Deep Learning Assessment of the Right Ventricle: Function, Etiology, and Prognosis

右心室的深度学习评估：功能、病因和预后

• 批准号: 10756662
• 负责人: David Ouyang
• 金额: $ 24.9万
• 依托单位: CEDARS-SINAI MEDICAL CENTER
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-02-01 至 2026-01-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10756662
• 关键词: Address; Advisory Committees; Architecture; Arrhythmogenic Right Ventricular Dysplasia; Award; Cardiovascular Diseases; Cardiovascular system; Categories; Cause of Death; Cessation of life; Characteristics; Classification; Clinical; Communities; Computer Vision Systems; Coronary Arteriosclerosis; Data; Data Science; Data Set; Derivation procedure; Diagnosis; Disease; Disease Outcome; Dissection; Early Diagnosis; Echocardiography; Engineering; Epidemiology; Etiology; Evaluation; Framingham Heart Study; Future; Goals; Health system; Healthcare; Healthcare Systems; Heart failure; Heterogeneity; Hospitals; Human; Image; Incidence; Learning; Machine Learning; Maps; Measures; Medical Imaging; Medicine; Mentors; Modeling; Morbidity - disease rate; Morphology; Motion; Multi-Ethnic Study of Atherosclerosis; Nature; Outcome; Participant; Patients; Pattern; Performance; Phase; Phenotype; Physicians; Prognosis; Program Development; Prospective cohort; Pulmonary Embolism; Research; Research Personnel; Right Ventricular Dysfunction; Right Ventricular Function; Right ventricular structure; Risk; Risk Factors; Sampling; Scientist; Semantics; Standardization; Stroke; Techniques; Training; Translational Research; United States; Validation; Variant; Ventricular; cardiovascular imaging; cardiovascular risk factor; career; career development; cohort; community based care; computer science; cost; deep learning; deep learning algorithm; deep learning model; deep neural network; design; hands on research; healthcare community; heart imaging; image translation; imaging science; improved; mortality; neural network; neural network architecture; novel; outcome prediction; performance tests; population based; predictive modeling; prognostic; programs; public health relevance; pulmonary arterial hypertension; skills; spatiotemporal; statistics; study population; success; temporal measurement

ABSTRACT Heart failure imposes a tremendous burden of morbidity and mortality, costing the United States in excess of $31 billion annually. An increasingly recognized major determinant of outcomes in heart failure is right ventricular (RV) dysfunction. However, the nature and character of RV contribution to cardiovascular outcomes remains poorly understood, largely due to the imprecision of imaging and interpretation of RV morphology and function. Echocardiography, with its high temporal resolution and low cost of acquisition, serves as frontline cardiovascular imaging and a mainstay in approaches to assessing RV morphology and function. However, echocardiographic imaging of the RV is limited by factors that include technical variation in image acquisition and heterogeneity in image assessment as well as overall interpretation. We postulate that deep learning based phenotyping can offer the ability to not only more precisely characterize RV function but also classify RV imaging phenotypes according to etiologic disease states and, even further, refine prognostic evaluations of future cardiovascular risk. Therefore, in Aim 1, we will use video-based deep learning segmentation models to assess RV function, evaluate its cross-sectional relation with a range of expert-measured parameters, and examine its variation in the context of patient characteristics derived from large hospital-based cohorts. In Aim 2, we will use video-based deep learning models to produce imaging-based classification of RV disease and assess the ability of unsupervised approaches to classify RV dysfunction into various categories of disease etiology. In Aim 3, we will use models developed in part from training in Aims 1 and 2 to predict major cardiovascular outcomes including heart failure in addition to coronary artery disease, stroke, and cardiovascular death in both hospital- based and community-based cohorts. The overarching goal of this proposal is to improve the precision and standardization of RV phenotyping and determine the extent to which deep learning models can augment human assessment of the RV. This research will be accomplished in the setting of a comprehensive career development program designed to provide the candidate with the skills needed to become an independent physician-scientist in cardiovascular medicine and translational imaging science. An advisory committee of established scientists/mentors in the fields of cardiac imaging, deep learning, data science, and translational science will guide the candidate in his transition to scientific independence over the course of the award period.

摘要 心力衰竭造成了巨大的发病率和死亡率负担，使美国损失超过 每年310亿美元。一个日益公认的心力衰竭结局的主要决定因素是右室 (RV)功能障碍。然而，RV对心血管结果的贡献的性质和特征仍然存在 了解较少，很大程度上是由于对右室形态和功能的成像和解释不精确。 超声心动图具有较高的时间分辨率和较低的获取成本，是心血管疾病的一线治疗手段。 成像是评估RV形态和功能的主要方法。然而，超声心动图 房车的成像受到一些因素的限制，包括图像采集的技术差异和 形象评估以及整体解读。我们假设基于深度学习的表型分析可以 不仅能够更精确地表征RV功能，还可以对RV成像表型进行分类 根据病因疾病状态，甚至进一步完善对未来心血管疾病的预后评估 风险。因此，在目标1中，我们将使用基于视频的深度学习分割模型来评估RV功能， 用一系列专家测量的参数评估它的横截面关系，并检查它在 患者特征的背景源自以医院为基础的大型队列。在目标2中，我们将使用基于视频的 深度学习模型，以产生基于成像的RV疾病分类，并评估 无人监督的方法将RV功能障碍归类为各种疾病病因。在目标3中，我们 将使用在AIMS 1和AIMS 2的训练中开发的部分模型来预测主要心血管结果 包括心力衰竭，以及两家医院的冠心病、中风和心血管死亡- 以社区为基础的队列和基于社区的队列。这项建议的总体目标是提高精度和 RV表型的标准化，并确定深度学习模型可以在多大程度上增强人类 对房车的评估。这项研究将在全面职业发展的背景下完成 旨在为候选人提供成为独立内科医生-科学家所需技能的计划 心血管医学和转译成像科学。成立了一个咨询委员会 心脏成像、深度学习、数据科学和翻译科学领域的科学家/导师将 在获奖期内，指导候选人向科学独立过渡。