{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T22:42:46Z","timestamp":1792795366789,"version":"4.5.0"},"posted":{"date-parts":[[2026,2,5]]},"group-title":"Cardiovascular Medicine","reference-count":31,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,2,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Quantitative myocardial blood flow (MBF) and myocardial flow reserve (MFR) provide incremental diagnostic and prognostic value in cardiac PET, but their widespread use is limited by the technical demands of dynamic imaging protocols. We evaluated the feasibility of using artificial intelligence (AI) to predict MBF and MFR from static and gated PET images, without the need for dynamic acquisition.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>A machine learning (XGBoost) model was trained on 82Rb PET multi-center dataset using static perfusion imaging, injected dose, hemodynamic measures, clinical data and CT-derived features (including body composition) from the hybrid CT attenuation scan. Model performance was evaluated externally in an independent cohort.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In total, 10,566 (derivation-cohort) and 7,842 (external-cohort) patients were included in this multi-center study. On the external-cohort, AI approach achieved an Area under the curve (AUC) of 0.92 (0.92\u20130.93) for abnormal stress MBF and 0.91 (0.90\u20130.92) for abnormal MFR; Intra-class correlation (ICC) 0.80 (0.78\u20130.82) and 0.78 (0.76\u20130.79), respectively. AI MFR closely mirrored the prognostic performance of measured MFR, showing nearly identical Kaplan\u2013Meier risk stratification (both p&lt;0.0001) and maintaining strong, and independently significant associations with all-cause mortality (HR 3.4 [2.8\u20134.2] vs. 4.6 [3.6\u20135.8]; both p&lt;0.001), and demonstrated similar added value to perfusion for mortality prediction.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>AI-predicted virtual stress MBF and MFR assessment using static and gated PET data is feasible and generalizable across cohorts. By removing the dependency on dynamic acquisitions, this approach has the potential to broaden the clinical adoption of flow quantification.<\/jats:p>\n                  <jats:fig id=\"ufig1\" position=\"float\" orientation=\"portrait\" fig-type=\"figure\">\n                    <jats:caption>\n                      <jats:title>STRUCTURED GRAPHICAL ABSTRACT<\/jats:title>\n                      <jats:p>PET: Positron Emission Tomography, CT: Computed Tomography, MFR: Myocardial Flow Reserve<\/jats:p>\n                    <\/jats:caption>\n                    <jats:graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"26345376v1_ufig1\" position=\"float\" orientation=\"portrait\"\/>\n                  <\/jats:fig>\n                  <jats:p>\n                    <jats:bold>Key Question:<\/jats:bold>\n                    Can machine learning models trained on dynamic PET datasets accurately predict regional stress myocardial blood flow (MBF) and myocardial flow reserve (MFR) from static image features, physiological parameters, and CT-based anatomical measures?\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Key Finding:<\/jats:bold>\n                    Artificial intelligence can accurately estimate MBF and MFR from non-dynamic PET data, with strong agreement to reference standards.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Take-home Message:<\/jats:bold>\n                    By eliminating reliance on dynamic PET acquisitions, machine-learning has the potential to broaden clinical adoption of quantitative flow assessment.\n                  <\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.02.03.26345376","type":"posted-content","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T01:20:15Z","timestamp":1770340815000},"source":"Crossref","is-referenced-by-count":1,"title":["Virtual myocardial blood flow and flow reserve from static PET imaging using artificial intelligence"],"prefix":"10.64898","author":[{"given":"Meghana","family":"Urs","sequence":"first","affiliation":[{"name":"Artificial Intelligence in Medicine Research Center, Departments of Biomedical Sciences, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, CA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacek","family":"Kwieci\u0144ski","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Research Center, Departments of Biomedical Sciences, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, CA, United States"},{"name":"Department of Interventional Cardiology and Angiology, Institute of Cardiology, Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Lemley","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Research Center, Departments of Biomedical Sciences, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, CA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Panithaya","family":"Chareonthaitawee","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giselle","family":"Ramirez","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Research Center, Departments of Biomedical Sciences, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, CA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aakash","family":"Shanbhag","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Research Center, Departments of Biomedical Sciences, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, CA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aditya","family":"Killekar","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Research Center, Departments of Biomedical Sciences, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, CA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"deKemp","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Department of Medicine, University of Ottawa Heart Institute, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanda","family":"Acampa","sequence":"additional","affiliation":[{"name":"Department of Advanced Biomedical Sciences, University of Naples Federico II, Naples, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viet T.","family":"Le","sequence":"additional","affiliation":[{"name":"Intermountain Medical Center Heart Institute, Intermountain Healthcare, Murray, UT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steve","family":"Mason","sequence":"additional","affiliation":[{"name":"Intermountain Medical Center Heart Institute, Intermountain Healthcare, Murray, UT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stacey","family":"Knight","sequence":"additional","affiliation":[{"name":"Intermountain Medical Center Heart Institute, Intermountain Healthcare, Murray, UT, USA"},{"name":"Department of Internal Medicine, University of Utah, Salt Lake City, UT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rene R. S.","family":"Packard","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Department of Medicine, David Geffen School of Medicine, University of California, Los Angeles, CA, USA"},{"name":"West Los Angeles Veterans Affairs Medical Center, Los Angeles, California, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mouaz","family":"Al-Mallah","sequence":"additional","affiliation":[{"name":"Houston Methodist DeBakey Heart & Vascular Center, Houston Methodist Academic Institute, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel S.","family":"Berman","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Research Center, Departments of Biomedical Sciences, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, CA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Damini","family":"Dey","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Research Center, Departments of Biomedical Sciences, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, CA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert J. H.","family":"Miller","sequence":"additional","affiliation":[{"name":"Department of Cardiac Sciences, University of Calgary, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcelo","family":"Di Carli","sequence":"additional","affiliation":[{"name":"Cardiovascular Imaging Program, Departments of Radiology and Medicine Division of Nuclear Medicine and Cardiovascular Imaging, Department of Radiology and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Harvard Medical School, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6110-938X","authenticated-orcid":false,"given":"Piotr J.","family":"Slomka","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Research Center, Departments of Biomedical Sciences, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, CA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"issue":"25","key":"2026020719400886000_2026.02.03.26345376v1.1","first-page":"e1096","article-title":"Correction to: 2025 Heart Disease and Stroke Statistics: A Report of US and Global Data From the American Heart Association","volume":"151","year":"2025","journal-title":"Circulation"},{"key":"2026020719400886000_2026.02.03.26345376v1.2","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.124.267869"},{"key":"2026020719400886000_2026.02.03.26345376v1.3","doi-asserted-by":"crossref","first-page":"117280","DOI":"10.1016\/j.atherosclerosis.2023.117280","article-title":"Prognostic value of positron emission tomography derived myocardial flow reserve: A systematic review and meta-analysis","volume":"382","year":"2023","journal-title":"Atherosclerosis"},{"key":"2026020719400886000_2026.02.03.26345376v1.4","doi-asserted-by":"publisher","DOI":"10.1161\/CIR.0000000000001029"},{"key":"2026020719400886000_2026.02.03.26345376v1.5","doi-asserted-by":"publisher","DOI":"10.1161\/CIR.0000000000001168"},{"key":"2026020719400886000_2026.02.03.26345376v1.6","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehae177"},{"key":"2026020719400886000_2026.02.03.26345376v1.7","doi-asserted-by":"publisher","DOI":"10.1016\/j.nuclcard.2024.102030"},{"issue":"12","key":"2026020719400886000_2026.02.03.26345376v1.8","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1016\/j.jcmg.2024.07.019","article-title":"Geographic Proximity to Cardiac Positron Emission Tomography Facilities Across the United States","volume":"17","year":"2024","journal-title":"JACC Cardiovasc Imaging"},{"key":"2026020719400886000_2026.02.03.26345376v1.9","doi-asserted-by":"crossref","first-page":"102449","DOI":"10.1016\/j.nuclcard.2025.102449","article-title":"The REgistry of Flow and Perfusion Imaging for Artificial Intelligence with positron emission tomography (REFINE PET):Rationale and design","volume":"52","year":"2025","journal-title":"J Nucl Cardiol"},{"key":"2026020719400886000_2026.02.03.26345376v1.10","doi-asserted-by":"publisher","DOI":"10.1007\/s12350-011-9496-3"},{"key":"2026020719400886000_2026.02.03.26345376v1.11","first-page":"124640D","article-title":"Comparative analysis between convolutional long short-term memory networks and vision transformers for coronary calcium scoring in non-contrast CT","volume":"2023","year":"2023","journal-title":"ProcSPIE"},{"key":"2026020719400886000_2026.02.03.26345376v1.12","doi-asserted-by":"crossref","unstructured":"Pieszko K , Shanbhag A , Killekar A , et al. Calcium scoring in low-dose ungated chest CT scans using convolutional long-short term memory networks. Proc SPIE Int Soc Opt Eng 2022; 12032.","DOI":"10.1117\/12.2613147"},{"key":"2026020719400886000_2026.02.03.26345376v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2022.06.006"},{"issue":"7","key":"2026020719400886000_2026.02.03.26345376v1.14","first-page":"e018188","article-title":"Deep Learning-Derived Cardiac Chamber Volumes and Mass From PET\/CT Attenuation Scans: Associations With Myocardial Flow Reserve and Heart Failure","volume":"18","year":"2025","journal-title":"Circ Cardiovasc Imaging"},{"key":"2026020719400886000_2026.02.03.26345376v1.15","doi-asserted-by":"crossref","unstructured":"Shanbhag AD , Marcinkiewicz A , Zhang W , et al. AI-based Aortic Measurements from Cardiac CT Attenuation Scans Identify High-risk Patients. Journal of Nuclear Cardiology 2025; 50.","DOI":"10.1016\/j.nuclcard.2025.102409"},{"issue":"24","key":"2026020719400886000_2026.02.03.26345376v1.16","doi-asserted-by":"crossref","first-page":"2336","DOI":"10.1093\/eurheartj\/ehaf131","article-title":"Deep learning-quantified body composition from positron emission tomography\/computed tomography and cardiovascular outcomes: a multicentre study","volume":"46","year":"2025","journal-title":"Eur Heart J"},{"issue":"2","key":"2026020719400886000_2026.02.03.26345376v1.17","first-page":"183","article-title":"Automatic quantification of myocardial perfusion stress-rest change: a new measure of ischemia","volume":"45","year":"2004","journal-title":"J Nucl Med"},{"key":"2026020719400886000_2026.02.03.26345376v1.18","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C. XGBoost: A Scalable Tree Boosting System; 2016.","DOI":"10.1145\/2939672.2939785"},{"key":"2026020719400886000_2026.02.03.26345376v1.19","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.111.095398"},{"key":"2026020719400886000_2026.02.03.26345376v1.20","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-021-05643-2"},{"key":"2026020719400886000_2026.02.03.26345376v1.21","doi-asserted-by":"crossref","unstructured":"Zhang W , Kwiecinski J , Shanbhag A , et al. Multicenter Evaluation of Interpretable AI for Coronary Artery Disease Diagnosis from PET Biomarkers. medRxiv 2025.","DOI":"10.1101\/2025.06.19.25329944"},{"key":"2026020719400886000_2026.02.03.26345376v1.22","doi-asserted-by":"publisher","DOI":"10.1161\/hc0402.102975"},{"key":"2026020719400886000_2026.02.03.26345376v1.23","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.111.050427"},{"key":"2026020719400886000_2026.02.03.26345376v1.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2014.05.069"},{"key":"2026020719400886000_2026.02.03.26345376v1.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2018.10.056"},{"key":"2026020719400886000_2026.02.03.26345376v1.26","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.109.915009"},{"key":"2026020719400886000_2026.02.03.26345376v1.27","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.113.121442"},{"key":"2026020719400886000_2026.02.03.26345376v1.28","doi-asserted-by":"publisher","DOI":"10.1007\/s12350-011-9506-5"},{"key":"2026020719400886000_2026.02.03.26345376v1.29","doi-asserted-by":"publisher","DOI":"10.1016\/j.nuclcard.2007.05.008"},{"key":"2026020719400886000_2026.02.03.26345376v1.30","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.117.201368"},{"key":"2026020719400886000_2026.02.03.26345376v1.31","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.104.007831"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.02.03.26345376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T03:40:27Z","timestamp":1770522027000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.02.03.26345376"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.64898\/2026.02.03.26345376","relation":{},"subject":[],"published":{"date-parts":[[2026,2,5]]},"subtype":"preprint"}}