공지사항

[개소 25주년 세미나] 김호성 교수(USC) @ 2019.05.24(금) 13:30

Author
웹관리자
Date
2019-05-21 13:25
Views
1029
Machine learning and deep learning approaches
for robust brain MRI processing and brain age prediction

 강사 : 김호성 교수 (University of Southern California (USC)
 일시 : 2019년 05월 24일(금) 오후 1시 30분- 2시 30분
 장소 : 서울대학교 뉴미디어통신공동연구소 1층 세미나 1실(132동 104호)

Abstract

Deep learning techniques, especially convolutional neural networks (CNNs) inspired by human neural architecture, are greatly demanded in brain image analyses, thanks to their successes in various biological data sciences. The application of deep learning CNNs in neuroimaging covers various research themes including image reconstruction/enhancement, and computer-aided diagnosis/prognosis. My lab has developed a set of CNN approaches to overcome the limitation of previous approaches and elaborate the brain morphometry on MRI. Our novel CNN modules are implemented for 1) the correction of head motion-driven artifacts; 2) estimation of brain age and prediction of neurodevelopmental outcome. Also, I will deal with applications of other machine learning techniques used for enhancement of our understanding in various brain disorders. My research focuses on developing an analytic platform that assesses aging of brain structures and their structural and functional networks as well as predicting the eventual long-term outcome for neurodevelopment and quantifying the progression of neurodegeneration. To follow-up long-term brain structural modification associated with neurodevelopmental/ neurodegenerative disorders, my group develops methods to quantify various aspects of brain anatomical and networking variability using longitudinally collected multi-contrast MRI. My technical expertise on surface-based morphology and texture modeling, network topology analysis, and multivariate statistical modeling consists of essential elements to develop a combination of techniques to accomplish the proposed specific aims. I have also applied various analytic frameworks, including cortical morphometry, voxel-based morphometry, deformation-based morphometry and structural/functional network analyses, to assessment of brain structures in healthy conditions as well as in pathological conditions that often present anatomical variations beyond the range of normal structures. Using a more advanced pattern analysis with machine learning and deep learning on innovative multi-contrast MRI features, my current research seeks to understand the atypical structural and network alterations in various neurological diseases including epilepsy, dementia, and preterm birth and ultimately to predict neurological/brain functional outcome in the patients.

Biography

 2016- Assistant Professor, Neurology, University of Southern California, LA
 2014-2016 Postdoctoral Fellow, Radiology, University of California San Francisco, San Francisco
 2012-2014 Postdoctoral Fellow, Neurology, Montreal Neurological Institute, Montreal, Canada
 2011 Ph.D. Ph.D., Biomedical Engineering, McGill University, Montreal, Canada

담당자: 바이오메디컬영상과학연구실 이종호(B) 교수 (이진아, 880-4147)