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

母公司提案的目标是设计和部署一个集成的虚拟手术模拟器，以实现 心血管内科的培训和手术计划。通过推动图形、可视化和 实时模拟，并与虚拟现实(VR)技术交互，我们将为临床实习生提供对 心脏生理学和病理学，以一种不可能的方式加速知识获取和直觉建立 使用当前的工具。尽管最近在心血管患者特定的建模和血流模拟方面取得了进展， 目前的虚拟手术能力仅限于繁琐的手工模型操作和血液流动 模拟一次在高性能计算集群上运行数天。这些复杂性排除了手- 供临床医生使用，并经常将模型限制为一小部分解剖设计。为了推动这项技术， 父提案包含以下具体目标：1)开发高效模型的计算机图形工具 操作，2)将降阶建模与可视化相结合，以创建实时交互体验， 3)为医学生和临床实习生开发和部署交互式VR教育环境。 为了支持这些努力，在本补充提案中，我们将为血管模型存储库(VMR)做好准备 用于人工智能(AI)和机器/深度学习(ML/DL)应用。VMR是一个开放的数据库 医学图像数据、分段血管模型和在支持下开发的血流模拟结果 来自国家医学图书馆。我们将使用VMR来支持社区中两个主要的AI/ML工作。 首先，我们将极大地加速利用动态链接库进行图像分割的解剖模型的建立，克服了主要的 对于大量患者的研究来说，这是一个瓶颈。其次，我们将开发物理知情的ML方法来 大幅减少当前冗长的模拟时间，并为外科和 介入计划。这将产生能够提供互动反馈的快速且可部署的“数字双胞胎” 对临床医生来说；这些方法将直接支持父母的建议，并引起现场的普遍关注。 补充方案包含三个具体目标：1)使VMR为非AI/ML的用户做好准备 领域专家和激起ML社区对心血管应用的兴趣，2)运行社区 图像分割和物理方面的挑战-在一个重要的国际会议上了解ML，以确定最佳的 ML/DL类方法，以及3)演示ML/DL方法在交互式手术规划中的应用 将努力与父提案相结合。我们将把我们的发现、方法、数据和源代码传播到 研究社区通过开源的SimVculate软件项目和开放数据VMR。我们的团队 汇集了心血管生物力学和有限元建模、计算机图形学和 降低阶数建模、物理信息的ML，以及开发开源和开放数据资源 科学界。

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.