Deep Learning based Imaging Modality Translation
Dr. Gobert Lee is a lecturer and a researcher in Data Science and Machine Learning in the College of Science and Engineering at Flinders University, Adelaide, Australia. She is an active member of the Flinders Medical Device Research Institute and is a project lead of the Freemasons Centre for Male Health and Wellbeing, Flinders Research Program. Her main research interest is in Machine Learning and Medical Image Analysis and Decision Support. She has been a chief investigator and co-investigator on internal and external grant projects including projects on early breast cancer detection, multiple-organ segmentation, paediatric anatomical model generation, organs-at-risk contouring on head CT for radiotherapy planning, prostate cancer treatment decision support and deep learning based imaging modality translation.
Abstract: Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are the two most commonly used imaging modalities in clinical settings. CT and MRI each have their strength and weakness. Specifically, CT imaging is widely available, quick to perform, cost-effective, provides excellent spatial resolution, and offers good visualization of the bony anatomy and calcific structures. On the other hand, MRI offers excellent soft tissue contrast including neural tissue and brain tissue. In many clinical applications, CT and MRI are often used in tandem to complement each other. The research in imaging modality translation has been attracting a lot of interest in recent years. This talk showcase some preliminary investigation in our research group.