analysis
报告摘要
To better understand early brain development in health and disorder, it is critical to accurately segment infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Deep learning-based methods have achieved state-of-the-art performance; however, one of the major limitations is that the learning-based methods may suffer from the multi-site issue. That is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners. In this talk, we will first introduce how to alleviate the multi-site issue and propose one model for all. Later, we will introduce an infant dedicated proposing pipeline, iBEAT V2.0 Cloud (www.ibeat.cloud). The current functionality of iBEAT V2.0 Cloud includes: Skull stripping, Inhomogeneity correction, Tissue segmentation, Topology Correction, Surface Reconstruction, Surface Measurement, and Surface Parcellation. iBEAT V2.0 Cloud can handle pediatric brain images from multiple sites with various scanners and protocols. Up to date, we have successfully processed 5000+ infant brain images and received numerous praise/positive feedback from 70+ institutions, including Boston Children's Hospital/Harvard Medical School, Stanford University, Yale University, University of Maryland, University of California, University of Pennsylvania, Washington University in St. Louis, Tokyo Metropolitan University, Arkansas Children’s Research Institute, and Princeton University.
嘉宾简介
Dr. Li Wang received the Ph.D. degree in Pattern Recognition and Intelligent System from Nanjing University of Science and Technology in 2010. He is currently a tenure-track assistant professor at the University of North Carolina at Chapel Hill. His interests focus on segmentation, registration, cortical surface analysis, and their applications on normal early brain development and disorders. Recently, he has been working on creating a unique suite of infant-specific analysis tools that enable accurate characterization of early brain development in infants with autism, as well as improved capabilities in early identification of biomarkers and early diagnosis of at-risk infants. His work is funded by NIH K01 Career Award. He is also working on developing innovative software modules with comprehensive user support for infant brain analysis. His work is funded by NIH R01 Award (R01MH117943). His software has been validated on 5000+ infant subjects with promising results and widely used in 70+ institutions. So far, he has published 200+ peer-reviewed papers, with Google Scholar citations 6400+ and h-index 40. More information can be found at: http://liwang.web.unc.edu/.
特别感谢本次Webinar主要组织者：
杜磊（西北工业大学）