A novel computing framework to automatically process cardiac valve image data and predict treatment outcomes

一种新颖的计算框架，可自动处理心脏瓣膜图像数据并预测治疗结果

• 批准号: 9973167
• 负责人: Wei Sun
• 金额: $ 38.36万
• 依托单位: GEORGIA INSTITUTE OF TECHNOLOGY
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-06-01 至 2022-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9973167
• 关键词: 3-Dimensional; Adverse event; Algorithms; Anatomy; Area; Artificial Intelligence; Attention; Biomechanics; Biomedical Computing; Clinical; Clinical Engineering; Complex; Computer Analysis; Computer Models; Computer Simulation; Consumption; Coronary Occlusions; Data; Data Analyses; Data Set; Development; Device Designs; Device or Instrument Development; Devices; Dictionary; Disease; Elements; Evaluation; Extravasation; Feedback; Finite Element Analysis; Generations; Geometry; Goals; Guidelines; Heart Valves; Hospitals; Hour; Human; Image; Intervention; Laboratories; Language; Learning; Left ventricular structure; Machine Learning; Manuals; Methods; Mitral Valve; Modeling; Outcome; Output; Patient-Focused Outcomes; Patients; Performance; Plant Roots; Postoperative Period; Problem Sets; Procedures; Process; Property; Research Personnel; Response Elements; Running; Rupture; Sampling; Shapes; Statistical Data Interpretation; Stents; Structure; Techniques; Testing; Thinness; Time; Tissue Model; Training; Translations; Treatment outcome; Uncertainty; Variant; X-Ray Computed Tomography; algorithm training; aortic valve; aortic valve replacement; ascending aorta; base; calcification; clinical application; clinical imaging; clinical practice; clinically translatable; deep learning; deep neural network; heart function; heart imaging; imaging modality; improved; innovation; machine learning algorithm; models and simulation; novel; patient population; personalized approach; population based; prevent; reconstruction; research clinical testing; simulation; speech recognition; time resolved data; two-dimensional; virtual; virtual clinical trial

PROJECT SUMMARY There is a massive amount of clinical three-dimensional (3D) cardiac image data available today in numerous hospitals, but such data has been considerably underutilized in both clinical and engineering analyses of cardiac function. These 3D data offers unique and valuable information, allowing researchers to develop innovative, personalized approaches to treat diseases. Furthermore, using these 3D datasets as input to computational models can facilitate a population-based analysis that can be used to quantify uncertainty in treatment procedures, and can be utilized for virtual clinical trials for innovative device development. However, there are several critical technical bottlenecks preventing simulation-based clinical evaluation a reality: 1) difficulty in automatic 3D reconstruction of thin complex structures such as heart valve leaflets from clinical images, 2) computational models are constructed without mesh correspondence, which makes it challenging to run batch simulations and conduct large patient population data analyses due to inconsistencies in model setups, and 3) computing time is long, which inhibits prompt feedback for clinical use. A potential paradigm-changing solution to the challenges is to incorporate machine learning algorithms to expedite the geometry reconstruction and computational analysis procedures. Therefore, the objective of this proposal is to develop a novel computing framework, using advanced tissue modeling and machine learning techniques, to automatically process pre-operative clinical image data and predict post-operative clinical outcomes. Transcatheter aortic valve replacement (TAVR) intervention will serve as a testbed for the modeling methods. In Aim 1, we will develop novel shape dictionary learning (SDL) based methods for automatic reconstruction of TAVR patient aortic valves. Through the modeling process, mesh correspondence will be established across the patient geometric models. The distribution and variation of TAVR patient geometries will be described by statistical shape models (SSMs). In Aim 2, population-based FE analysis of the TAVR procedure will be conducted on thousands of virtual patient models generated by the SSMs (Aim 1). A deep neural network (DNN) will be developed and trained to learn the relationship between the TAVR FE inputs and outputs. Successful completion of this study will result in a ML-FE surrogate for TAVR analysis, combining the automated TAVR patient geometry reconstruction algorithms and the trained DNN, to provide fast TAVR biomechanics analysis without extensive re-computing of the model. Furthermore, the algorithms developed in this study can be generalized for other applications and devices.

项目概要 目前有大量临床三维 (3D) 心脏图像数据可供使用 许多医院，但这些数据在临床和工程分析中都没有得到充分利用 心脏功能。这些 3D 数据提供了独特且有价值的信息，使研究人员能够开发 创新、个性化的疾病治疗方法。此外，使用这些 3D 数据集作为输入 计算模型可以促进基于人群的分析，可用于量化不确定性 治疗程序，并可用于创新设备开发的虚拟临床试验。然而， 有几个关键的技术瓶颈阻碍了基于模拟的临床评估成为现实：1) 临床上难以自动 3D 重建薄的复杂结构，例如心脏瓣膜小叶 图像，2）计算模型是在没有网格对应的情况下构建的，这使得它具有挑战性 由于模型设置不一致，运行批量模拟并进行大量患者群体数据分析， 3)计算时间长，不利于临床使用的及时反馈。 应对挑战的潜在范式改变解决方案是结合机器学习算法 加快几何重建和计算分析程序。因此，本次活动的目的 提案是利用先进的组织建模和机器学习开发一种新颖的计算框架 技术，自动处理术前临床图像数据并预测术后临床 结果。经导管主动脉瓣置换术（TAVR）干预将作为模型的测试平台 方法。在目标 1 中，我们将开发基于形状字典学习 (SDL) 的新颖方法，用于自动 TAVR 患者主动脉瓣重建。通过建模过程，网格对应关系将是 建立跨患者的几何模型。 TAVR 患者几何形状的分布和变化将 通过统计形状模型（SSM）来描述。在目标 2 中，基于人群的 TAVR 手术有限元分析 将在 SSM 生成的数千个虚拟患者模型上进行（目标 1）。深度神经网络 (DNN) 将被开发和训练以了解 TAVR FE 输入和输出之间的关系。 这项研究的成功完成将产生用于 TAVR 分析的 ML-FE 替代品，结合自动化 TAVR 患者几何重建算法和经过训练的 DNN，提供快速的 TAVR 生物力学 无需对模型进行大量重新计算即可进行分析。此外，本研究开发的算法可以 可以推广到其他应用程序和设备。