| Biography | |
|---|---|
 Dr. Xuming Zhang Huazhong University of Science and Technology, China |
|
| Title: Non-rigid multi-modal medical image registration | |
| Abstract: Image registration is one of key technologies in the field of medical image processing and analysis. Specially, the non-rigid multi-modal 3D medical image registration is highly challenging. To address this problem, we have proposed two kinds of registration methods in recent years. The first strategy is to convert multi-modal image registration problem into the single-modal one using structural representation methods based on Weber local descriptor (WLD), spiking cortical model (SCM) and Zernike moment. The second one is to use deep learning models such as PCANet and Generative Adversarial Networks (GAN) to produce the registered images. The registration performance of our proposed methods will be appreciated and compared with existing structural representation methods and such deep learning methods as VoxelMorph. | |
| Biography: Xuming Zhang received his doctorate from Shanghai Jiaotong University in 2006. He worked as a postdoctoral researcher at Huazhong University of Science and Technology from 2006 to 2008, and at University of California, Davis from 2008 to 2009. At present, he is an associate professor of Department of Biomedical Engineering, Huazhong University of Science and Technology. His main research direction is surgical navigation and surgical robot. He published about 100 SCI indexed papers and obtained 20 authorized national patents. In recent years, he has served as reviewer of such journals as Information Fusion, IEEE Transaction on Image Processing, Information Sciences and Signal Processing. He has undertaken more than ten projects including National Natural Science Foundation of China, National Key Research and Development Project, 863 project, National Key Scientific Instrument and Equipment Development Project, and National Science and Technology Support Program. | |
