Image Reconstruction & Quantitative Analysis for Total Body PET
Date and Time: 15:30-17:00, Sept 16 (Friday), 2022
Zoom Link: https://cuhk.zoom.us/j/92775210812
Speaker: Dr. Zhaoheng Xie
Position: Postdoctoral Fellow, CUHK
Biography: Dr. Zhaoheng Xie received the B.S. degree in electronics science and technology from Xi'an Jiaotong University, Shannxi, China, in 2012, and the Ph.D. degree in biomedical engineering from the Peking University, Beijing, China, in 2017, respectively. Since 2018, he is a Postdoc research fellow at the University of California at Davis, Davis, CA, USA. Dr. Xie's research interests include (1) PET image reconstruction methods, (2) quantitative corrections in PET physics and (3) machine learning based medical image applications. Dr. Xie has published over 17 papers in peer-reviewed journals, includes PNAS, JNM, PMB, etc. Dr. Xie received the Fully3D and IEEE NSS/MIC trainee grant in 2018 and 2020, respectively. In 2019, Dr. Xie co-authored the (Henry N. Wagner) Best Paper Award by the Society of Nuclear Medicine and Molecular Imaging (SNMMI). One year later, Dr. Xie was awarded the Young Investigator Award of the SNMMI (1st Place winner)
Title: Image Reconstruction & Quantitative Analysis for Total Body PET
Abstract: Positron emission tomography (PET) in vivo visualizes the molecular pathway and is the most sensitive molecular imaging modality routinely applied in clinic. Recent developments in PET technology dramatically increased the effective sensitivity by increasing the geometric coverage leading to total-body PET imaging. It has a number of ground- breaking properties including ultra-high sensitivity, ultra-large field of view (FOV) and the opportunity for ultra-fast scanning, which enables a tailor-made solution for more convenient and safer clinical practice, medical research and drug screening. In this talk, I will start with the world's first quad-modality molecular imaging system we developed for small animal study. Then I will introduce the data handling techniques we have developed for the EXPLORER PET scanner, which has a 2-meter long FOV with tremendous numbers of detectors. The specific 3D/4D statistical image reconstruction and quantitative correction techniques will be described. Furthermore, I will provide some frontline applications of AI in total-body PET, which will cover the latest works we published including learning-based PET image reconstruction, scatter correction, motion correction, and kinetic modeling. The talk will conclude with a few challenging opportunities in various research and clinical applications.