Automated cardiovascular MR myocardial scar quantification with unsupervised domain adaptation.

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.

Hybrid artificial intelligence outcome prediction using features extraction from stress perfusion cardiac magnetic resonance images and electronic health records.

Background: Prediction of clinical outcomes in coronary artery disease (CAD) has been conventionally achieved using clinical risk factors. The relationship between imaging features and outcome is still not well understood. This study aims to use artificial intelligence to link image features with mortality outcome. Methods: A retrospective study was performed on patients who had stress perfusion cardiac magnetic resonance (SP-CMR) between 2011 and 2021. The endpoint was all-cause mortality. Convolutional neural network (CNN) was used to extract features from stress perfusion images, and multilayer perceptron (MLP) to extract features from electronic health records (EHRs), both networks were concatenated in a hybrid neural network (HNN) to predict study endpoint. Image CNN was trained to predict study endpoint directly from images. HNN and image CNN were compared with a linear clinical model using area under the curve (AUC), F1 scores, and McNemar's test. Results: Total of 1,286 cases were identified, with 201 death events (16%). The clinical model had good performance (AUC =80%, F1 score =37%). Best Image CNN model showed AUC =72% and F1 score =38%. HNN outperformed the other two models (AUC =82%, F1 score =43%). McNemar's test showed statistical difference between image CNN and both clinical model (P<0.01) and HNN (P<0.01). There was no significant difference between HNN and clinical model (P=0.15). Conclusions: Death in patients with suspected or known CAD can be predicted directly from stress perfusion images without clinical knowledge. Prediction can be improved by HNN that combines clinical and SP-CMR images.

Deep Learning Synthesis of White-Blood From Dark-Blood Late Gadolinium Enhancement Cardiac Magnetic Resonance.

OBJECTIVES: Dark-blood late gadolinium enhancement (DB-LGE) cardiac magnetic resonance has been proposed as an alternative to standard white-blood LGE (WB-LGE) imaging protocols to enhance scar-to-blood contrast without compromising scar-to-myocardium contrast. In practice, both DB and WB contrasts may have clinical utility, but acquiring both has the drawback of additional acquisition time. The aim of this study was to develop and evaluate a deep learning method to generate synthetic WB-LGE images from DB-LGE, allowing the assessment of both contrasts without additional scan time. MATERIALS AND METHODS: DB-LGE and WB-LGE data from 215 patients were used to train 2 types of unpaired image-to-image translation deep learning models, cycle-consistent generative adversarial network (CycleGAN) and contrastive unpaired translation, with 5 different loss function hyperparameter settings each. Initially, the best hyperparameter setting was determined for each model type based on the Fréchet inception distance and the visual assessment of expert readers. Then, the CycleGAN and contrastive unpaired translation models with the optimal hyperparameters were directly compared. Finally, with the best model chosen, the quantification of scar based on the synthetic WB-LGE images was compared with the truly acquired WB-LGE. RESULTS: The CycleGAN architecture for unpaired image-to-image translation was found to provide the most realistic synthetic WB-LGE images from DB-LGE images. The results showed that it was difficult for visual readers to distinguish if an image was true or synthetic (55% correctly classified). In addition, scar burden quantification with the synthetic data was highly correlated with the analysis of the truly acquired images. Bland-Altman analysis found a mean bias in percentage scar burden between the quantification of the real WB and synthetic white-blood images of 0.44% with limits of agreement from -10.85% to 11.74%. The mean image quality of the real WB images (3.53/5) was scored higher than the synthetic white-blood images (3.03), P = 0.009. CONCLUSIONS: This study proposed a CycleGAN model to generate synthetic WB-LGE from DB-LGE images to allow assessment of both image contrasts without additional scan time. This work represents a clinically focused assessment of synthetic medical images generated by artificial intelligence, a topic with significant potential for a multitude of applications. However, further evaluation is warranted before clinical adoption.

Automated inversion time selection for late gadolinium-enhanced cardiac magnetic resonance imaging.

OBJECTIVES: To develop and share a deep learning method that can accurately identify optimal inversion time (TI) from multi-vendor, multi-institutional and multi-field strength inversion scout (TI scout) sequences for late gadolinium enhancement cardiac MRI. MATERIALS AND METHODS: Retrospective multicentre study conducted on 1136 1.5-T and 3-T cardiac MRI examinations from four centres and three scanner vendors. Deep learning models, comprising a convolutional neural network (CNN) that provides input to a long short-term memory (LSTM) network, were trained on TI scout pixel data from centres 1 to 3 to identify optimal TI, using ground truth annotations by two readers. Accuracy within 50 ms, mean absolute error (MAE), Lin's concordance coefficient (LCCC) and reduced major axis regression (RMAR) were used to select the best model from validation results, and applied to holdout test data. Robustness of the best-performing model was also tested on imaging data from centre 4. RESULTS: The best model (SE-ResNet18-LSTM) produced accuracy of 96.1%, MAE 22.9 ms and LCCC 0.47 compared to ground truth on the holdout test set and accuracy of 97.3%, MAE 15.2 ms and LCCC 0.64 when tested on unseen external (centre 4) data. Differences in vendor performance were observed, with greatest accuracy for the most commonly represented vendor in the training data. CONCLUSION: A deep learning model was developed that can identify optimal inversion time from TI scout images on multi-vendor data with high accuracy, including on previously unseen external data. We make this model available to the scientific community for further assessment or development. CLINICAL RELEVANCE STATEMENT: A robust automated inversion time selection tool for late gadolinium-enhanced imaging allows for reproducible and efficient cross-vendor inversion time selection. KEY POINTS: • A model comprising convolutional and recurrent neural networks was developed to extract optimal TI from TI scout images. • Model accuracy within 50 ms of ground truth on multi-vendor holdout and external data of 96.1% and 97.3% respectively was achieved. • This model could improve workflow efficiency and standardise optimal TI selection for consistent LGE imaging.

High-resolution quantification of stress perfusion defects by cardiac magnetic resonance.

Aims: Quantitative stress perfusion cardiac magnetic resonance (CMR) is becoming more widely available, but it is still unclear how to integrate this information into clinical decision-making. Typically, pixel-wise perfusion maps are generated, but diagnostic and prognostic studies have summarized perfusion as just one value per patient or in 16 myocardial segments. In this study, the reporting of quantitative perfusion maps is extended from the standard 16 segments to a high-resolution bullseye. Cut-off thresholds are established for the high-resolution bullseye, and the identified perfusion defects are compared with visual assessment. Methods and results: Thirty-four patients with known or suspected coronary artery disease were retrospectively analysed. Visual perfusion defects were contoured on the CMR images and pixel-wise quantitative perfusion maps were generated. Cut-off values were established on the high-resolution bullseye consisting of 1800 points and compared with the per-segment, per-coronary, and per-patient resolution thresholds. Quantitative stress perfusion was significantly lower in visually abnormal pixels, 1.11 (0.75-1.57) vs. 2.35 (1.82-2.9) mL/min/g (Mann-Whitney U test P < 0.001), with an optimal cut-off of 1.72 mL/min/g. This was lower than the segment-wise optimal threshold of 1.92 mL/min/g. The Bland-Altman analysis showed that visual assessment underestimated large perfusion defects compared with the quantification with good agreement for smaller defect burdens. A Dice overlap of 0.68 (0.57-0.78) was found. Conclusion: This study introduces a high-resolution bullseye consisting of 1800 points, rather than 16, per patient for reporting quantitative stress perfusion, which may improve sensitivity. Using this representation, the threshold required to identify areas of reduced perfusion is lower than for segmental analysis.

AI-AIF: artificial intelligence-based arterial input function for quantitative stress perfusion cardiac magnetic resonance.

Aims: One of the major challenges in the quantification of myocardial blood flow (MBF) from stress perfusion cardiac magnetic resonance (CMR) is the estimation of the arterial input function (AIF). This is due to the non-linear relationship between the concentration of gadolinium and the MR signal, which leads to signal saturation. In this work, we show that a deep learning model can be trained to predict the unsaturated AIF from standard images, using the reference dual-sequence acquisition AIFs (DS-AIFs) for training. Methods and results: A 1D U-Net was trained, to take the saturated AIF from the standard images as input and predict the unsaturated AIF, using the data from 201 patients from centre 1 and a test set comprised of both an independent cohort of consecutive patients from centre 1 and an external cohort of patients from centre 2 (n = 44). Fully-automated MBF was compared between the DS-AIF and AI-AIF methods using the Mann-Whitney U test and Bland-Altman analysis. There was no statistical difference between the MBF quantified with the DS-AIF [2.77 mL/min/g (1.08)] and predicted with the AI-AIF (2.79 mL/min/g (1.08), P = 0.33. Bland-Altman analysis shows minimal bias between the DS-AIF and AI-AIF methods for quantitative MBF (bias of -0.11 mL/min/g). Additionally, the MBF diagnosis classification of the AI-AIF matched the DS-AIF in 669/704 (95%) of myocardial segments. Conclusion: Quantification of stress perfusion CMR is feasible with a single-sequence acquisition and a single contrast injection using an AI-based correction of the AIF.

Deep learning applications in myocardial perfusion imaging, a systematic review and meta-analysis.

Background: Coronary artery disease (CAD) is a leading cause of death worldwide, and the diagnostic process comprises of invasive testing with coronary angiography and non-invasive imaging, in addition to history, clinical examination, and electrocardiography (ECG). A highly accurate assessment of CAD lies in perfusion imaging which is performed by myocardial perfusion scintigraphy (MPS) and magnetic resonance imaging (stress CMR). Recently deep learning has been increasingly applied on perfusion imaging for better understanding of the diagnosis, safety, and outcome of CAD.The aim of this review is to summarise the evidence behind deep learning applications in myocardial perfusion imaging. Methods: A systematic search was performed on MEDLINE and EMBASE databases, from database inception until September 29, 2020. This included all clinical studies focusing on deep learning applications and myocardial perfusion imaging, and excluded competition conference papers, simulation and animal studies, and studies which used perfusion imaging as a variable with different focus. This was followed by review of abstracts and full texts. A meta-analysis was performed on a subgroup of studies which looked at perfusion images classification. A summary receiver-operating curve (SROC) was used to compare the performance of different models, and area under the curve (AUC) was reported. Effect size, risk of bias and heterogeneity were tested. Results: 46 studies in total were identified, the majority were MPS studies (76%). The most common neural network was convolutional neural network (CNN) (41%). 13 studies (28%) looked at perfusion imaging classification using MPS, the pooled diagnostic accuracy showed AUC = 0.859. The summary receiver operating curve (SROC) comparison showed superior performance of CNN (AUC = 0.894) compared to MLP (AUC = 0.848). The funnel plot was asymmetrical, and the effect size was significantly different with p value < 0.001, indicating small studies effect and possible publication bias. There was no significant heterogeneity amongst studies according to Q test (p = 0.2184). Conclusion: Deep learning has shown promise to improve myocardial perfusion imaging diagnostic accuracy, prediction of patients' events and safety. More research is required in clinical applications, to achieve better care for patients with known or suspected CAD.

Optimized automated cardiac MR scar quantification with GAN-based data augmentation.

BACKGROUND: The clinical utility of late gadolinium enhancement (LGE) cardiac MRI is limited by the lack of standardization, and time-consuming postprocessing. In this work, we tested the hypothesis that a cascaded deep learning pipeline trained with augmentation by synthetically generated data would improve model accuracy and robustness for automated scar quantification. METHODS: A cascaded pipeline consisting of three consecutive neural networks is proposed, starting with a bounding box regression network to identify a region of interest around the left ventricular (LV) myocardium. Two further nnU-Net models are then used to segment the myocardium and, if present, scar. The models were trained on the data from the EMIDEC challenge, supplemented with an extensive synthetic dataset generated with a conditional GAN. RESULTS: The cascaded pipeline significantly outperformed a single nnU-Net directly segmenting both the myocardium (mean Dice similarity coefficient (DSC) (standard deviation (SD)): 0.84 (0.09) vs 0.63 (0.20), p < 0.01) and scar (DSC: 0.72 (0.34) vs 0.46 (0.39), p < 0.01) on a per-slice level. The inclusion of the synthetic data as data augmentation during training improved the scar segmentation DSC by 0.06 (p < 0.01). The mean DSC per-subject on the challenge test set, for the cascaded pipeline augmented by synthetic generated data, was 0.86 (0.03) and 0.67 (0.29) for myocardium and scar, respectively. CONCLUSION: A cascaded deep learning-based pipeline trained with augmentation by synthetically generated data leads to myocardium and scar segmentations that are similar to the manual operator, and outperforms direct segmentation without the synthetic images.

Brief Research Report: Quantitative Analysis of Potential Coronary Microvascular Disease in Suspected Long-COVID Syndrome.

Background: Case series have reported persistent cardiopulmonary symptoms, often termed long-COVID or post-COVID syndrome, in more than half of patients recovering from Coronavirus Disease 19 (COVID-19). Recently, alterations in microvascular perfusion have been proposed as a possible pathomechanism in long-COVID syndrome. We examined whether microvascular perfusion, measured by quantitative stress perfusion cardiac magnetic resonance (CMR), is impaired in patients with persistent cardiac symptoms post-COVID-19. Methods: Our population consisted of 33 patients post-COVID-19 examined in Berlin and London, 11 (33%) of which complained of persistent chest pain and 13 (39%) of dyspnea. The scan protocol included standard cardiac imaging and dual-sequence quantitative stress perfusion. Standard parameters were compared to 17 healthy controls from our institution. Quantitative perfusion was compared to published values of healthy controls. Results: The stress myocardial blood flow (MBF) was significantly lower [31.8 ± 5.1 vs. 37.8 ± 6.0 (µl/g/beat), P < 0.001] and the T2 relaxation time was significantly higher (46.2 ± 3.6 vs. 42.7 ± 2.8 ms, P = 0.002) post-COVID-19 compared to healthy controls. Stress MBF and T1 and T2 relaxation times were not correlated to the COVID-19 severity (Spearman r = -0.302, -0.070, and -0.297, respectively) or the presence of symptoms. The stress MBF showed a U-shaped relation to time from PCR to CMR, no correlation to T1 relaxation time, and a negative correlation to T2 relaxation time (Pearson r = -0.446, P = 0.029). Conclusion: While we found a significantly reduced microvascular perfusion post-COVID-19 compared to healthy controls, this reduction was not related to symptoms or COVID-19 severity.

High-Resolution Free-Breathing Quantitative First-Pass Perfusion Cardiac MR Using Dual-Echo Dixon With Spatio-Temporal Acceleration.

Introduction: To develop and test the feasibility of free-breathing (FB), high-resolution quantitative first-pass perfusion cardiac MR (FPP-CMR) using dual-echo Dixon (FOSTERS; Fat-water separation for mOtion-corrected Spatio-TEmporally accelerated myocardial peRfuSion). Materials and Methods: FOSTERS was performed in FB using a dual-saturation single-bolus acquisition with dual-echo Dixon and a dynamically variable Cartesian k-t undersampling (8-fold) approach, with low-rank and sparsity constrained reconstruction, to achieve high-resolution FPP-CMR images. FOSTERS also included automatic in-plane motion estimation and T 2 * correction to obtain quantitative myocardial blood flow (MBF) maps. High-resolution (1.6 x 1.6 mm2) FB FOSTERS was evaluated in eleven patients, during rest, against standard-resolution (2.6 x 2.6 mm2) 2-fold SENSE-accelerated breath-hold (BH) FPP-CMR. In addition, MBF was computed for FOSTERS and spatial wavelet-based compressed sensing (CS) reconstruction. Two cardiologists scored the image quality (IQ) of FOSTERS, CS, and standard BH FPP-CMR images using a 4-point scale (1-4, non-diagnostic - fully diagnostic). Results: FOSTERS produced high-quality images without dark-rim and with reduced motion-related artifacts, using an 8x accelerated FB acquisition. FOSTERS and standard BH FPP-CMR exhibited excellent IQ with an average score of 3.5 ± 0.6 and 3.4 ± 0.6 (no statistical difference, p > 0.05), respectively. CS images exhibited severe artifacts and high levels of noise, resulting in an average IQ score of 2.9 ± 0.5. MBF values obtained with FOSTERS presented a lower variance than those obtained with CS. Discussion: FOSTERS enabled high-resolution FB FPP-CMR with MBF quantification. Combining motion correction with a low-rank and sparsity-constrained reconstruction results in excellent image quality.

CardiSort: a convolutional neural network for cross vendor automated sorting of cardiac MR images.

OBJECTIVES: To develop an image-based automatic deep learning method to classify cardiac MR images by sequence type and imaging plane for improved clinical post-processing efficiency. METHODS: Multivendor cardiac MRI studies were retrospectively collected from 4 centres and 3 vendors. A two-head convolutional neural network ('CardiSort') was trained to classify 35 sequences by imaging sequence (n = 17) and plane (n = 10). Single vendor training (SVT) on single-centre images (n = 234 patients) and multivendor training (MVT) with multicentre images (n = 434 patients, 3 centres) were performed. Model accuracy and F1 scores on a hold-out test set were calculated, with ground truth labels by an expert radiologist. External validation of MVT (MVTexternal) was performed on data from 3 previously unseen magnet systems from 2 vendors (n = 80 patients). RESULTS: Model sequence/plane/overall accuracy and F1-scores were 85.2%/93.2%/81.8% and 0.82 for SVT and 96.1%/97.9%/94.3% and 0.94 MVT on the hold-out test set. MVTexternal yielded sequence/plane/combined accuracy and F1-scores of 92.7%/93.0%/86.6% and 0.86. There was high accuracy for common sequences and conventional cardiac planes. Poor accuracy was observed for underrepresented classes and sequences where there was greater variability in acquisition parameters across centres, such as perfusion imaging. CONCLUSIONS: A deep learning network was developed on multivendor data to classify MRI studies into component sequences and planes, with external validation. With refinement, it has potential to improve workflow by enabling automated sequence selection, an important first step in completely automated post-processing pipelines. KEY POINTS: • Deep learning can be applied for consistent and efficient classification of cardiac MR image types. • A multicentre, multivendor study using a deep learning algorithm (CardiSort) showed high classification accuracy on a hold-out test set with good generalisation to images from previously unseen magnet systems. • CardiSort has potential to improve clinical workflows, as a vital first step in developing fully automated post-processing pipelines.

Physics-informed neural networks for myocardial perfusion MRI quantification.

Tracer-kinetic models allow for the quantification of kinetic parameters such as blood flow from dynamic contrast-enhanced magnetic resonance (MR) images. Fitting the observed data with multi-compartment exchange models is desirable, as they are physiologically plausible and resolve directly for blood flow and microvascular function. However, the reliability of model fitting is limited by the low signal-to-noise ratio, temporal resolution, and acquisition length. This may result in inaccurate parameter estimates. This study introduces physics-informed neural networks (PINNs) as a means to perform myocardial perfusion MR quantification, which provides a versatile scheme for the inference of kinetic parameters. These neural networks can be trained to fit the observed perfusion MR data while respecting the underlying physical conservation laws described by a multi-compartment exchange model. Here, we provide a framework for the implementation of PINNs in myocardial perfusion MR. The approach is validated both in silico and in vivo. In the in silico study, an overall decrease in mean-squared error with the ground-truth parameters was observed compared to a standard non-linear least squares fitting approach. The in vivo study demonstrates that the method produces parameter values comparable to those previously found in literature, as well as providing parameter maps which match the clinical diagnosis of patients.

Deep learning applications in coronary anatomy imaging: a systematic review and meta-analysis.

Background: The application of deep learning on medical imaging is growing in prevalence in the recent literature. One of the most studied areas is coronary artery disease (CAD). Imaging of coronary artery anatomy is fundamental, which has led to a high number of publications describing a variety of techniques. The aim of this systematic review is to review the evidence behind the accuracy of deep learning applications in coronary anatomy imaging. Methods: The search for the relevant studies, which applied deep learning on coronary anatomy imaging, was performed in a systematic approach on MEDLINE and EMBASE databases, followed by reviewing of abstracts and full texts. The data from the final studies was retrieved using data extraction forms. A meta-analysis was performed on a subgroup of studies, which looked at fractional flow reserve (FFR) prediction. Heterogeneity was tested using tau2, I2 and Q tests. Finally, a risk of bias was performed using Quality Assessment of Diagnostic Accuracy Studies (QUADAS) approach. Results: A total of 81 studies met the inclusion criteria. The most common imaging modality was coronary computed tomography angiography (CCTA) (58%) and the most common deep learning method was convolutional neural network (CNN) (52%). The majority of studies demonstrated good performance metrics. The most common outputs were focused on coronary artery segmentation, clinical outcome prediction, coronary calcium quantification and FFR prediction, and most studies reported area under the curve (AUC) of ≥80%. The pooled diagnostic odds ratio (DOR) derived from 8 studies looking at FFR prediction using CCTA was 12.5 using the Mantel-Haenszel (MH) method. There was no significant heterogeneity amongst studies according to Q test (P=0.2496). Conclusions: Deep learning has been used in many applications on coronary anatomy imaging, most of which are yet to be externally validated and prepared for clinical use. The performance of deep learning, especially CNN models, proved to be powerful and some applications have already translated into medical practice, such as computed tomography (CT)-FFR. These applications have the potential to translate technology into better care of CAD patients.

Automated Quantitative Stress Perfusion Cardiac Magnetic Resonance in Pediatric Patients.

Background: Myocardial ischemia occurs in pediatrics, as a result of both congenital and acquired heart diseases, and can lead to further adverse cardiac events if untreated. The aim of this work is to assess the feasibility of fully automated, high resolution, quantitative stress myocardial perfusion cardiac magnetic resonance (CMR) in a cohort of pediatric patients and to evaluate its agreement with the coronary anatomical status of the patients. Methods: Fourteen pediatric patients, with 16 scans, who underwent dual-bolus stress perfusion CMR were retrospectively analyzed. All patients also had anatomical coronary assessment with either CMR, CT, or X-ray angiography. The perfusion CMR images were automatically processed and quantified using an analysis pipeline previously developed in adults. Results: Automated perfusion quantification was successful in 15/16 cases. The coronary perfusion territories supplied by vessels affected by a medium/large aneurysm or stenosis (according to the AHA guidelines), induced by Kawasaki disease, an anomalous origin, or interarterial course had significantly reduced myocardial blood flow (MBF) (median (interquartile range), 1.26 (1.05, 1.67) ml/min/g) as compared to territories supplied by unaffected coronaries [2.57 (2.02, 2.69) ml/min/g, p < 0.001] and territories supplied by vessels with a small aneurysm [2.52 (2.45, 2.83) ml/min/g, p = 0.002]. Conclusion: Automatic CMR-derived MBF quantification is feasible in pediatric patients, and the technology could be potentially used for objective non-invasive assessment of ischemia in children with congenital and acquired heart diseases.

Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge.

The emergence of deep learning has considerably advanced the state-of-the-art in cardiac magnetic resonance (CMR) segmentation. Many techniques have been proposed over the last few years, bringing the accuracy of automated segmentation close to human performance. However, these models have been all too often trained and validated using cardiac imaging samples from single clinical centres or homogeneous imaging protocols. This has prevented the development and validation of models that are generalizable across different clinical centres, imaging conditions or scanner vendors. To promote further research and scientific benchmarking in the field of generalizable deep learning for cardiac segmentation, this paper presents the results of the Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms) Challenge, which was recently organized as part of the MICCAI 2020 Conference. A total of 14 teams submitted different solutions to the problem, combining various baseline models, data augmentation strategies, and domain adaptation techniques. The obtained results indicate the importance of intensity-driven data augmentation, as well as the need for further research to improve generalizability towards unseen scanner vendors or new imaging protocols. Furthermore, we present a new resource of 375 heterogeneous CMR datasets acquired by using four different scanner vendors in six hospitals and three different countries (Spain, Canada and Germany), which we provide as open-access for the community to enable future research in the field.

High-Resolution Cardiac Magnetic Resonance Imaging Techniques for the Identification of Coronary Microvascular Dysfunction.

OBJECTIVES: This study assessed the ability to identify coronary microvascular dysfunction (CMD) in patients with angina and nonobstructive coronary artery disease (NOCAD) using high-resolution cardiac magnetic resonance (CMR) and hypothesized that quantitative perfusion techniques would have greater accuracy than visual analysis. BACKGROUND: Half of all patients with angina are found to have NOCAD, while the presence of CMD portends greater morbidity and mortality, it now represents a modifiable therapeutic target. Diagnosis currently requires invasive assessment of coronary blood flow during angiography. With greater reliance on computed tomography coronary angiography as a first-line tool to investigate angina, noninvasive tests for diagnosing CMD warrant validation. METHODS: Consecutive patients with angina and NOCAD were enrolled. Intracoronary pressure and flow measurements were acquired during rest and vasodilator-mediated hyperemia. CMR (3-T) was performed and analyzed by visual and quantitative techniques, including calculation of myocardial blood flow (MBF) during hyperemia (stress MBF), transmural myocardial perfusion reserve (MPR: MBFHYPEREMIA / MBFREST), and subendocardial MPR (MPRENDO). CMD was defined dichotomously as an invasive coronary flow reserve <2.5, with CMR readers blinded to this classification. RESULTS: A total of 75 patients were enrolled (57 ± 10 years of age, 81% women). Among the quantitative perfusion indices, MPRENDO and MPR had the highest accuracy (area under the curve [AUC]: 0.90 and 0.88) with high sensitivity and specificity, respectively, both superior to visual assessment (both p < 0.001). Visual assessment identified CMD with 58% accuracy (41% sensitivity and 83% specificity). Quantitative stress MBF performed similarly to visual analysis (AUC: 0.64 vs. 0.60; p = 0.69). CONCLUSIONS: High-resolution CMR has good accuracy at detecting CMD but only when analyzed quantitatively. Although omission of rest imaging and stress-only protocols make for quicker scans, this is at the cost of accuracy compared with integrating rest and stress perfusion. Quantitative perfusion CMR has an increasingly important role in the management of patients frequently encountered with angina and NOCAD.