Improving cardiovascular image-based phenotyping using emerging methods in artificial intelligence

使用人工智能新兴方法改善基于心血管图像的表型分析

• 批准号: 10379426
• 负责人: Rima Arnaout
• 金额: $ 80.89万
• 依托单位: UNIVERSITY OF CALIFORNIA, SAN FRANCISCO
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-04-01 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10379426
• 关键词: Abdomen; Address; Adult; Age; Aging; Apical; Artificial Intelligence; Biometry; Birth; Cardiac; Cardiovascular Diseases; Cardiovascular system; Clinical; Clinical Research; Collection; Communities; Complex; Congenital Abnormality; Data; Data Science; Data Set; Detection; Diagnosis; Diagnostic; Early Diagnosis; Early treatment; Echocardiography; Environment; Evaluation; Face; Fetal Heart; Goals; Heart; Heart Abnormalities; Human; Image; Image Analysis; Informatics; Label; Lead; Lesion; Life; Literature; Machine Learning; Measurement; Medical Imaging; Methods; Modeling; Morbidity - disease rate; Outcome; Patients; Pattern; Pattern Recognition; Performance; Phenotype; Physicians; Population; Pregnant Women; Provider; Psyche structure; Quality Control; Rare Diseases; Reproducibility; Research; Secure; Structure; Supervision; Surveys; Techniques; Testing; Time; Trachea; Training; Translating; Ultrasonography; Variant; Work; base; cardiovascular imaging; clinical center; clinical decision-making; clinical imaging; clinically relevant; comorbidity; computerized data processing; congenital heart disorder; cost; data curation; data harmonization; deep learning; deep learning algorithm; deep learning model; design; detection test; diagnostic accuracy; disease diagnosis; fetal; fetal diagnosis; heart imaging; image guided; image processing; imaging study; improved; insight; learning network; machine learning algorithm; machine learning method; model design; mortality; multidisciplinary; multimodality; neural network; neural network architecture; novel; patient population; precision medicine; prenatal; prevent; programs; repaired; screening; standard of care; statistics; theories; tool; ultrasound

Summary / Abstract Objective — The goal of this proposal is to develop and optimize novel deep learning (DL) assisted approaches to improve diagnosis and clinical decision-making for congenital heart disease (CHD). This will be achieved by using DL, machine learning (ML), and related methods to extract diagnosis, biometric characterizations, and other information from fetal ultrasound imaging. Notably, this work includes a clinical translational evaluation of these methods in a population-wide imaging collection spanning two decades, tens of thousands of patients, and several clinical centers. Background — Despite clear and numerous benefits to prenatal detection of CHD and an ability for fetal ultrasound to detect over 90% of CHD lesions in theory, in practice the fetal CHD detection rate is closer to 50%. Prior literature suggests a key cause of this startling diagnosis gap is suboptimal acquisition and interpretation of fetal heart images. DL is a novel data science technique that is proving excellent at pattern recognition in images. DL models are a function of the design and tuning of a neural network architecture, and the curation and processing of the image data used to train the network. Preliminary Studies — We have assembled a multidisciplinary team of experts in echocardiography and CHD (Drs. Grady, Levine, and Arnaout), DL and data science (Drs. Keiser, Butte and Arnaout), and statistics and clinical research (Drs. Arnaout and Grady) and secured access to tens of thousands of multicenter (UCSF and six other centers), multimodal fetal imaging studies. We have created a scalable image processing pipeline to transform clinical studies into image data ready for computing. We have designed and trained DL models to find key cardiac views in fetal ultrasound, calculate standard and advanced fetal cardiac biometrics from those views, and distinguish between normal hearts and certain CHD lesions. Hypothesis — While DL is powerful, much work is still needed to adapt it for clinical imaging and to translate it toward clinically relevant performance in patient populations. We hypothesize that an integrated ensemble DL/ML approach can lead to vast improvements in fetal CHD diagnosis. Aims — To this end, the main Aims of this proposal are (1) to develop and optimize neural network architectures and efficient data inputs to relieve key performance bottlenecks for DL in fetal CHD; and (2) to deploy DL models population-wide to evaluate their ability to improve diagnosis, biometric characterization, and precision phenotyping over the current standard of care. Our methods include DL/ML algorithms and retrospective imaging analysis. Environment and Impact — This work will be supported in an outstanding environment for research at the crossroads of data science, cardiovascular and fetal imaging, and translational informatics. The work proposed will provide valuable tools and insight into designing and evaluating both the data and the algorithms for DL on imaging for clinically relevant goals, and will lay important groundwork for DL-assisted phenotyping for both clinical use and precision medicine research.

摘要 /摘要 目标 - 该提案的目的是开发和优化新颖的深度学习（DL）辅助方法 改善先天性心脏病（CHD）的诊断和临床决策。这将通过 使用DL，机器学习（ML）和相关方法来提取诊断，生物特征特征和 来自胎儿超声成像的其他信息。值得注意的是，这项工作包括对 这些方法在整个人口的成像集中，跨越了二十年，成千上万的患者，以及 几个临床中心。背景 - 尽管明确且在产前检测冠心病和许多好处 从理论上讲，胎儿超声检测超过90％的CHD病变的能力，实际上是胎儿CHD检测 费率接近50％。先前的文献表明，这种起始诊断差距的关键原因是次优获取 和胎儿心脏图像的解释。 DL是一种新颖的数据科学技术，证明在模式下很棒 图像中的识别。 DL模型是神经网络体系结构的设计和调整的函数， 用于训练网络的图像数据的策展和处理。初步研究 - 我们有 组建了一个超声心动图专家和冠心病专家（Grady，Levine和Arnaout博士）的多学科团队， DL和数据科学（Keizer博士，Butte和Arnaout）以及统计和临床研究（Arnaout和Arnaout博士 Grady）并获得了数以万计的多中心（UCSF和其他六个中心），多模式胎儿的安全访问权限 成像研究。我们创建了可扩展的图像处理管道，以将临床研究转化为图像 准备计算的数据。我们设计和训练了DL模型，以在胎儿超声波中找到关键的心脏视野， 计算标准和晚期胎儿心脏生物识别技术与这些观点，并区分正常 心脏和某些CHD病变。假设 - 尽管DL功能强大，但仍需要做很多工作以适应它 临床成像，并将其转化为患者人群中临床相关的表现。我们假设 集成的集合DL/ML方法可以导致胎儿冠心病诊断的大幅改善。目标 - 为此，该提案的主要目的是（1）开发和优化神经网络体系结构和 有效的数据输入以挽救胎儿冠心病中DL的关键性能瓶颈； （2）部署DL模型 在人群范围内评估他们改善诊断，生物特征表征和精度的能力 在当前护理标准上进行表型。我们的方法包括DL/ML算法和回顾性成像 分析。环境和影响 - 这项工作将在杰出的研究环境中得到支持 在数据科学，心血管和胎儿成像的十字路口，并翻译信息。工作 拟议的将为设计和评估数据和算法提供宝贵的工具和洞察力 用于成像临床相关目标的DL，并将为DL辅助表型奠定重要的基础。 临床使用和精密医学研究。