Cian M. Scannell

Background: Quantitative stress perfusion cardiovascular magnetic resonance (CMR) is a powerful tool for assessing myocardial ischemia. Motion correction is essential for accurate pixel-wise mapping but traditional registration-based methods are slow and sensitive to acquisition variability, limiting robustness and scalability. Methods: We developed an unsupervised deep learning-based motion correction pipeline that replaces iterative registration with efficient one-shot estimation. The method corrects motion in three steps and uses robust principal component analysis to reduce contrast-related effects. It aligns the perfusion series and auxiliary images (arterial input function and proton density-weighted series). Models were trained and validated on multivendor data from 201 patients, with 38 held out for testing. Performance was assessed via temporal alignment and quantitative perfusion values, compared to a previously published registration-based method. Results: The deep learning approach significantly improved temporal smoothness of time-intensity curves (p<0.001). Myocardial alignment (Dice = 0.92 (0.04) and 0.91 (0.05)) was comparable to the baseline and superior to before registration (Dice = 0.80 (0.09), p<0.001). Perfusion maps showed reduced motion, with lower standard deviation in the myocardium (0.52 (0.39) ml/min/g) compared to baseline (0.55 (0.44) ml/min/g). Processing time was reduced 15-fold. Conclusion: This deep learning pipeline enables fast, robust motion correction for stress perfusion CMR, improving accuracy across dynamic and auxiliary images. Trained on multivendor data, it generalizes across sequences and may facilitate broader clinical adoption of quantitative perfusion imaging.

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.

Self-supervised pretraining (SSP) has shown promising results in learning from large unlabeled datasets and, thus, could be useful for automated cardiovascular magnetic resonance (CMR) short-axis cine segmentation. However, inconsistent reports of the benefits of SSP for segmentation have made it difficult to apply SSP to CMR. Therefore, this study aimed to evaluate SSP methods for CMR cine segmentation. To this end, short-axis cine stacks of 296 subjects (90618 2D slices) were used for unlabeled pretraining with four SSP methods; SimCLR, positional contrastive learning, DINO, and masked image modeling (MIM). Subsets of varying numbers of subjects were used for supervised fine-tuning of 2D models for each SSP method, as well as to train a 2D baseline model from scratch. The fine-tuned models were compared to the baseline using the 3D Dice similarity coefficient (DSC) in a test dataset of 140 subjects. The SSP methods showed no performance gains with the largest supervised fine-tuning subset compared to the baseline (DSC = 0.89). When only 10 subjects (231 2D slices) are available for supervised training, SSP using MIM (DSC = 0.86) improves over training from scratch (DSC = 0.82). This study found that SSP is valuable for CMR cine segmentation when labeled training data is scarce, but does not aid state-of-the-art deep learning methods when ample labeled data is available. Moreover, the choice of SSP method is important. The code is publicly available at: https://github.com/q-cardIA/ssp-cmr-cine-segmentation

Quantification of myocardial scar from late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) images can be facilitated by automated artificial intelligence (AI)-based analysis. However, AI models are susceptible to domain shifts in which the model performance is degraded when applied to data with different characteristics than the original training data. In this study, CycleGAN models were trained to translate local hospital data to the appearance of a public LGE CMR dataset. After domain adaptation, an AI scar quantification pipeline including myocardium segmentation, scar segmentation, and computation of scar burden, previously developed on the public dataset, was evaluated on an external test set including 44 patients clinically assessed for ischemic scar. The mean ± standard deviation Dice similarity coefficients between the manual and AI-predicted segmentations in all patients were similar to those previously reported: 0.76 ± 0.05 for myocardium and 0.75 ± 0.32 for scar, 0.41 ± 0.12 for scar in scans with pathological findings. Bland-Altman analysis showed a mean bias in scar burden percentage of -0.62% with limits of agreement from -8.4% to 7.17%. These results show the feasibility of deploying AI models, trained with public data, for LGE CMR quantification on local clinical data using unsupervised CycleGAN-based domain adaptation. Relevance statement: Our study demonstrated the possibility of using AI models trained from public databases to be applied to patient data acquired at a specific institution with different acquisition settings, without additional manual labor to obtain further training labels. Graphical