题  目：Mathematical Modeling for biomedical Imaging applications with small data

报告人：王超

单  位：南方科技大学

时  间：12月14日，上午9:00

腾讯ID: 910-194-578  

摘  要： Although big data is ubiquitous in data science, one often faces challenges with small data, as the amount of data that can be taken or transmitted is limited by technical or economic constraints.  To retrieve useful information from the insufficient amount of data, an additional assumption or leveraging information from other sources are required.  In this presentation, I will talk about two kinds of two biomedical applications related to small data. In the first application,  we consider minimizing the L1/L2 term on the gradient for a limited-angle scanning problem in computed tomography (CT) reconstruction. We design a specific splitting framework for an unconstrained optimization model so that the alternating direction method of multipliers (ADMM) has guaranteed convergence under certain conditions. In the second application, we consider a grey-matter/white-matter segmentation problem using gigapixel pathology images from autopsied human brain tissues. The need for manual and detailed annotations limits the applicability of supervised deep learning algorithms in this problem. To tackle this challenge, we propose a semi-supervised active learning framework with a region-based selection criterion. This framework iteratively selects regions for annotation query to quickly expand the diversity and volume of the labeled set.

个人简介：王超，博士，南方科技大学统计与数据科学系助理教授, 博士生导师。加入南科大前，在加州大学戴维斯分校的数据科学研究从事博士后研究。2018年获得香港中文大学数学博士；2018年至2020年，在德州大学西南医学中心与达拉斯分校做研究。研究兴趣包括科学计算、图像处理、深度学习、跨学科数学建模、凸与非凸优化，曾在 IEEE Trans. Signal Process, SIAM J. Sci. Comput. SIAM J. Imag. Sci., ICCV等高水平期刊发表论文。