Learning Clinically Useful Information From Medical Images

发布日期：2015-11-17

 讲座嘉宾： Daniel Rueckert

英国皇家工程院  院士

英国帝国理工大学教授 

邀请人：庄吓海   工程力学系

主讲嘉宾介绍：

Daniel Rueckert教授是帝国理工大学计算科学系教授，英国皇家工程院院士，MICCAI Fellow。他发表peer-reviewed文章300多篇；H-index高达55，引用超过18000次（谷歌学术数据）。他是形变模型和配准算法临床应用研究的先驱，其工作成果已被成功应用到乳腺、肝脏、心脏以及大脑等临床问题中。他关于自由形变模型配准技术的一篇文章获得超过3600次引用。他是英国上市公司IXICO创始人之一，该公司的技术已经应用到超过40个大规模临床试验，涉及超过8000个病人。基于Rueckert院士研究成果的影像生物标记已经被 European Medicines Agency所认可并作为临床验证中老年痴呆症患者判断的有效工具。

讲座摘要：

Three-dimensional (3D) and four-dimensional (4D) imaging plays an increasingly important role in computer-assisted diagnosis, intervention and therapy. However, in many cases the interpretation of these images is heavily dependent on the subjective assessment of the imaging data by clinicians. Over the last decades image registration has transformed the clinical workflow in many areas of medical imaging. At the same time, advances in machine learning have transformed many of the classical problems in computer vision into machine learning problems. This talk will focus on the convergence of image registration and machine learning techniques for the discovery and quantification of clinically useful information from medical images. In the first part of part of this talk I will give an overview of recent advances in image registration. The second part will focus on the how the combination of machine learning and image registration can be used to address a wide range of challenges in medical image analysis such as segmentation and tracking. To illustrate this I will show several examples such as the segmentation of anatomical structures, the discovery of biomarkers and the quantification of temporal changes such as growth and motion.