用于人工智能的正电子发射断层扫描血流灌注成像注册研究（REFINE PET）：原理与设计

The REgistry of Flow and Perfusion Imaging for Artificial Intelligence with positron emission tomography (REFINE PET): Rationale and design.

作者信息

Ramirez Giselle, Lemley Mark, Shanbhag Aakash, Kwiecinski Jacek, Miller Robert J H, Kavanagh Paul B, Liang Joanna X, Dey Damini, Slipczuk Leandro, Travin Mark I, Alexanderson Erick, Carvajal-Juarez Isabel, Packard René R S, Al-Mallah Mouaz, Einstein Andrew J, Feher Attila, Acampa Wanda, Knight Stacey, Le Viet T, Mason Steve, Sanghani Rupa, Wopperer Samuel, Chareonthaitawee Panithaya, Buechel Ronny R, Rosamond Thomas L, deKemp Robert A, Berman Daniel S, Di Carli Marcelo F, Slomka Piotr J

机构信息

Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA.

Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Signal and Image Processing Institute, Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA.

出版信息

J Nucl Cardiol. 2025 Aug 6:102449. doi: 10.1016/j.nuclcard.2025.102449.

DOI:10.1016/j.nuclcard.2025.102449

PMID:40774620

Abstract

BACKGROUND

The REgistry of Flow and Perfusion Imaging for Artificial Intelligence with positron emission tomography (REFINE PET) was established to collect multicenter PET and associated computed tomography (CT) images, together with clinical data and outcomes, into a comprehensive research resource. REFINE-PET will enable validation and development of both standard and novel cardiac PET/CT processing methods.

METHODS

REFINE-PET is a multicenter, international registry that contains both clinical and imaging data. The PET scans were processed using QPET software (Cedars-Sinai Medical Center, Los Angeles, CA), while the CT scans were processed using deep learning (DL) to detect coronary artery calcium (CAC). Patients were followed up for the occurrence of major adverse cardiovascular events (MACE), which include death, myocardial infarction, unstable angina, and late revascularization (>90 days from PET).

RESULTS

The REFINE-PET registry currently contains data for 35595 patients from 14 sites, with additional patient data and sites anticipated. Comprehensive clinical data (including demographics, medical history, and stress test results) were integrated with more than 2100 imaging variables across 34 categories. The registry is poised to address a broad range of clinical questions, supported by correlating invasive angiography (within 6 months of PET myocardial perfusion imaging [MPI]) in 5955 patients and a total of 9278 major adverse cardiovascular events during a median follow-up of 4.2 years.

CONCLUSIONS

The REFINE-PET registry leverages the integration of clinical, multimodality imaging, and novel quantitative and AI tools to advance the role of PET/CT MPI in diagnosis and risk stratification.

摘要

背景

建立了用于人工智能正电子发射断层扫描的血流与灌注成像注册库（REFINE PET），以收集多中心PET及相关计算机断层扫描（CT）图像，以及临床数据和结果，形成一个综合研究资源库。REFINE-PET将有助于验证和开发标准及新型心脏PET/CT处理方法。

方法

REFINE-PET是一个包含临床和影像数据的多中心国际注册库。PET扫描使用QPET软件（加利福尼亚州洛杉矶市雪松西奈医疗中心）进行处理，而CT扫描则使用深度学习（DL）来检测冠状动脉钙化（CAC）。对患者进行主要不良心血管事件（MACE）的随访，MACE包括死亡、心肌梗死、不稳定型心绞痛和晚期血运重建（PET后>90天）。

结果

REFINE-PET注册库目前包含来自14个地点的3559名患者的数据，预计还会有更多患者数据和地点。综合临床数据（包括人口统计学、病史和压力测试结果）与34个类别的2100多个影像变量相结合。该注册库准备解决广泛的临床问题，5955名患者的侵入性血管造影（在PET心肌灌注成像[MPI]的6个月内）以及在4.2年的中位随访期间总共9278例主要不良心血管事件为此提供了支持。