您好,欢迎来到华中科技大学自动化学院官网!

联系我们| English

当前位置: 首页 > 科学研究 > 学术报告 > 正文

学术报告第201808期

发布时间:2018-03-19 编辑:张惠兰 来源:

报告题目:Quantitative imaging and artificial intelligence in radiation therapy

报 告 人:Jing Wang  Associate ProfessorUniversity of Texas Southwestern Medical Center

报告时间:32614:30

报告地点:南一楼中311

 

Short Bio:

Jing Wang received his B.S. degree in Materials Physics from University of Science and Technology of China in 2001, M.A. and Ph.D. degrees in physics from the State University of New York at Stony Brook in 2003 and 2006, respectively. He finished his postdoctoral training in the Department of Radiation Oncology at Stanford University in 2009. He is currently an Associate Professor and Medical Physicist in the Department of Radiation Oncology at the University of Texas Southwestern Medical Center. Dr. Wang has published more than 70 peer reviewed journal papers. His research focuses on medical imaging and its application in radiation therapy. Dr. Wang's research has been supported by National Institute of Health, American Cancer Society, Department of Defense and Cancer Prevention and Research Institute of Texas.

Abstract:

Imaging guidance plays a critical in radiation therapy. For example, cone-beam computed tomography (CBCT) has been integrated into treatment machines. In the integrated systems, imaging can be performed with a patient in the actual treatment position, allowing direct visualization of the target and relevant anatomy in the treatment room. Although CBCT offers significant advantages for improving radiotherapy, several drawbacks limit its potentials, including: 1) the repeated use of CBCT during a course of treatment delivers high extra radiation dose to patients; 2) the presence of scatter pollution within the projection images degrades the CBCT image quality by decreasing the contrast and by introducing shading artifacts that lead to inaccuracies in reconstructed CT-number; and 3) respiration motion introduces motion artifacts in CBCT leading to decreased localization accuracy. In this talk, I will present our recent results on optimizing CBCT for image-guided adaptive radiation therapy, including both software and hardware approaches for dose reduction, scatter correction and motion compensation in CBCT. I will also discuss the application of artificial intelligence for different steps involved in radiation therapy.