Plaque Risk Stratification Using Routinely Available CCTA to Optimize Therapeutic Decision-making in Patients with Known or Suspected Coronary Artery Disease

使用常规 CCTA 进行斑块风险分层，优化已知或疑似冠状动脉疾病患者的治疗决策

• 批准号: 9752019
• 负责人: Andrew John Buckler
• 金额: $ 99.15万
• 依托单位: ELUCID
• 依托单位国家: 美国
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-09-01 至 2022-04-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9752019
• 关键词: Adverse event; Angiography; Applications Grants; Arterial Fatty Streak; Artificial Intelligence; Atherosclerosis; Beds; Biological; Caliber; Cardiac; Cardiovascular Diseases; Cardiovascular system; Categories; Characteristics; Classification; Client; Clinical; Clinical Trials; Collection; Complement; Computer Assisted; Computer software; Consensus; Consumption; Coronary; Coronary Arteriosclerosis; Data; Data Set; Decision Making; Detection; Devices; Diagnosis; Digital Imaging and Communications in Medicine; Electronic Health Record; Event; Goals; Grant; Histologic; Histology; Image; Image Analysis; Individual; Industry; Label; Length; Lesion; Link; Lipids; Manuals; Mathematics; Measurement; Methods; Modality; Modeling; Molecular; Morphology; Nature; Necrosis; Pathologist; Pathway interactions; Patients; Performance; Phenotype; Procedures; Process; Protocols documentation; Reader; Reporting; Research; Resolution; Retrospective cohort; Risk; Risk stratification; Rupture; Sampling; Secondary to; Severities; Solid; Specimen; Speed; Stenosis; Structure; System; Technology; Therapeutic; Time; Tissues; Translating; Validation; X-Ray Computed Tomography; base; bioimaging; biomarker panel; cohort; convolutional neural network; cost; deep learning; improved; improved outcome; in vivo; innovation; meetings; multi-scale modeling; noninvasive diagnosis; novel; novel strategies; novel therapeutics; prevent; prospective; quantitative imaging; reconstruction; research clinical testing; risk prediction model; scale up; software as a service; standard of care; success; tool

Project Summary/Abstract New treatments have been revolutionary in improving outcomes over the last 30 years, yet cardiovascular disease still exerts a $320B annual burden on the US economy. Increasing evidence is showing that Coronary CT Angiography (CCTA) may be an ideal modality to fill gaps in understanding the extent and rate of progression coronary artery disease. But despite the apparent promise of CCTA, there are barriers that prevent realizing the improvement that it theoretically provides. Currently available solutions do not overcome the barriers – a new approach is needed. Elucid Bioimaging has developed an image analysis software product vascuCAP (CAP stands for Computer Aided Phenotyping) to accurately quantify structural and morphological characteristics of plaque tissues linked to plaque rupture vulnerability. Fundamental to our approach is validated, objective quantitative accuracy; vascuCAP enjoys the most robust and well documented analytic validation of any plaque morphology software available. vascuCAP is the only system to mitigate specific issues in CT reconstruction known to effect accurate measurement of atherosclerotic plaque composition in routinely acquired CTA; it is the only system to effectively leverage objective tissue characterization validated by histology across multiple arterial beds; it achieves an effective resolution with routinely acquired CTA in the same ballpark as IVUS VH, based on solid mathematics principles that respect the Nyquist-Shannon sampling theorem; and it innovates by novel reporting that expresses the findings in a manner that fits efficiently into existing clinical workflows. vascuCAP has been implemented in a client-server model supporting SaaS. Working from our strong current device clearances, this research strategy is developed based on approved meeting notes from the FDA pre-submission process Phenotype classification claims to be cleared through direct De Novo pathway on the basis of accurately determining the class from in vivo CTA data relative to pathologist annotation on ex vivo specimen data. Risk prediction claims: validate ability to predict adverse events at one year, adding the IFU according to the direct De Novo pathway, One does not strictly depend on the other.This proposal is innovative in dealing with two fundamental limitations of the application of artificial intelligence and deep learning to the analysis of atherosclerosis imaging data. This proposal maximizes use of available retrospective data while putting in place the necessary structure for prospective validation and scale up. This proposal further develops vascuCAP as a tool that may reduce cost and length of clinical trials. While out of scope for this grant, it is important to also note that vascuCAP is innovative in its ability to support multi-scale modeling across cellular/molecular-level analyses and macroscopic manifestation. Also, vascuCAP’s quantitative ability makes it ideal for analysis of more advanced CT imaging protocols. These attributes complement and support the proposed objectives.

项目总结/文摘