题目:Machine Learning in Internet-based Intelligent Medicine
(互联网智能医疗中的机器学习方法)
报告人:沈定刚教授(美国北卡罗来纳大学教堂山分校终身教授)
组织:计算机科学与技术学院
时间:11.11(周五上午) 9:50-11:00
地点:六教6206
专家简介:
沈定刚,国家“千人计划”入选者,美国北卡罗来纳大学教堂山分校计算机系、生物医学工程系、医学影像中心终身教授。影像信息中心主任,医学图像分析实验室主任。先后任职约翰霍普金斯大学讲师、宾夕法尼亚大学助理教授。
现在主要从事计算机视觉、模式识别、医学图像分析等领域的研究。作为课题负责人,获得过十余项美国研究基金。其提出的大脑弹性配准算法HAMMER是该领域的知名算法,2006年获得IEEE Signal Processing Society年度最佳论文,被引用700多次,相关软件下载10000多次。在Human Brain Mapping、 Neuroscience、IEEE Trans. on Pattern Analysis and Machine Intelligence等国际学术期刊和会议发表700多篇论文。担任六个国际期刊的编委,是医学图像计算和计算机辅助治疗组织(MICCAI)的执委会成员。
更多信息见个人主页http://www.med.unc.edu/~dgshen.
报告摘要:This talk will describe how the future internet-based intelligent medicine will look like, as well as main challenges such as how to integrate different scale information together for helping disease diagnosis. To achieve this goal, we have recently developed various machine learning techniques, including sparse learning and deep learning, for respective applications. Specifically, 1) in neuroimaging field, we have developed an automatic brain measurement method for the first-year brain images with the goal of early detection of autism such as before 1 year old. This effort is aligned with our recently awarded Baby Connectome Project (BCP) (where I serve as Co-PI), which will acquire MR images and behavioral assessments from typically developing children, from birth to five years of age. Besides, we have also developed a novel multivariate classification method for early diagnosis of Alzheimer’s Disease (AD) with the goal of potential early treatment, as well as prediction of success of neurosurgery by collaboration with Huashan Hospital in Shanghai. 2) In image reconstruction field, we have developed a sparse learning method for reconstructing 7T-like MRI from 3T MRI for enhancing image quality, and also another novel sparse learning technique for estimation of standard-dose PET image from low-dose PET and MRI data. 3) Finally, in cancer radiotherapy field, we have developed an innovative regression-guided deformable model to automatically segment pelvic organs from single planning CT which is currently done manually, as well as a novel image synthesis technique for estimating CT from MRI for current new direction of MRI-based dose planning (and also for PET attenuation correction in the case of using PET/MRI scanner). All these techniques are the important components of future internet-based intelligent medicine, and will be discussed in this talk.