Prof. Jinman Kim – The University of Sydney, Australia
Bio: Jinman Kim is a Professor of Computer Science at the University of Sydney. He received his PhD from the University of Sydney in 2006, and was an Australian Research Council (ARC) Postdoctoral Research Fellow at the University of Sydney and then a Marie Curie Senior Research Fellow at the University of Geneva, prior to joining the University of Sydney in 2013 as a Faculty member. He co-leads the Faculty of Engineering’s Digital Health Imaging, which is a pillar of the Digital Science Initiatives (DSI), with the vision to combine the Faculty’s expertise in AI applied medical image analysis. He is also the Director of the Telehealth and Technology Center, Nepean hospital. Prof Kim’s research is in the application of machine learning for biomedical image analysis and visualization. His focus is on cross-model and multi-modal learning, which includes biomedical visual-language representations, image-omics, multi-modal data processing, and biomedical mixed reality technologies. He established and leads the Biomedical Data Analysis and Visualisation (BDAV) Lab at the School of Computer Science. He has produced a number of publications in this field and received multiple competitive grants and scientific recognitions.
THE PRESENTATION
Title: RibMR – A Mixed Reality System for Rib Fracture Localization in Surgical Stabilization of Rib Fractures
Abstract: In the context of surgical stabilization of rib fractures (SSRF), the current standard relies on preoperative CT imaging and complementary methods like ultrasound (US) for rib fracture localization. While mixed reality (MR) holds promise in enhancing fracture localization, its application in SSRF faces distinctive challenges. This study aims to present an MR-based visualization system tailored to SSRF requirements for rib fracture localization. In this talk, I will present our ongoing work in RibMR – a head mounted MR system designed to project patient-specific 3D models (holograms) onto the patient’s bone structures in the operating room. RibMR enables rib fracture localization in relation to the patient’s anatomy without modifications to the imaging workflows or the installation of stationary infrastructure. We conducted comprehensive evaluations of RibMR using phantom, preclinical, and clinical case studies, comparing it to the conventional US-based clinical practice. RibMR offers an accurate and fast rib fracture localization. These attributes position it as a promising and alternative for visualizing and localizing rib fractures, not only in SSRF but also in other clinical settings.