报告题目：Medical Image Retrieval and Visual Analytics
报告人： Jinman Kim (PhD)
报告时间：2015年11月10 日（周二）上午 9:00
报告地点：博习楼327会议室
报告摘要：
Medical imaging is a critical and indispensable component of modern healthcare and are producing vast amounts of data repositories. Yet the true value of medical data comes not just from the quantity but the patterns that can be derived from the relationships between diverse pieces of data. These relationships are fundamental to understanding the ‘big picture’ for vast range of applications in evidenced-based diagnosis, physician education, and biomedical research. These decision support applications are predicated on the ability to objectively retrieve related images by computing the similarity of image’s visual content in a manner that matches the subjective similarity judgement of human domain experts. In this talk, I will present my team’s ongoing research on automated medical image processing for image feature extractions, as well as describing methods for characterising and comparing the visual content of images, including a graph-based method for comparing 3D PET-CT lung cancer images and our more recent work using convolutional neural networks. This talk will also present the activities in the Faculty-wide research cluster – institute of biomedical engineering and technology (BMET) and its links to other University’s research activities.
欢迎广大师生踊跃参加！