Abstract
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-Altman analyses. Results: Complete stress and rest perfusion datasets were available for 31 patients. A bias of -0.07 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 -0.30 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.