题目：Diffeomorphic Deformations Based Indirect Image Registration with Extension to Spatiotemporal Medical Imaging

报告人：陈冲 副研究员（中国科学院数学与系统科学研究院计算数学研究所）

摘要：

Indirect image registration is one of the significant problems for the image reconstruction in spatiotemporal medical imaging. We adapt the large deformation diffeomorphic metric mapping framework for image registration to the indirect setting, where a template is registered against a target that is given through indirect noisy observations. The registration uses diffeomorphisms that transform the template through a (group) action. These diffeomorphisms are generated by solving a flow equation that is defined by a velocity field with certain regularity. The theoretical analysis includes a proof that indirect image registration has solutions (existence) that are stable and that converge as the data error tends to zero, so it becomes a well-defined regularization method. Moreover, an efficiently computational method is also presented. The talk concludes with examples of indirect image registration in 2D tomography with very sparse and/or highly noisy data and the potential extension to spatiotemporal medical imaging.

时间：12月22日（周五）上午09:00-10:00

地点：首师大新教二813

主办单位：

565net必赢客户端565net必赢客户端

检测成像北京市高校工程研究中心

北京成像技术高精尖创新中心

欢迎全体师生积极参加！