报告题目：医学影像分析与手术模拟——人工智能和虚拟现实在医学中的应用
Medical Image Analysis and Surgical Simulation – AI and VR Applications for Medicine
时 间：2019年1月14日10:00-12:00
地 点：光电国家研究中心A101
报 告 人：王平安 教授， 香港中文大学
邀 请 人：李 强 教授
报告人简介（Biography）：
王平安博士现任香港中文大学计算机科学与工程系教授。自1999年以来，他一直担任香港中文大学虚拟现实、可视化与图像学研究中心主任，并曾担任计算机科学与工程系系主任（2014-2017）和研究生部主任（2005-2008和2011-2016）。他自2006年起担任中国科学院深圳先进技术研究院人机交互中心主任，并于2007年被中国教育部评为“长江学者讲座教授”。发表了超过470篇同行评审论文，包括190篇国际期刊论文和280篇国际会议论文。他的团队近年来在医学影像分析方面获得三项最佳论文奖，包括MIA-MICCAI 2017年最佳论文奖。他的研究兴趣包括医学应用的人工智能和虚拟现实，手术模拟，可视化，计算机图形学和人机交互。
Dr. Pheng Ann Heng is a professor at the Department of Computer Science and Engineering at The Chinese University of Hong Kong (CUHK). He has served as the Director of Virtual Reality, Visualization and Imaging Research Center at CUHK since 1999. He has also served as the Department Chairman (2014-2017) and Head of Graduate Division (2005-1008 and 2011-2016). He has served as the Director of Center for Human-Computer Interaction at Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences since 2006 and has been appointed by China Ministry of Education as a Cheung Kong Scholar Chair Professor in 2007. He is the author of over 470 peer-reviewed publications, including 190 international journal articles and 280 international conference papers. His group has received three best paper awards in medical image analysis in recent years, including MIA-MICCAI 2017 best paper award. His research interests include artificial intelligence and virtual reality for medical applications, surgical simulation, visualization, graphics and human-computer interaction.
报告摘要（Abstract）：
近年来，深度学习在一些具有挑战性的高难度问题中取得了巨大成功，这其中就包括深度学习在医学图像分析中的应用。王博士团队率先提出并采用三维卷积神经网络从MR图像中自动检测大脑微出血。为了减少肺结节自动检测中的假阳性，他们设计了考虑多级上下文信息的三维卷积神经网络框架，并进一步提出了一种新颖高效的三维神经网络，配备了三维深度监督机制，从而全面解决了三维网络优化难点和医学训练样本不足的挑战。他们对深度学习的成功应用涵盖了广泛的医学图像模式，包括组织病理学成像，超声成像，MR/CT成像，皮肤镜成像和结肠镜检查视频。同时，虚拟现实在临床医疗中的应用也取得了长足进步，基于虚拟现实的手术模拟成为一种经济且有效的临床培训手段。王博士团队通过医学成像，运动跟踪，物理模拟，触觉反馈和视觉呈现的智能集成来构建逼真的虚拟环境，从而实现提供外科手术专业培训的目标。在此次演讲中，王博士将介绍他们使用深度学习进行医学图像分析的最新工作，以及他们开发的基于虚拟现实的一系列手术模拟系统。
There are many successful applications of deep learning in solving challenging and difficult problems in recent years. An excellent example is its application in medical image analysis. Dr. Heng’s group is the first to employ 3D convolutional neural networks for automatic detection of cerebral micro-bleeds from MR images. They also proposed multi-level contextual 3D convolutional neural network framework for false positive reduction in automated pulmonary nodule detection. They further proposed a novel and efficient 3D CNN equipped with a 3D deep supervision mechanism to comprehensively address the challenges of optimization difficulties of 3D networks and inadequacy of medical training samples. Their successful deep learning applications cover a wide spectrum of medical image modalities, include histopathological imaging, ultrasound imaging, MR/CT imaging, dermoscopy imaging and colonoscopy videos. Concurrently, there are also many significant and promising developments in virtual reality that are applicable for medical applications. Virtual reality based surgical simulation can provide a cost-effective and efficient way to train novices. In order to achieve the goal of delivering specialized training of a surgical procedure, one practical solution is to construct a realistic virtual environment through intelligent integration of medical imaging, motion tracking, physically based simulation, haptic feedback and visual rendering. In this talk, Dr. Heng shall present their recent works in using deep learning for medical image analysis and introduce some VR-based surgical simulators they have developed.
