SCH: INT: A Virtual Surgery Simulator to Accelerate Medical Training in Cardiovascular Disease

点击翻译按钮获取中文摘要

The objective of the parent proposal is to devise and deploy an integrated virtual surgery simulator to transform training and surgical planning in cardiovascular medicine. By advancing science in graphics, visualization and real-time simulations, and interfacing with virtual reality (VR) technology, we will offer clinical trainees insight into cardiac physiology and pathology, accelerating knowledge acquisition and intuition-building in ways not possible with current tools. Despite recent advances in cardiovascular patient-specific modeling and blood flow simulation, current virtual surgery capabilities are limited to cumbersome by-hand model manipulations and blood flow simulations run on high-performance computing clusters for days at a time. These complexities preclude hands- on use by clinicians and often limit the models to a small cohort of anatomic designs. To drive this technology, the parent proposal contained the following specific aims: 1) Develop computer-graphics tools for efficient model manipulation, 2) Integrate reduced-order modeling with visualization to create a real-time interactive experience, and 3) Develop and deploy an interactive VR educational environment for medical students and clinical trainees. In support of these efforts, in this supplement proposal we will ready the Vascular Model Repository (VMR) for use in artificial intelligence (AI) and machine / deep learning (ML/DL) applications. The VMR is an open database of medical image data, segmented vascular models, and blood flow simulation results developed with support from the National Library of Medicine. We will use the VMR to support two major AI/ML efforts in the community. First, we will greatly accelerate anatomic model construction by DL for image segmentation, overcoming a major bottle neck to studies with large cohorts of patients. Second, we will develop physics-informed ML methods to drastically reduce current lengthy simulation times and provide fast and interactive feedback for surgical and interventional planning. This will produce fast and deployable ``digital twins'' that can provide interactive feedback to clinicians; these methods will be in direct support of the parent proposal and of general interest to the field. The supplement proposal contains three specific aims: 1) To ready the VMR for AI/ML by users who are not domain experts and spark interest in cardiovascular applications in the ML community, 2) To run community challenges in image segmentation and physics-informed ML at a major international meeting to identify best in class ML/DL methods, and 3) To demonstrate ML/DL methods in interactive surgical planning applications by integrating efforts with the parent proposal. We will disseminate our findings, methods, data, and source code to the research community via the open source SimVascular software project and the open data VMR. Our team brings together expertise in cardiovascular biomechanics and finite element modeling, computer graphics and reduced order modeling, physics informed ML, and development of open source and open data resources for the scientific community.