Segmentation Joint Registration for Low-Contrast Image
数学专题报告
报告题目(Title)：Segmentation Joint Registration for Low-Contrast Image
报告人(Speaker)：韩欢（武汉理工大学）
地点(Place)：后主楼1124
时间(Time)：2025年11月7日（周五）15:00-16:00
邀请人(Inviter)：段玉萍
报告摘要
Low-contrast medical images present significant challenges in segmentation due to weak intensity gradients and ambiguous boundaries (e.g., prostate or brain tumor regions). Traditional methods, such as thresholding or edge detection, often fail to simultaneously address joint registration, segmentation, and displacement field correction, leading to misalignment and inaccurate tissue delineation. To address this challenge, in this talk, we proposed a novel variational model which joints three tasks including segmentation, registration and bias correction. Theoretical results are given to show the existence of the solution to the proposed model, asymptotic behavior of the solution with respect to parameters and the convergence of the ADM algorithm. Numerical tests are performed to validate the theoretical results.
主讲人简介
韩欢，武汉理工大学副教授，博导，从事医学图像配准相关的变分理论与小样本学习研究，入选“湖北省青年拔尖人才培养计划”，主持国家自然科学基金(面上、青年项目)、湖北省自然科学基金面上等项目，参与国家重点研发计划项目。在SIAM J. Multiscale Model. Simul.、SIAM J. Imaging Sci.、ESAIM: Math. Model. Numer. Anal.、Inverse Probl. Imag.、IEEE Transactions on Medical Imaging、IEEE Trans. Multimedia 等国际权威期刊发表论文 20 余篇。曾先后到英国利物浦大学、思克莱德大学等高校数学系开展学术访问。
