Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
[Preprint]. 2025 Jul 11:2025.07.10.25330435.
doi: 10.1101/2025.07.10.25330435.

The REgistry of Flow and Perfusion Imaging for Artificial INtelligEnce with PET (REFINE PET): Rationale and Design

Giselle Ramirez  1 , Mark Lemley  1 , Aakash Shanbhag  1   2 , Jacek Kwiecinski  1   3 , Robert J H Miller  1   4 , Paul B Kavanagh  1 , Joanna X Liang  1 , Damini Dey  1 , Leandro Slipczuk  5 , Mark I Travin  6 , Erick Alexanderson  7   8 , Isabel Carvajal-Juarez  7 , René R S Packard  9   10 , Mouaz Al-Mallah  11 , Andrew J Einstein  12 , Attila Feher  13 , Wanda Acampa  14 , Stacey Knight  15   16 , Viet T Le  15 , Steve Mason  15 , Rupa Sanghani  17 , Samuel Wopperer  18 , Panithaya Chareonthaitawee  18 , Ronny R Buechel  19 , Thomas L Rosamond  20 , Robert A deKemp  21 , Daniel S Berman  1 , Marcelo F Di Carli  22 , Piotr J Slomka  1
Affiliations

The REgistry of Flow and Perfusion Imaging for Artificial INtelligEnce with PET (REFINE PET): Rationale and Design

Giselle Ramirez et al. medRxiv. .

Update in

  • The REgistry of Flow and Perfusion Imaging for Artificial INtelligEnce with PET(REFINE PET): Rationale and Design.
    Ramirez G, Lemley M, Shanbhag A, Kwiecinski J, Miller RJH, Kavanagh PB, Liang JX, Dey D, Slipczuk L, Travin MI, Alexanderson E, Carvajal-Juarez I, Packard RRS, Al-Mallah M, Einstein AJ, Feher A, Acampa W, Knight S, Le VT, Mason S, Sanghani R, Wopperer S, Chareonthaitawee P, Buechel RR, Rosamond TL, deKemp RA, Berman DS, Di Carli MF, Slomka PJ. Ramirez G, et al. J Nucl Cardiol. 2025 Aug 5:102449. doi: 10.1016/j.nuclcard.2025.102449. Online ahead of print. J Nucl Cardiol. 2025. PMID: 40774620

Abstract

Rationale: The REgistry of Flow and Perfusion Imaging for Artificial INtelligEnce with PET (REFINE PET) was established to aggregate PET and associated computed tomography (CT) images with clinical data from hospitals around the world into one comprehensive research resource.

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 35,588 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 2200 imaging variables across 42 categories. The registry is poised to address a broad range of clinical questions, supported by correlating invasive angiography (within 6 months of MPI) in 5972 patients and a total of 9252 major adverse cardiovascular events during a median follow-up of 4.2 years.

Conclusion: 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.

Keywords: PET; artificial intelligence; coronary artery disease; myocardial perfusion imaging; quantitative analysis.

PubMed Disclaimer

Figures

Figure 1:
Figure 1:
Process of data collection and processing for REFINE PET registry. CTAC: computed tomography attenuation correction; QC: quality control.
Figure 2:
Figure 2:
Sankey diagram illustrating data flow for the 10 sites with cleaned clinical and imaging data, including stress prefusion, dynamic imaging, and a CTAC scans. Rest CTAC scan was used when available; if stress-only imaging was performed, the stress CTAC scan was used. Total n= 25,310. CAC: coronary artery calcium; CTAC: computed tomography attenuation correction; TPD: total perfusion deficit; MFR: myocardial flow reserve; MACE: major adverse cardiovascular event; BWH: Brigham and Women’s Hospital; CSMC: Cedars-Sinai Medical Center, KUMC: University of Kansas Medical Center, Mexico City: National Autonomous University of Mexico, Naples: University of Naples Federico II, WLAVA: West Los Angeles Veterans Affair MCE
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Association A.H., Cardiovascular Disease: A Costly Burden for America Projections Through 2035. 2017.
    1. Roth G.A., et al. , Global Burden of Cardiovascular Diseases and Risk Factors, 1990–2019: Update From the GBD 2019 Study. J Am Coll Cardiol, 2020. 76(25): p. 2982–3021. - PMC - PubMed
    1. Bajaj N.S., et al. , Coronary Microvascular Dysfunction and Cardiovascular Risk in Obese Patients. J Am Coll Cardiol, 2018. 72(7): p. 707–717. - PMC - PubMed
    1. Murthy V.L., et al. , Association between coronary vascular dysfunction and cardiac mortality in patients with and without diabetes mellitus. Circulation, 2012. 126(15): p. 1858–68. - PMC - PubMed
    1. Osborne M.T., et al. , Coronary Microvascular Dysfunction Identifies Patients at High Risk of Adverse Events Across Cardiometabolic Diseases. J Am Coll Cardiol, 2017. 70(22): p. 2835–2837. - PMC - PubMed

Publication types

LinkOut - more resources