报告地点： 电子信息楼 306
报告人： Jianhua Yao，Associate Scientist，Radiology and Imaging Science Department，National Institutes of Health (USA)
报告摘要：Major advances in computer science and artificial intelligence are beginning to have an impact on radiology. Most dramatically, there has been an explosion of research and commercial interest about the use of "deep learning" in radiology. In this presentation, I will give a brief overview of deep learning technologies. I will demonstrate how deep learning can be applied in radiology image analysis in four aspects: computer aided diagnosis and detection, semantic organ and lesion segmentation, disease monitoring and outcome prediction, and data mining on a Large-Scale Radiology Image Database. I will show examples of current researches conducted at the Radiology department in the National Institutes of Health, demonstrating the performance improvement and new research topics brought by the deep learning techniques. Finally, I will discuss the perspective and challenges in the field.
报告人简介：Jianhua Yao is currently an Associate Scientist in the Radiology and Imaging Science Department at the National Institutes of Health (USA), where he leads a clinical image processing service group since 2002. He is also affiliated with the Imaging Biomarker and Computer-Aided Detection Lab at NIH. He received his Ph.D. in computer science from Johns Hopkins University in 2002.
Dr. Yao’s researches focus on clinical image processing, computer aided detection and machine learning. He has published more than 350 papers through research collaboration and independent research, and holds two patents in colon cancer CAD technique. Dr. Yao serves as guest editors for special issues on IEEE TMI, Pattern Recognition and CMIG. He also organized workshops in MICCAI from 2010 to 2016. He co-edited 5 books in the field of medical image analysis.
Dr. Yao received NIH Clinical Center Director’s Award in 2010 and 2016 for sustained scientific innovation and leadership in radiology image processing. He also received best paper awards in SPIE Medical Imaging (2011, 2013) and CARS (2002, 2013).