Integrating Artificial Intelligence for Optimal Analysis of CardiacPET/CT

集成人工智能以优化心脏 PET/CT 分析

• 批准号: 10708921
• 负责人: Marcelo F DI CARLI
• 金额: $ 72.04万
• 依托单位: CEDARS-SINAI MEDICAL CENTER
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-22 至 2026-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10708921
• 关键词: Adoption; Anatomy; Artificial Intelligence; Atherosclerosis; Automation; Blood flow; Cardiac; Cardiometabolic Disease; Cause of Death; Chest; Clinical; Clinical Data; Collaborations; Complex; Computer software; Computing Methodologies; Coronary; Coronary Arteriosclerosis; Data; Detection; Development; Diabetes Mellitus; Diagnostic; Diffuse; Disease; Dose; Engineering; Fatty acid glycerol esters; Goals; Growth; Hybrids; Image; Image Analysis; Institution; Intelligence; Ischemia; Joints; Kinetics; Knowledge; Measurement; Measures; Methods; Microvascular Dysfunction; Modality; Modeling; Myocardial; Myocardial perfusion; Nature; Obesity Epidemic; Patient Care; Patient risk; Patients; Performance; Perfusion; Physicians; Positron-Emission Tomography; Protocols documentation; Psyche structure; Quality Control; Radioisotopes; Radiology Specialty; Research; Research Personnel; Risk Assessment; Scanning; Site; Statistical Models; Survival Analysis; Technical Expertise; Techniques; Technology; Testing; Translating; Visual; Widespread Disease; Work; adverse outcome; artificial intelligence algorithm; artificial intelligence method; attenuation; biomedical imaging; cardiovascular imaging; clinical application; clinical imaging; coronary artery calcium; deep learning; diagnostic accuracy; disability; disease diagnosis; disorder risk; diverse data; experience; heart imaging; image processing; imaging Segmentation; imaging biomarker; imaging modality; improved; medical specialties; multidisciplinary; multimodal data; multimodality; new technology; novel; outcome prediction; perfusion imaging; prognostic; prototype; risk stratification; single photon emission computed tomography; supervised learning; tool; unsupervised learning

PROJECT SUMMARY Coronary artery disease (CAD) is the leading cause of death and disability in the US and globally. The epidemic of obesity, diabetes, and cardiometabolic disease is changing the nature of CAD, with diffuse and microvascular disease emerging as key drivers of adverse outcomes. Radionuclide myocardial perfusion imaging is the most widely used modality for CAD assessment and is still primarily performed with SPECT. But SPECT evaluates only relative perfusion and is inherently insensitive in the setting of diffuse or microvascular disease. PET, with its unique ability to accurately quantify absolute myocardial blood flow, allows robust detection of obstructive CAD, diffuse atherosclerosis, balanced ischemia, and coronary microvascular dysfunction. Cardiac PET is also always obtained with additional chest CT for attenuation correction purposes. However, this modality requires a high level of on-site technical expertise to maximize its broad capabilities. We have applied highly efficient, image-based artificial intelligence (AI) approaches extensively to SPECT and CT, demonstrating improved diagnostic accuracy and risk stratification. These tools can be harnessed to enhance the utility of cardiac PET/CT. We propose to efficiently translate the latest AI advances and our recent SPECT developments to fully automate cardiac PET/CT analysis, including novel tools for quality control, high- performance image segmentation, new quantitative variables, and direct outcome prediction from images, using PET/CT data from multiple centers. The overall aim is to develop is to develop practical AI algorithms for comprehensive cardiac PET/CT analysis and to validate them in a multi-center setting. For this work, we propose the following 3 specific aims: (1) To develop and test automated end-to-end PET quantification, (2) To develop and test automated end-to-end chest CT quantification, (3) To develop and validate explainable AI models for enhanced patient assessment from images and clinical data, employing latest advances in survival analysis, supervised and unsupervised learning, and knowledge transfer. This research will result in personalized tools, which will improve the accuracy of patient assessment by PET/CT beyond what is possible by the current practice of subjective interpretation and mental integration of diverse data. Explainable methods combining image and clinical data to make AI conclusions more tangible will allow clinical adoption of this technology. The new tools can dramatically simplify PET/CT protocols, reduce subjectivity, reduce burden on the physicians, and maximize the information derived from the multimodal scans. They will fit directly into existing workflows, facilitating deployment in diverse clinical settings. The new AI methods for image analysis and explainable integration of multimodality data will generalize to other diseases and problems in biomedical imaging.

项目概要 冠状动脉疾病（CAD）是美国和全球死亡和残疾的主要原因。流行 肥胖、糖尿病和心脏代谢疾病的发病率正在改变 CAD 的性质，具有弥漫性和微血管性 疾病正在成为不良后果的关键驱动因素。放射性核素心肌灌注显像是最 广泛使用的 CAD 评估方式，目前仍主要通过 SPECT 进行。但 SPECT 评估 仅相对灌注，并且在弥漫性或微血管疾病的情况下本质上不敏感。 PET，具有 其独特的准确量化绝对心肌血流量的能力，可以稳健地检测梗阻 CAD、弥漫性动脉粥样硬化、平衡缺血和冠状动脉微血管功能障碍。心脏PET也 总是通过额外的胸部 CT 获得，用于衰减校正目的。然而，这种模式需要 高水平的现场技术专业知识，以最大限度地发挥其广泛的能力。 我们已将高效、基于图像的人工智能 (AI) 方法广泛应用于 SPECT 和 CT，显示诊断准确性和风险分层得到提高。这些工具可以用来 增强心脏 PET/CT 的实用性。我们建议有效地转化最新的人工智能进展和我们最近的成果 SPECT 的发展使心脏 PET/CT 分析完全自动化，包括用于质量控制、高 性能图像分割、新的定量变量以及图像的直接结果预测，使用 来自多个中心的 PET/CT 数据。 总体目标是开发用于综合心脏 PET/CT 分析的实用 AI 算法 并在多中心环境中验证它们。对于这项工作，我们提出以下 3 个具体目标：（1） 开发和测试自动化端到端 PET 定量，(2) 开发和测试自动化端到端胸部 CT 量化，(3) 开发和验证可解释的 AI 模型，以增强患者评估 图像和临床数据，采用生存分析、监督和非监督学习的最新进展， 和知识转移。 这项研究将产生个性化工具，从而提高 PET/CT 对患者评估的准确性 超出了目前主观解释和不同的心理整合实践所能做到的 数据。结合图像和临床数据的可解释方法将使人工智能结论更加具体 临床采用该技术。新工具可以极大地简化 PET/CT 方案，减少 主观性，减轻医生的负担，并最大限度地利用多模态扫描获得的信息。 它们将直接融入现有的工作流程，促进在不同临床环境中的部署。新的人工智能 图像分析和可解释的多模态数据整合方法将推广到其他疾病 以及生物医学成像中的问题。

项目成果

Coronary Microvascular Function Following Severe Preeclampsia.

严重先兆子痫后的冠状动脉微血管功能。

• 发表时间: 2024-04-02
• 作者: Honigberg, Michael C;Economy, Katherine E;Pabón, Maria A;Wang, Xiaowen;Castro, Claire;Brown, Jenifer M;Divakaran, Sanjay;Weber, Brittany N;Barrett, Leanne;Perillo, Anna;Sun, Anina Y;Antoine, Tajmara;Farrohi, Faranak;Docktor, Brenda;Lau, Emil
• 通讯作者: Lau, Emil

Future of Radionuclide Myocardial Perfusion Imaging: Transitioning from SPECT to PET.

放射性核素心肌灌注成像的未来：从 SPECT 过渡到 PET。

• 发表时间: 2023-11
• 作者: Di Carli; Marcelo F
• 通讯作者: Marcelo F

Downward myocardial creep during stress PET imaging is inversely associated with mortality.

应激 PET 成像期间心肌向下蠕动与死亡率呈负相关。

• 发表时间: 2024-05
• 影响因子: 9.1
• 作者: Kuronuma, Keiichiro;Miller, Robert J H;Wei, Chih;Singh, Ananya;Lemley, Mark H;Van Kriekinge, Serge D;Kavanagh, Paul B;Gransar, Heidi;Han, Donghee;Hayes, Sean W;Thomson, Louise;Dey, Damini;Friedman, John D;Berman, Daniel S;Slomka, Piotr
• 通讯作者: Slomka, Piotr

Automated Motion Correction for Myocardial Blood Flow Measurements and Diagnostic Performance of 82Rb PET Myocardial Perfusion Imaging.

心肌血流测量的自动运动校正和 82Rb PET 心肌灌注成像的诊断性能。

• 发表时间: 2024-01-02
• 作者: Kuronuma, Keiichiro;Wei, Chih;Singh, Ananya;Lemley, Mark;Hayes, Sean W;Otaki, Yuka;Hyun, Mark C;Van Kriekinge, Serge D;Kavanagh, Paul;Huang, Cathleen;Han, Donghee;Dey, Damini;Berman, Daniel S;Slomka, Piotr J
• 通讯作者: Slomka, Piotr J