GUMP-Net: An Interpretable Model-Data-Driven Intelligent Algorithm for Multi-Class Pelvic Segmentation
报告题目(Title):GUMP-Net: An Interpretable Model-Data-Driven Intelligent Algorithm for Multi-Class Pelvic Segmentation
报告人(Speaker):陈冲 研究员(中国科学院数学与系统科学研究院)
地点(Place):后主楼1124
时间(Time):2026年6月5日(周五)16:00-17:00
邀请人(Inviter):刘君
报告摘要
Pelvic segmentation is one of the most important and fundamental research problems in precise and intelligent diagnosis and treatment, as well as surgical planning and navigation for pelvic fractures. In this talk, we will introduce the proposed algorithm GUMP-Net. Extensive experiments on pelvic and ankle datasets demonstrate the rationality and effectiveness of the proposed algorithm.
主讲人简介
陈冲,中国科学院数学与系统科学研究院研究员,研究兴趣包括医学成像反问题、图像处理、计算几何以及人工智能等,担任计算数学、CT理论与应用研究、Int. J. Comput. Math.、J. Math. Imaging Vis.等国内外期刊编委,研究工作获国家自然科学基金委优秀青年科学基金资助。