Date(s) - 02/06/2023
3:00 pm - 4:00 pm
Positron Emission Tomography (PET) has wide applications in cardiology, neurology, and oncology studies. To enable the quantitative nature of PET imaging, accurate corrections (e.g., attenuation correction and motion correction) are needed. Due to various physical degradation factors and limited counts received, the signal-to-noise ratio (SNR) and resolution of PET is low, which comprises its clinical values in diagnosis, staging and treatment monitoring. In this talk, I will introduce my works of further improving PET correction and image quality through deep learning-based image reconstruction and analysis.
Kuang Gong is an Assistant Professor of Radiology at Massachusetts General Hospital and Harvard Medical School. He received his M.S. degree in Statistics and Ph.D. degree in Biomedical Engineering from University of California, Davis in 2015 and 2018, respectively. His areas of expertise include medical imaging, deep learning, data science, and image processing. His research goal is to combine deep learning, medical imaging, and data science to further improve the diagnosis and treatment of various diseases, such as Alzheimer’s disease (AD) and cancer. To achieve this, his current research is conducted in three directions: deep learning-based image reconstruction and analysis, clinical task-driven deep learning, and multi-modality information integration for precision medicine. He has published 32 journal papers and is the Principal Investigator of research grants from NIH. He received the Bruce H. Hasegawa Young Investigator Medical Imaging Science Award from the IEEE Nuclear and Plasma Sciences Society in 2021 for contributions to machine learning-based PET image reconstruction, denoising and attenuation correction.