{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T06:28:08Z","timestamp":1782455288812,"version":"3.54.5"},"reference-count":43,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Dutch Research Council (NWO)"},{"name":"Maastricht University Medical Centre+"},{"name":"Faculty of Health, Medicine and Life Sciences of Maastricht University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: To validate an artificial intelligence-based arterial input function (AI-AIF) deep learning model for myocardial blood flow (MBF) quantification during stress perfusion and assess its extension to rest perfusion, enabling myocardial perfusion reserve (MPR) calculation. Methods: Sixty patients with or at risk for vascular cognitive impairment, prospectively enrolled in the CRUCIAL consortium, underwent quantitative stress and rest myocardial perfusion imaging using a 3 T MRI system. Perfusion imaging was performed using a dual-sequence (DS) protocol after intravenous administration of 0.05 mmol\/kg gadobutrol. Retrospectively, the AI-AIF was estimated from standard perfusion images using a 1-D U-Net model trained to predict an unsaturated AIF from a saturated input. MBF was quantified using Fermi function-constrained deconvolution with motion compensation. MPR was calculated as the stress-to-rest MBF ratio. MBF and MPR estimates from both AIF methods were compared using Bland\u2013Altman analyses. Results: Complete stress and rest perfusion datasets were available for 31 patients. A bias of \u22120.07 mL\/g\/min was observed between AI-AIF and DS-AIF for stress MBF (median 2.19 vs. 2.30 mL\/g\/min), with concordant coronary artery disease classification based on the optimal MBF threshold in over 92% of myocardial segments and coronary arteries. Larger biases of 0.12 mL\/g\/min and \u22120.30 were observed for rest MBF (1.12 vs. 1.02 mL\/g\/min) and MPR (2.31 vs. 1.84), respectively, with lower concordance using the optimal MPR threshold (85% of segments, 72% of arteries). Conclusions: The AI-AIF model showed comparable performance to DS-AIF for stress MBF quantification but requires further training for accurate rest MBF and MPR assessment.<\/jats:p>","DOI":"10.3390\/diagnostics15182341","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T08:56:46Z","timestamp":1758013006000},"page":"2341","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Artificial Intelligence-Based Arterial Input Function for the Quantitative Assessment of Myocardial Blood Flow and Perfusion Reserve in Cardiac Magnetic Resonance: A Validation Study"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5761-1861","authenticated-orcid":false,"given":"Lara R.","family":"van der Meulen","sequence":"first","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, Maastricht University Medical Centre, 6229 HX Maastricht, The Netherlands"},{"name":"Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, 6200 MD Maastricht, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7349-4783","authenticated-orcid":false,"given":"Maud","family":"van Dinther","sequence":"additional","affiliation":[{"name":"Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, 6200 MD Maastricht, The Netherlands"},{"name":"Department of Neurology, Maastricht University Medical Centre, 6229 HX Maastricht, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3394-4289","authenticated-orcid":false,"given":"Amedeo","family":"Chiribiri","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering and Imaging Sciences, King\u2019s College London, St Thomas\u2019 Hospital, London SE1 7EH, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jouke","family":"Smink","sequence":"additional","affiliation":[{"name":"Philips Healthcare, 5684 PC Best, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"CRUCIAL Investigators","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Walter H.","family":"Backes","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, Maastricht University Medical Centre, 6229 HX Maastricht, The Netherlands"},{"name":"Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, 6200 MD Maastricht, The Netherlands"},{"name":"Mental Health & Neuroscience Research Institute, Maastricht University, 6200 MD Maastricht, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Bennett","sequence":"additional","affiliation":[{"name":"Institute of Cardiovascular Science, University College London, London WC1E 6BT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joachim E.","family":"Wildberger","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, Maastricht University Medical Centre, 6229 HX Maastricht, The Netherlands"},{"name":"Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, 6200 MD Maastricht, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cian M.","family":"Scannell","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Eindhoven University of Technology, 5600 MB Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert J.","family":"Holtackers","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, Maastricht University Medical Centre, 6229 HX Maastricht, The Netherlands"},{"name":"Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, 6200 MD Maastricht, The Netherlands"},{"name":"School of Biomedical Engineering and Imaging Sciences, King\u2019s College London, St Thomas\u2019 Hospital, London SE1 7EH, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1186\/1532-429X-12-57","article-title":"Quantification of myocardial perfusion by cardiovascular magnetic resonance","volume":"12","year":"2010","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1093\/ehjci\/jew315","article-title":"Diagnostic value of global myocardial perfusion reserve assessment based on coronary sinus flow measurements using cardiovascular magnetic resonance in addition to myocardial stress perfusion imaging","volume":"18","author":"Shomanova","year":"2017","journal-title":"Eur. Heart J. Cardiovasc. Imaging"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1958","DOI":"10.1016\/j.jcmg.2018.12.022","article-title":"Automated Pixel-Wise Quantitative Myocardial Perfusion Mapping by CMR to Detect Obstructive Coronary Artery Disease and Coronary Microvascular Dysfunction: Validation Against Invasive Coronary Physiology","volume":"12","author":"Kotecha","year":"2019","journal-title":"JACC Cardiovasc. Imaging"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1186\/s12968-018-0493-4","article-title":"Importance of operator training and rest perfusion on the diagnostic accuracy of stress perfusion cardiovascular magnetic resonance","volume":"20","author":"Villa","year":"2018","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.pnmrs.2013.04.002","article-title":"Arterial input function in perfusion MRI: A comprehensive review","volume":"74","author":"Calamante","year":"2013","journal-title":"Prog. Nucl. Magn. Reson. Spectrosc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.1002\/mrm.22101","article-title":"Model-based blind estimation of kinetic parameters in dynamic contrast enhanced (DCE)-MRI","volume":"62","author":"Fluckiger","year":"2009","journal-title":"Magn. Reson. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.1002\/jmri.20910","article-title":"Contrast-dose relation in first-pass myocardial MR perfusion imaging","volume":"25","author":"Utz","year":"2007","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1002\/mrm.22018","article-title":"Quantitative analysis of first-pass contrast-enhanced myocardial perfusion MRI using a Patlak plot method and blood saturation correction","volume":"62","author":"Ichihara","year":"2009","journal-title":"Magn. Reson. Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1093\/ehjci\/jeab193","article-title":"How to do quantitative myocardial perfusion cardiovascular magnetic resonance","volume":"23","author":"Sharrack","year":"2022","journal-title":"Eur. Heart J. Cardiovasc. Imaging"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"101085","DOI":"10.1016\/j.jocmr.2024.101085","article-title":"Comparison of dual-bolus versus dual-sequence techniques for determining myocardial blood flow and myocardial perfusion reserve by cardiac magnetic resonance stress perfusion: From the Automated Quantitative analysis of myocardial perfusion cardiac Magnetic Resonance Consortium","volume":"26","author":"Chong","year":"2024","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1186\/1532-429X-13-28","article-title":"Development of a universal dual-bolus injection scheme for the quantitative assessment of myocardial perfusion cardiovascular magnetic resonance","volume":"13","author":"Ishida","year":"2011","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1093\/ehjdh\/ztac074","article-title":"AI-AIF: Artificial intelligence-based arterial input function for quantitative stress perfusion cardiac magnetic resonance","volume":"4","author":"Scannell","year":"2023","journal-title":"Eur. Heart J. Digit. Health"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1002\/mp.15327","article-title":"Implementation and prospective clinical validation of AI-based planning and shimming techniques in cardiac MRI","volume":"49","author":"Edalati","year":"2022","journal-title":"Med. Phys."},{"key":"ref_14","unstructured":"van Gorp, H., Huijben, I.A.M., Veeling, B.S., Pezzotti, N., and van Sloun, R.J.G. (2021, January 18\u201324). Active Deep Probabilistic Subsampling. Proceedings of the 38th International Conference on Machine Learning, Virtual."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3055","DOI":"10.1002\/mrm.26977","article-title":"Learning a variational network for reconstruction of accelerated MRI data","volume":"79","author":"Hammernik","year":"2018","journal-title":"Magn. Reson. Med."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Mart\u00edn-Gonz\u00e1lez, E., Alskaf, E., Chiribiri, A., Casaseca-de-la-Higuera, P., Alberola-L\u00f3pez, C., Nunes, R.G., and Correia, T. (2021). Physics-Informed Self-supervised Deep Learning Reconstruction for Accelerated First-Pass Perfusion Cardiac MRI, Springer International Publishing.","DOI":"10.1007\/978-3-030-88552-6_9"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wang, J., Weller, D.S., Kramer, C.M., and Salerno, M. (2022). DEep learning-based rapid Spiral Image REconstruction (DESIRE) for high-resolution spiral first-pass myocardial perfusion imaging. NMR Biomed., 35.","DOI":"10.1002\/nbm.4661"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.mri.2021.08.007","article-title":"Deep learning for radial SMS myocardial perfusion reconstruction using the 3D residual booster U-net","volume":"83","author":"Le","year":"2021","journal-title":"Magn. Reson. Imaging"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Fan, L., Shen, D., Haji-Valizadeh, H., Naresh, N.K., Carr, J.C., Freed, B.H., Lee, D.C., and Kim, D. (2020). Rapid dealiasing of undersampled, non-Cartesian cardiac perfusion images using U-net. NMR Biomed., 33.","DOI":"10.1002\/nbm.4239"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1689","DOI":"10.1002\/jmri.26983","article-title":"Deep-Learning-Based Preprocessing for Quantitative Myocardial Perfusion MRI","volume":"51","author":"Scannell","year":"2020","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Yalcinkaya, D.M., Youssef, K., Heydari, B., Zamudio, L., Dharmakumar, R., and Sharif, B. (2021, January 1\u20135). Deep Learning-Based Segmentation and Uncertainty Assessment for Automated Analysis of Myocardial Perfusion MRI Datasets Using Patch-Level Training and Advanced Data Augmentation. Proceedings of the 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Guadalajara, Mexico.","DOI":"10.1109\/EMBC46164.2021.9629581"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.mri.2020.01.005","article-title":"Denoising arterial spin labeling perfusion MRI with deep machine learning","volume":"68","author":"Xie","year":"2020","journal-title":"Magn. Reson. Imaging"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Huang, J., Guo, J., Pedrosa, I., and Fei, B. (2022, January 25). Deep learning-based deformable registration of dynamic contrast enhanced MR images of the kidney. Proceedings of the SPIE Medical Imaging, San Diego, CA, USA.","DOI":"10.1117\/12.2611768"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"McKinley, R., Hung, F., Wiest, R., Liebeskind, D.S., and Scalzo, F. (2018). A Machine Learning Approach to Perfusion Imaging with Dynamic Susceptibility Contrast MR. Front. Neurol., 9.","DOI":"10.3389\/fneur.2018.00717"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1159\/000529067","article-title":"Evaluation of Microvascular Rarefaction in Vascular Cognitive Impairment and Heart Failure (CRUCIAL): Study Protocol for an Observational Study","volume":"13","author":"Bennett","year":"2023","journal-title":"Cerebrovasc. Dis. Extra"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1186\/s12968-015-0116-2","article-title":"Optimization of dual-saturation single bolus acquisition for quantitative cardiac perfusion and myocardial blood flow maps","volume":"17","author":"Nothnagel","year":"2015","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation, Springer International Publishing.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"qyae001","DOI":"10.1093\/ehjimp\/qyae001","article-title":"High-resolution quantification of stress perfusion defects by cardiac magnetic resonance","volume":"2","author":"Scannell","year":"2024","journal-title":"Eur. Heart J. Imaging Methods Pract."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1812","DOI":"10.1109\/TMI.2019.2897044","article-title":"Robust Non-Rigid Motion Compensation of Free-Breathing Myocardial Perfusion MRI Data","volume":"38","author":"Scannell","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1161\/hc0402.102975","article-title":"Standardized myocardial segmentation and nomenclature for tomographic imaging of the heart. A statement for healthcare professionals from the Cardiac Imaging Committee of the Council on Clinical Cardiology of the American Heart Association","volume":"105","author":"Cerqueira","year":"2002","journal-title":"Circulation"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1093\/biomet\/52.3-4.591","article-title":"An Analysis of Variance Test for Normality (Complete Samples)","volume":"52","author":"Shapiro","year":"1965","journal-title":"Biometrika"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1080\/01621459.1951.10500769","article-title":"The Kolmogorov-Smirnov Test for Goodness of Fit","volume":"46","author":"Massey","year":"1951","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/S0140-6736(86)90837-8","article-title":"Statistical Methods for Assessing Agreement between Two Methods of Clinical Measurement","volume":"327","author":"Bland","year":"1986","journal-title":"Lancet"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"141","DOI":"10.11613\/BM.2015.015","article-title":"Understanding Bland Altman analysis","volume":"25","author":"Giavarina","year":"2015","journal-title":"Biochem. Med."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1016\/j.jcmg.2018.01.005","article-title":"Diagnostic Performance of Fully Automated Pixel-Wise Quantitative Myocardial Perfusion Imaging by Cardiovascular Magnetic Resonance","volume":"11","author":"Hsu","year":"2018","journal-title":"JACC Cardiovasc. Imaging"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.jacc.2010.09.019","article-title":"High-resolution magnetic resonance myocardial perfusion imaging at 3.0-Tesla to detect hemodynamically significant coronary stenoses as determined by fractional flow reserve","volume":"57","author":"Lockie","year":"2011","journal-title":"J. Am. Coll. Cardiol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1186\/s12968-021-00733-4","article-title":"Influence of the arterial input sampling location on the diagnostic accuracy of cardiovascular magnetic resonance stress myocardial perfusion quantification","volume":"23","author":"Milidonis","year":"2021","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.mri.2005.02.013","article-title":"Quantitative pharmacokinetic analysis of DCE-MRI data without an arterial input function: A reference region model","volume":"23","author":"Yankeelov","year":"2005","journal-title":"Magn. Reson. Imaging"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1002\/mrm.22809","article-title":"Constrained estimation of the arterial input function for myocardial perfusion cardiovascular magnetic resonance","volume":"66","author":"Fluckiger","year":"2011","journal-title":"Magn. Reson. Med."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1186\/s12968-023-00945-w","article-title":"A simplified method to correct saturation of arterial input function for cardiac magnetic resonance first-pass perfusion imaging: Validation with simultaneously acquired PET","volume":"25","author":"Li","year":"2023","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s12968-018-0462-y","article-title":"Fully automated, inline quantification of myocardial blood flow with cardiovascular magnetic resonance: Repeatability of measurements in healthy subjects","volume":"20","author":"Brown","year":"2018","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1002\/mrm.29295","article-title":"Free-breathing motion-informed locally low-rank quantitative 3D myocardial perfusion imaging","volume":"88","author":"Hoh","year":"2022","journal-title":"Magn. Reson. Med."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"102399","DOI":"10.1016\/j.media.2022.102399","article-title":"Physics-informed neural networks for myocardial perfusion MRI quantification","volume":"78","author":"Chiribiri","year":"2022","journal-title":"Med. Image Anal."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/18\/2341\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:46:11Z","timestamp":1760035571000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/18\/2341"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"references-count":43,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["diagnostics15182341"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15182341","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,16]]}}}