Pulmonary Artery Stenosis After an Orthotopic Heart Transplantation: A Case Report With Cardiac Imaging Findings and a Literature Review.

Pulmonary artery stenosis is a rare complication of heart transplantation. It is typically a congenital condition or can be secondary to rheumatic fever, systemic vasculitis like Behcet's disease, or Takayasu's arteritis. It can also occur as a rarity of a delayed complication post-heart transplant. In this report, we describe the imaging findings of pulmonary artery stenosis in a patient who underwent an orthotopic heart transplant more than 10 years prior. Dynamic cardiac magnetic resonance imaging (MRI), phase contrast imaging, and MR angiography in the management of pulmonary artery stenosis helped in heart and pulmonary circulation. Functional evaluation can be achieved with current multichannel transmit-receive coils. Cardiac gated pre- and dynamic contrast-enhanced MR was performed with phase-contrast imaging for further evaluation confirming the diagnosis of pulmonary artery stenosis.

Computed Tomography Angiography for Aortic Diseases.

Aortic pathologies encompass a heterogeneous group of disorders, including acute aortic syndrome, traumatic aortic injury , aneurysm, aortitis, and atherosclerosis. The clinical manifestations of these disorders can be varied and non-specific, ranging from acute presentations in the emergency department to chronic incidental findings in an outpatient setting. Given the non-specific nature of their clinical presentations, the reliance on non-invasive imaging for screening, definitive diagnosis, therapeutic strategy planning, and post-intervention surveillance has become paramount. Commonly used imaging modalities include ultrasound, computed tomography (CT), and MR imaging. Among these modalities, computed tomography angiography (CTA) has emerged as a first-line imaging modality owing to its excellent anatomic detail, widespread availability, established imaging protocols, evidence-proven indications, and rapid acquisition time.

Utilizing Artificial Intelligence-Based Deformable Registration for Global and Layer-Specific Cardiac MRI Strain Analysis in Healthy Children and Young Adults.

RATIONALE AND OBJECTIVES: The absence of published reference values for multilayer-specific strain measurement using cardiac magnetic resonance (CMR) in young healthy individuals limits its use. This study aimed to establish normal global and layer-specific strain values in healthy children and young adults using a deformable registration algorithm (DRA). MATERIALS AND METHODS: A retrospective study included 131 healthy children and young adults (62 males and 69 females) with a mean age of 16.6 ± 3.9 years. CMR examinations were conducted using 1.5T scanners, and strain analysis was performed using TrufiStrain research prototype software (Siemens Healthineers, Erlangen, Germany). Global and layer-specific strain parameters were extracted from balanced Steady-state free precession cine images. Statistical analyses were conducted to evaluate the impact of demographic variables on strain measurements. RESULTS: The peak global longitudinal strain (LS) was -16.0 ± 3.0%, peak global radial strain (RS) was 29.9 ± 6.3%, and peak global circumferential strain (CS) was -17.0 ± 1.8%. Global LS differed significantly between males and females. Transmural strain analysis showed a consistent pattern of decreasing LS and CS from endocardium to epicardium, while radial strain increased. Basal-to-apical strain distribution exhibited decreasing LS and increasing CS in both global and layer-specific analysis. CONCLUSION: This study uses DRA to provide reference values for global and layer-specific strain in healthy children and young adults. The study highlights the impact of sex and age on LS and body mass index on RS. These insights are vital for future cardiac assessments in children, particularly for early detection of heart diseases.

Optimizing Deep Learning for Cardiac MRI Segmentation: The Impact of Automated Slice Range Classification.

RATIONALE AND OBJECTIVES: Cardiac magnetic resonance imaging is crucial for diagnosing cardiovascular diseases, but lengthy postprocessing and manual segmentation can lead to observer bias. Deep learning (DL) has been proposed for automated cardiac segmentation; however, its effectiveness is limited by the slice range selection from base to apex. MATERIALS AND METHODS: In this study, we integrated an automated slice range classification step to identify basal to apical short-axis slices before DL-based segmentation. We employed publicly available Multi-Disease, Multi-View & Multi-Center Right Ventricular Segmentation in Cardiac MRI data set with short-axis cine data from 160 training, 40 validation, and 160 testing cases. Three classification and seven segmentation DL models were studied. The top-performing segmentation model was assessed with and without the classification model. Model validation to compare automated and manual segmentation was performed using Dice score and Hausdorff distance and clinical indices (correlation score and Bland-Altman plots). RESULTS: The combined classification (CBAM-integrated 2D-CNN) and segmentation model (2D-UNet with dilated convolution block) demonstrated superior performance, achieving Dice scores of 0.952 for left ventricle (LV), 0.933 for right ventricle (RV), and 0.875 for myocardium, compared to the stand-alone segmentation model (0.949 for LV, 0.925 for RV, and 0.867 for myocardium). Combined classification and segmentation model showed high correlation (0.92-0.99) with manual segmentation for biventricular volumes, ejection fraction, and myocardial mass. The mean absolute difference (2.8-8.3 mL) for clinical parameters between automated and manual segmentation was within the interobserver variability range, indicating comparable performance to manual annotation. CONCLUSION: Integrating an initial automated slice range classification step into the segmentation process improves the performance of DL-based cardiac chamber segmentation.

"From Vision to Reality: Virtual Reality's Impact on Baffle Planning in Congenital Heart Disease".

This study aims to evaluate the feasibility and utility of virtual reality (VR) for baffle planning in congenital heart disease (CHD), specifically by creating patient-specific 3D heart models and assessing a user-friendly VR interface. Patient-specific 3D heart models were created using high-resolution imaging data and a VR interface was developed for baffle planning. The process of model creation and the VR interface were assessed for their feasibility, usability, and clinical relevance. Collaborative and interactive planning within the VR space were also explored. The study findings demonstrate the feasibility and usefulness of VR in baffle planning for CHD. Patient-specific 3D heart models generated from imaging data provided valuable insights into complex spatial relationships. The developed VR interface allowed clinicians to interact with the models, simulate different baffle configurations, and assess their impact on blood flow. The VR space's collaborative and interactive planning enhanced the baffle planning process. This study highlights the potential of VR as a valuable tool in baffle planning for CHD. The findings demonstrate the feasibility of using patient-specific 3D heart models and a user-friendly VR interface to enhance surgical planning and patient outcomes. Further research and development in this field are warranted to harness the full benefits of VR technology in CHD surgical management.

Differentiation Between Glioblastoma and Metastatic Disease on Conventional MRI Imaging Using 3D-Convolutional Neural Networks: Model Development and Validation.

RATIONALE AND OBJECTIVES: Imaging-based differentiation between glioblastoma (GB) and brain metastases (BM) remains challenging. Our aim was to evaluate the performance of 3D-convolutional neural networks (CNN) to address this binary classification problem. MATERIALS AND METHODS: T1-CE, T2WI, and FLAIR 3D-segmented masks of 307 patients (157 GB and 150 BM) were generated post resampling, co-registration normalization and semi-automated 3D-segmentation and used for internal model development. Subsequent external validation was performed on 59 cases (27 GB and 32 BM) from another institution. Four different mask-sequence combinations were evaluated using area under the curve (AUC), precision, recall and F1-scores. Diagnostic performance of a neuroradiologist and a general radiologist, both without and with the model output available, was also assessed. RESULTS: 3D-model using the T1-CE tumor mask (TM) showed the highest performance [AUC 0.93 (95% CI 0.858-0.995)] on the external test set, followed closely by the model using T1-CE TM and FLAIR mask of peri-tumoral region (PTR) [AUC of 0.91 (95% CI 0.834-0.986)]. Models using T2WI masks showed robust performance on the internal dataset but lower performance on the external set. Both neuroradiologist and general radiologist showed improved performance with model output provided [AUC increased from 0.89 to 0.968 (p = 0.06) and from 0.78 to 0.965 (p = 0.007) respectively], the latter being statistically significant. CONCLUSION: 3D-CNNs showed robust performance for differentiating GB from BMs, with T1-CE TM, either alone or combined with FLAIR-PTR masks. Availability of model output significantly improved the accuracy of the general radiologist.

Clinical and Magnetic Resonance Imaging Radiomics-Based Survival Prediction in Glioblastoma Using Multiparametric Magnetic Resonance Imaging.

INTRODUCTION: Survival prediction in glioblastoma remains challenging, and identification of robust imaging markers could help with this relevant clinical problem. We evaluated multiparametric magnetic resonance imaging-derived radiomics to assess prediction of overall survival (OS) and progression-free survival (PFS). METHODOLOGY: A retrospective, institutional review board-approved study was performed. There were 93 eligible patients, of which 55 underwent gross tumor resection and chemoradiation (GTR-CR). Overall survival and PFS were assessed in the entire cohort and the GTR-CR cohort using multiple machine learning pipelines. A model based on multiple clinical variables was also developed. Survival prediction was assessed using the radiomics-only, clinical-only, and the radiomics and clinical combined models. RESULTS: For all patients combined, the clinical feature-derived model outperformed the best radiomics model for both OS (C-index, 0.706 vs 0.597; P < 0.0001) and PFS prediction (C-index, 0.675 vs 0.588; P < 0.001). Within the GTR-CR cohort, the radiomics model showed nonstatistically improved performance over the clinical model for predicting OS (C-index, 0.638 vs 0.588; P = 0.4). However, the radiomics model outperformed the clinical feature model for predicting PFS in GTR-CR cohort (C-index, 0.641 vs 0.550; P = 0.004). Combined clinical and radiomics model did not yield superior prediction when compared with the best model in each case. CONCLUSIONS: When considering all patients, regardless of therapy, the radiomics-derived prediction of OS and PFS is inferior to that from a model derived from clinical features alone. However, in patients with GTR-CR, radiomics-only model outperforms clinical feature-derived model for predicting PFS.

ComBat Harmonization of Myocardial Radiomic Features Sensitive to Cardiac MRI Acquisition Parameters.

Purpose: To investigate the effect of ComBat harmonization methods on the robustness of cardiac MRI-derived radiomic features to variations in imaging parameters. Materials and Methods: This Health Insurance Portability and Accountability Act-compliant retrospective study used a publicly available data set of 11 healthy controls (mean age, 33 years ± 16 [SD]; six men) and five patients (mean age, 52 years ± 16; four men). A single midventricular short-axis section was acquired with 3-T MRI using cine balanced steady-state free precision, T1-weighted, T2-weighted, T1 mapping, and T2 mapping imaging sequences. Each sequence was acquired using baseline parameters and after variations in flip angle, spatial resolution, section thickness, and parallel imaging. Image registration was performed for all sequences at a per-individual level. Manual myocardial contouring was performed, and 1652 radiomic features per sequence were extracted using baseline and variations in imaging parameters. Radiomic feature stability to change in imaging parameters was assessed using Cohen d sensitivity. The stability of radiomic features was assessed both without and after ComBat harmonization of radiomic features. Three ComBat methods were studied: parametric, nonparametric, and Gaussian mixture model (GMM). Results: For all sequences combined, 51.4% of features were robust to changes in imaging parameters when no ComBat method was applied. ComBat harmonization substantially increased the number of stable features to 95.1% (95% CI: 94.9, 95.3) when parametric ComBat was used and 90.9% (95% CI: 90.6, 91.2) when nonparametric ComBat was used. GMM combat resulted in only 52.6% stable features. Conclusion: ComBat harmonization improved the stability of radiomic features to changes in imaging parameters across all cardiac MRI sequences.Keywords: Cardiac MRI, Radiomics, ComBat, Harmonization Supplemental material is available for this article. © RSNA, 2023.

Proposed competencies for the performance of cardiovascular computed tomography in pediatric and adult congenital heart disease.

Cardiovascular computed tomography (CCT) is rated appropriate by published guidelines for the initial evaluation and follow up of congenital heart disease (CHD) and is an essential modality in cardiac imaging programs for patients of all ages. However, no recommended core competencies exist to guide CCT in CHD imaging training pathways, curricula development, or establishment of a more formal educational platform. To fill this gap, a group of experienced congenital cardiac imagers, intentionally inclusive of adult and pediatric cardiologists and radiologists, was formed to propose core competencies fundamental to the expert-level performance of CCT in pediatric acquired and congenital heart disease and adult CHD. The 2020 SCCT Guideline for Training Cardiology and Radiology Trainees as Independent Practitioners (Level II) and Advanced Practitioners (Level III) in Cardiovascular Computed Tomography (1) for adult imaging were used as a framework to define pediatric and CHD-specific competencies. Established competencies will be immediately relevant for advanced cardiac imaging fellowships in both cardiology and radiology training pathways. Proposed future steps include radiology and cardiology society collaboration to establish provider certification levels, training case-volume recommendations, and continuing medical education (CME) requirements for expert-level performance of CCT in pediatric and adult CHD.

AI-based classification of three common malignant tumors in neuro-oncology: A multi-institutional comparison of machine learning and deep learning methods.

PURPOSE: To determine if machine learning (ML) or deep learning (DL) pipelines perform better in AI-based three-class classification of glioblastoma (GBM), intracranial metastatic disease (IMD) and primary CNS lymphoma (PCNSL). METHODOLOGY: Retrospective analysis included 502 cases for training (208 GBM, 67 PCNSL and 227 IMD), with external validation on 86 cases (27:27:32). Multiparametric MRI images (T1W, T2W, FLAIR, DWI and T1-CE) were co-registered, resampled, denoised and intensity normalized, followed by semiautomatic 3D segmentation of the enhancing tumor (ET) and peritumoral region (PTR). Model performance was assessed using several ML pipelines and 3D-convolutional neural networks (3D-CNN) using sequence specific masks, as well as combination of masks. All pipelines were trained and evaluated with 5-fold nested cross-validation on internal data followed by external validation using multi-class AUC. RESULTS: Two ML models achieved similar performance on test set, one using T2-ET and T2-PTR masks (AUC: 0.885, 95% CI: [0.816, 0.935] and another using T1-CE-ET and FLAIR-PTR mask (AUC: 0.878, CI: [0.804, 0.930]). The best performing DL models achieved an AUC of 0.854, (CI [0.774, 0.914]) on external data using T1-CE-ET and T2-PTR masks, followed by model derived from T1-CE-ET, ADC-ET and FLAIR-PTR masks (AUC: 0.851, CI [0.772, 0.909]). CONCLUSION: Both ML and DL derived pipelines achieved similar performance. T1-CE mask was used in three of the top four overall models. Additionally, all four models had some mask derived from PTR, either T2WI or FLAIR.

Automatic Multiple Articulator Segmentation in Dynamic Speech MRI Using a Protocol Adaptive Stacked Transfer Learning U-NET Model.

Dynamic magnetic resonance imaging has emerged as a powerful modality for investigating upper-airway function during speech production. Analyzing the changes in the vocal tract airspace, including the position of soft-tissue articulators (e.g., the tongue and velum), enhances our understanding of speech production. The advent of various fast speech MRI protocols based on sparse sampling and constrained reconstruction has led to the creation of dynamic speech MRI datasets on the order of 80-100 image frames/second. In this paper, we propose a stacked transfer learning U-NET model to segment the deforming vocal tract in 2D mid-sagittal slices of dynamic speech MRI. Our approach leverages (a) low- and mid-level features and (b) high-level features. The low- and mid-level features are derived from models pre-trained on labeled open-source brain tumor MR and lung CT datasets, and an in-house airway labeled dataset. The high-level features are derived from labeled protocol-specific MR images. The applicability of our approach to segmenting dynamic datasets is demonstrated in data acquired from three fast speech MRI protocols: Protocol 1: 3 T-based radial acquisition scheme coupled with a non-linear temporal regularizer, where speakers were producing French speech tokens; Protocol 2: 1.5 T-based uniform density spiral acquisition scheme coupled with a temporal finite difference (FD) sparsity regularization, where speakers were producing fluent speech tokens in English, and Protocol 3: 3 T-based variable density spiral acquisition scheme coupled with manifold regularization, where speakers were producing various speech tokens from the International Phonetic Alphabetic (IPA). Segments from our approach were compared to those from an expert human user (a vocologist), and the conventional U-NET model without transfer learning. Segmentations from a second expert human user (a radiologist) were used as ground truth. Evaluations were performed using the quantitative DICE similarity metric, the Hausdorff distance metric, and segmentation count metric. This approach was successfully adapted to different speech MRI protocols with only a handful of protocol-specific images (e.g., of the order of 20 images), and provided accurate segmentations similar to those of an expert human.

Utility of cardiac magnetic resonance imaging in diagnosing eosinophilic myocarditis in a patient recently recovered from COVID-19: a grand round case report.

Background: Eosinophilic myocarditis (EM) secondary to eosinophilic granulomatosis with polyangiitis (EGPA) is a rare disease, for which cardiac magnetic resonance imaging (CMRI) is a useful non-invasive modality for diagnosis. We present a case of EM in a patient who recently recovered from COVID-19 and discuss the role of CMRI and endomyocardial biopsy (EMB) to differentiate between COVID-19-associated myocarditis and EM. Case summary: A 20-year-old Hispanic male with a history of sinusitis and asthma, and who recently recovered from COVID-19, presented to the emergency room with pleuritic chest pain, dyspnoea on exertion, and cough. His presentation labs were pertinent for leucocytosis, eosinophilia, elevated troponin, and elevated erythrocyte sedimentation rate and C-reactive protein. The electrocardiogram showed sinus tachycardia. Echocardiogram showed an ejection fraction of 40%. The patient was admitted, and on day 2 of admission, he underwent CMRI which showed findings of EM and mural thrombi. On hospital day 3, the patient underwent right heart catheterization and EMB which confirmed EM. The patient was treated with steroids and mepolizumab. He was discharged on hospital day 7 and continued outpatient heart failure treatment. Discussion: This is a unique case of EM and heart failure with reduced ejection fraction as a presentation of EGPA, in a patient who recently recovered from COVID-19. In this case, CMRI and EMB were critical to identify the cause of myocarditis and helped in the optimal management of this patient.

Joint Cardiac T1 Mapping and Cardiac Cine Using Manifold Modeling.

The main focus of this work is to introduce a single free-breathing and ungated imaging protocol to jointly estimate cardiac function and myocardial T1 maps. We reconstruct a time series of images corresponding to k-space data from a free-breathing and ungated inversion recovery gradient echo sequence using a manifold algorithm. We model each image in the time series as a non-linear function of three variables: cardiac and respiratory phases and inversion time. The non-linear function is realized using a convolutional neural networks (CNN) generator, while the CNN parameters, as well as the phase information, are estimated from the measured k-t space data. We use a dense conditional auto-encoder to estimate the cardiac and respiratory phases from the central multi-channel k-space samples acquired at each frame. The latent vectors of the auto-encoder are constrained to be bandlimited functions with appropriate frequency bands, which enables the disentanglement of the latent vectors into cardiac and respiratory phases, even when the data are acquired with intermittent inversion pulses. Once the phases are estimated, we pose the image recovery as the learning of the parameters of the CNN generator from the measured k-t space data. The learned CNN generator is used to generate synthetic data on demand by feeding it with appropriate latent vectors. The proposed approach capitalizes on the synergies between cine MRI and T1 mapping to reduce the scan time and improve patient comfort. The framework also enables the generation of synthetic breath-held cine movies with different inversion contrasts, which improves the visualization of the myocardium. In addition, the approach also enables the estimation of the T1 maps with specific phases, which is challenging with breath-held approaches.

Subclinical cardiac involvement in student athletes after COVID-19 infection - Evaluation using feature tracking cardiac MRI strain analysis.

OBJECTIVES: To evaluate subclinical cardiac dysfunction in student athletes after COVID-19 infection using feature tracking cardiac MRI strain analysis. METHODS: Student athletes with history of COVID-19 infection underwent cardiac MRI as part of screening before return to competitive play. Subjects were enrolled if they had no or mild symptoms, normal cardiac MRI findings with no imaging evidence of myocarditis. Feature tracking strain analysis was performed using short and long axis cine MRI images of athletes and a separate cohort of healthy controls. Differences between the cardiac strain parameters were statistically analyzed by Mann-Whitney U test. RESULTS: The study cohort included 122 athletes (49 females, mean age 20 years ± 1.5 standard deviations) who had a history of COVID-19, and 35 healthy controls (24 females, mean age 34 years ± 18 standard deviations). COVID-19 positive athletes had normal physiologic cardiac adaptations, including significantly higher left and right ventricle end-diastolic volumes (p = 0.00001) when compared to healthy controls. There was no significant difference between biventricular ejection fraction between athletes and control subjects (p > 0.05). Cardiac MRI parameters, including left ventricle global longitudinal strain (LV-GLS), global circumferential strain (LV-GCS), and global radial strain (LV-GRS) values were normal but slightly lower in athletes compared to controls. LV-GCS and LV-GRS were significantly lower in athletes compared to controls (p = 0.007 and p = 0.005 respectively), but there was no significant difference for LV-GLS (p = 0.088). CONCLUSION: In this study of 122 athletes, there was no evidence of subclinical myocardial alterations following recovery from COVID-19 found on cardiac MRI strain analysis. When compared to healthy controls, the competitive athletes had higher end-diastolic volume indices and reduced, albeit normal, strain values of LV-GLS, LV-GCS, and LV-GRS.

Evaluating Autoencoders for Dimensionality Reduction of MRI-derived Radiomics and Classification of Malignant Brain Tumors.

Malignant brain tumors including parenchymal metastatic (MET) lesions, glioblastomas (GBM), and lymphomas (LYM) account for 29.7% of brain cancers. However, the characterization of these tumors from MRI imaging is difficult due to the similarity of their radiologically observed image features. Radiomics is the extraction of quantitative imaging features to characterize tumor intensity, shape, and texture. Applying machine learning over radiomic features could aid diagnostics by improving the classification of these common brain tumors. However, since the number of radiomic features is typically larger than the number of patients in the study, dimensionality reduction is needed to balance feature dimensionality and model complexity. Autoencoders are a form of unsupervised representation learning that can be used for dimensionality reduction. It is similar to PCA but uses a more complex and non-linear model to learn a compact latent space. In this work, we examine the effectiveness of autoencoders for dimensionality reduction on the radiomic feature space of multiparametric MRI images and the classification of malignant brain tumors: GBM, LYM, and MET. We further aim to address the class imbalances imposed by the rarity of lymphomas by examining different approaches to increase overall predictive performance through multiclass decomposition strategies.

Motion Compensated Unsupervised Deep Learning for 5D MRI.

We propose an unsupervised deep learning algorithm for the motion-compensated reconstruction of 5D cardiac MRI data from 3D radial acquisitions. Ungated free-breathing 5D MRI simplifies the scan planning, improves patient comfort, and offers several clinical benefits over breath-held 2D exams, including isotropic spatial resolution and the ability to reslice the data to arbitrary views. However, the current reconstruction algorithms for 5D MRI take very long computational time, and their outcome is greatly dependent on the uniformity of the binning of the acquired data into different physiological phases. The proposed algorithm is a more data-efficient alternative to current motion-resolved reconstructions. This motion-compensated approach models the data in each cardiac/respiratory bin as Fourier samples of the deformed version of a 3D image template. The deformation maps are modeled by a convolutional neural network driven by the physiological phase information. The deformation maps and the template are then jointly estimated from the measured data. The cardiac and respiratory phases are estimated from 1D navigators using an auto-encoder. The proposed algorithm is validated on 5D bSSFP datasets acquired from two subjects.

Image level detection of large vessel occlusion on 4D-CTA perfusion data using deep learning in acute stroke.

OBJECTIVES: Automated image-level detection of large vessel occlusions (LVO) could expedite patient triage for mechanical thrombectomy. A few studies have previously attempted LVO detection using artificial intelligence (AI) on CT angiography (CTA) images. To our knowledge this is the first study to detect LVO existence and location on raw 4D-CTA/ CT perfusion (CTP) images using neural network (NN) models. MATERIALS AND METHODS: Retrospective study using data from a level-I stroke center was performed. A total of 306 (187 with LVO, and 119 without) patients were evaluated. Image pre-processing included co-registration, normalization and skull stripping. Five consecutive time-points for each patient were selected to provide variable contrast density in data. Additional data augmentation included rotation and horizonal image flipping. Our model architecture consisted of two neural networks, first for classification (based on hemispheric asymmetry), followed by second model for exact site of LVO detection. Only cases deemed positive by the classification model were routed to the detection model, thereby reducing false positives and improving specificity. The results were compared with expert annotated LVO detection. RESULTS: Using a 80:20 split for training and validation, the combination of both classification and detection model achieved a sensitivity of 86.5%, a specificity of 89.5%, and an accuracy of 87.5%. A 5-fold cross-validation using the entire data achieved a mean sensitivity of 82.7%, a specificity of 89.8%, and an accuracy of 85.5% and a mean AUC of 0.89 (95% CI: 0.85-0.93). CONCLUSION: Our findings suggest that accurate image-level LVO detection is feasible on CTP raw images.

Variational Manifold Learning From Incomplete Data: Application to Multislice Dynamic MRI.

Current deep learning-based manifold learning algorithms such as the variational autoencoder (VAE) require fully sampled data to learn the probability density of real-world datasets. However, fully sampled data is often unavailable in a variety of problems, including the recovery of dynamic and high-resolution magnetic resonance imaging (MRI). We introduce a novel variational approach to learn a manifold from undersampled data. The VAE uses a decoder fed by latent vectors, drawn from a conditional density estimated from the fully sampled images using an encoder. Since fully sampled images are not available in our setting, we approximate the conditional density of the latent vectors by a parametric model whose parameters are estimated from the undersampled measurements using back-propagation. We use the framework for the joint alignment and recovery of multi-slice free breathing and ungated cardiac MRI data from highly undersampled measurements. Experimental results demonstrate the utility of the proposed scheme in dynamic imaging alignment and reconstructions.