Vivek Muthurangu

Endrit Pajaziti, Javier Montalt-Tordera, Claudio Capelli et al.

Computational fluid dynamics (CFD) can be used to simulate vascular haemodynamics and analyse potential treatment options. CFD has shown to be beneficial in improving patient outcomes. However, the implementation of CFD for routine clinical use is yet to be realised. Barriers for CFD include high computational resources, specialist experience needed for designing simulation set-ups, and long processing times. The aim of this study was to explore the use of machine learning (ML) to replicate conventional aortic CFD with automatic and fast regression models. Data used to train/test the model consisted of 3,000 CFD simulations performed on synthetically generated 3D aortic shapes. These subjects were generated from a statistical shape model (SSM) built on real patient-specific aortas (N=67). Inference performed on 200 test shapes resulted in average errors of 6.01% +/-3.12 SD and 3.99% +/-0.93 SD for pressure and velocity, respectively. Our ML-based models performed CFD in +/-0.075 seconds (4,000x faster than the solver). This proof-of-concept study shows that results from conventional vascular CFD can be reproduced using ML at a much faster rate, in an automatic process, and with high accuracy.

Olivier Jaubert, Javier Montalt-Tordera, James Brown et al.

Purpose: Real-time monitoring of cardiac output (CO) requires low latency reconstruction and segmentation of real-time phase contrast MR (PCMR), which has previously been difficult to perform. Here we propose a deep learning framework for 'Flow Reconstruction and Segmentation for low latency Cardiac Output monitoring' (FReSCO). Methods: Deep artifact suppression and segmentation U-Nets were independently trained. Breath hold spiral PCMR data (n=516) was synthetically undersampled using a variable density spiral sampling pattern and gridded to create aliased data for training of the artifact suppression U-net. A subset of the data (n=96) was segmented and used to train the segmentation U-net. Real-time spiral PCMR was prospectively acquired and then reconstructed and segmented using the trained models (FReSCO) at low latency at the scanner in 10 healthy subjects during rest, exercise and recovery periods. CO obtained via FReSCO was compared to a reference rest CO and rest and exercise Compressed Sensing (CS) CO. Results: FReSCO was demonstrated prospectively at the scanner. Beat-to-beat heartrate, stroke volume and CO could be visualized with a mean latency of 622ms. No significant differences were noted when compared to reference at rest (Bias = -0.21+-0.50 L/min, p=0.246) or CS at peak exercise (Bias=0.12+-0.48 L/min, p=0.458). Conclusion: FReSCO was successfully demonstrated for real-time monitoring of CO during exercise and could provide a convenient tool for assessment of the hemodynamic response to a range of stressors.

Tina Yao, Nicole St. Clair, Gabriel F. Miller et al.

Purpose: To develop and evaluate an end-to-end deep learning pipeline for segmentation and analysis of cardiac magnetic resonance images to provide core-lab processing for a multi-centre registry of Fontan patients. Materials and Methods: This retrospective study used training (n = 175), validation (n = 25) and testing (n = 50) cardiac magnetic resonance image exams collected from 13 institutions in the UK, US and Canada. The data was used to train and evaluate a pipeline containing three deep-learning models. The pipeline's performance was assessed on the Dice and IoU score between the automated and reference standard manual segmentation. Cardiac function values were calculated from both the automated and manual segmentation and evaluated using Bland-Altman analysis and paired t-tests. The overall pipeline was further evaluated qualitatively on 475 unseen patient exams. Results: For the 50 testing dataset, the pipeline achieved a median Dice score of 0.91 (0.89-0.94) for end-diastolic volume, 0.86 (0.82-0.89) for end-systolic volume, and 0.74 (0.70-0.77) for myocardial mass. The deep learning-derived end-diastolic volume, end-systolic volume, myocardial mass, stroke volume and ejection fraction had no statistical difference compared to the same values derived from manual segmentation with p values all greater than 0.05. For the 475 unseen patient exams, the pipeline achieved 68% adequate segmentation in both systole and diastole, 26% needed minor adjustments in either systole or diastole, 5% needed major adjustments, and the cropping model only failed in 0.4%. Conclusion: Deep learning pipeline can provide standardised 'core-lab' segmentation for Fontan patients. This pipeline can now be applied to the >4500 cardiac magnetic resonance exams currently in the FORCE registry as well as any new patients that are recruited.

Olivier Jaubert, Michele Pascale, Javier Montalt-Tordera et al.

Purpose: To develop and assess a deep learning (DL) pipeline to learn dynamic MR image reconstruction from publicly available natural videos (Inter4K). Materials and Methods: Learning was performed for a range of DL architectures (VarNet, 3D UNet, FastDVDNet) and corresponding sampling patterns (Cartesian, radial, spiral) either from true multi-coil cardiac MR data (N=692) or from pseudo-MR data simulated from Inter4K natural videos (N=692). Real-time undersampled dynamic MR images were reconstructed using DL networks trained with cardiac data and natural videos, and compressed sensing (CS). Differences were assessed in simulations (N=104 datasets) in terms of MSE, PSNR, and SSIM and prospectively for cardiac (short axis, four chambers, N=20) and speech (N=10) data in terms of subjective image quality ranking, SNR and Edge sharpness. Friedman Chi Square tests with post-hoc Nemenyi analysis were performed to assess statistical significance. Results: For all simulation metrics, DL networks trained with cardiac data outperformed DL networks trained with natural videos, which outperformed CS (p<0.05). However, in prospective experiments DL reconstructions using both training datasets were ranked similarly (and higher than CS) and presented no statistical differences in SNR and Edge Sharpness for most conditions. Additionally, high SSIM was measured between the DL methods with cardiac data and natural videos (SSIM>0.85). Conclusion: The developed pipeline enabled learning dynamic MR reconstruction from natural videos preserving DL reconstruction advantages such as high quality fast and ultra-fast reconstructions while overcoming some limitations (data scarcity or sharing). The natural video dataset, code and pre-trained networks are made readily available on github. Key Words: real-time; dynamic MRI; deep learning; image reconstruction; machine learning;

Michele Pascale, Vivek Muthurangu, Javier Montalt Tordera et al.

Three-dimensional (3D) imaging is popular in medical applications, however, anisotropic 3D volumes with thick, low-spatial-resolution slices are often acquired to reduce scan times. Deep learning (DL) offers a solution to recover high-resolution features through super-resolution reconstruction (SRR). Unfortunately, paired training data is unavailable in many 3D medical applications and therefore we propose a novel unpaired approach; CLADE (Cycle Loss Augmented Degradation Enhancement). CLADE uses a modified CycleGAN architecture with a cycle-consistent gradient mapping loss, to learn SRR of the low-resolution dimension, from disjoint patches of the high-resolution plane within the anisotropic 3D volume data itself. We show the feasibility of CLADE in abdominal MRI and abdominal CT and demonstrate significant improvements in CLADE image quality over low-resolution volumes and state-of-the-art self-supervised SRR; SMORE (Synthetic Multi-Orientation Resolution Enhancement). Quantitative PIQUE (qualitative perception-based image quality evaluator) scores and quantitative edge sharpness (ES - calculated as the maximum gradient of pixel intensities over a border of interest), showed superior performance for CLADE in both MRI and CT. Qualitatively CLADE had the best overall image quality and highest perceptual ES over the low-resolution volumes and SMORE. This paper demonstrates the potential of using CLADE for super-resolution reconstruction of anisotropic 3D medical imaging data without the need for paired 3D training data.

Julius Åkesson, Iulius Dragonu, Einar Heiberg et al.

Purpose: Real-time (RT) bSSFP MRI enables fast free-breathing cardiovascular imaging but requires 10-16 slices for functional assessment, resulting in prolonged scan times. Simultaneous multi-slice (SMS) imaging can reduce acquisition time but when combined with non-Cartesian trajectories, it relies on iterative reconstructions that preclude online use. This study investigates deep artifact suppression to facilitate rapid, online reconstruction of RT-SMS. Methods: A spiral bSSFP SMS RT sequence with two simultaneously acquired slices was implemented at 1.5 T. Reconstruction used slice separation in k-space, followed by deep artifact suppression in image space using a 3D U-Net. Ten healthy volunteers were imaged. RT-SMS image quality and reconstruction time were compared between deep artifact suppression and compressed sensing (CS) reconstructions. Left (LV) and right (RV) ventricular volumes at end diastole (EDV) and end systole (ESV) and LV mass (LVM) were compared between RT-SMS with deep artifact suppression and reference-standard breath-hold (BH) imaging. Results: The RT-SMS acquisition was ~13x faster than BH imaging (15 s vs 3 min 15 s). RT-SMS reconstruction using deep artifact suppression was ~50x faster than CS (30 s vs 24 min 55 s). Deep artifact suppression consistently outperformed CS in quantitative and qualitative image quality (p<0.001). Functional agreement between BH and RT-SMS with deep artifact suppression was good (LVEDV: -7.5 +/- 6.8 ml, LVESV: -0.9 +/- 4.2 ml, RVEDV: -6.4 +/- 8.4 ml, RVESV: 0.2 +/- 10.7 ml, LVM: -10.3 +/- 11.0 g). Conclusion: Online deep artifact suppression reconstruction for RT-SMS bSSFP CMR enables free-breathing short-axis coverage with a substantial reduction in acquisition and reconstruction time while maintaining diagnostic image quality.

Mark Wrobel, Michele Pascale, Tina Yao et al.

Background: Conventional cardiovascular magnetic resonance (CMR) in paediatric and congenital heart disease uses 2D, breath-hold, balanced steady state free precession (bSSFP) cine imaging for assessment of function and cardiac-gated, respiratory-navigated, static 3D bSSFP whole-heart imaging for anatomical assessment. Our aim is to concatenate a stack 2D free-breathing real-time cines and use Deep Learning (DL) to create an isotropic a fully segmented 3D cine dataset from these images. Methods: Four DL models were trained on open-source data that performed: a) Interslice contrast correction; b) Interslice respiratory motion correction; c) Super-resolution (slice direction); and d) Segmentation of right and left atria and ventricles (RA, LA, RV, and LV), thoracic aorta (Ao) and pulmonary arteries (PA). In 10 patients undergoing routine cardiovascular examination, our method was validated on prospectively acquired sagittal stacks of real-time cine images. Quantitative metrics (ventricular volumes and vessel diameters) and image quality of the 3D cines were compared to conventional breath hold cine and whole heart imaging. Results: All real-time data were successfully transformed into 3D cines with a total post-processing time of <1 min in all cases. There were no significant biases in any LV or RV metrics with reasonable limits of agreement and correlation. There is also reasonable agreement for all vessel diameters, although there was a small but significant overestimation of RPA diameter. Conclusion: We have demonstrated the potential of creating a 3D-cine data from concatenated 2D real-time cine images using a series of DL models. Our method has short acquisition and reconstruction times with fully segmented data being available within 2 minutes. The good agreement with conventional imaging suggests that our method could help to significantly speed up CMR in clinical practice.

Tina Yao, Endrit Pajaziti, Michael Quail et al.

Computational fluid dynamics (CFD) can be used for evaluation of hemodynamics. However, its routine use is limited by labor-intensive manual segmentation, CFD mesh creation, and time-consuming simulation. This study aims to train a deep learning model to both generate patient-specific volume-meshes of the pulmonary artery from 3D cardiac MRI data and directly estimate CFD flow fields. This study used 135 3D cardiac MRIs from both a public and private dataset. The pulmonary arteries in the MRIs were manually segmented and converted into volume-meshes. CFD simulations were performed on ground truth meshes and interpolated onto point-point correspondent meshes to create the ground truth dataset. The dataset was split 85/10/15 for training, validation and testing. Image2Flow, a hybrid image and graph convolutional neural network, was trained to transform a pulmonary artery template to patient-specific anatomy and CFD values. Image2Flow was evaluated in terms of segmentation and accuracy of CFD predicted was assessed using node-wise comparisons. Centerline comparisons of Image2Flow and CFD simulations performed using machine learning segmentation were also performed. Image2Flow achieved excellent segmentation accuracy with a median Dice score of 0.9 (IQR: 0.86-0.92). The median node-wise normalized absolute error for pressure and velocity magnitude was 11.98% (IQR: 9.44-17.90%) and 8.06% (IQR: 7.54-10.41), respectively. Centerline analysis showed no significant difference between the Image2Flow and conventional CFD simulated on machine learning-generated volume-meshes. This proof-of-concept study has shown it is possible to simultaneously perform patient specific volume-mesh based segmentation and pressure and flow field estimation. Image2Flow completes segmentation and CFD in ~205ms, which ~7000 times faster than manual methods, making it more feasible in a clinical environment.

Tina Yao, Nicole St. Clair, Madeline Gong et al.

We present a deep learning framework with two models for automated segmentation and large-scale flow phenotyping in a registry of single-ventricle patients. MultiFlowSeg simultaneously classifies and segments five key vessels, left and right pulmonary arteries, aorta, superior vena cava, and inferior vena cava, from velocity encoded phase-contrast magnetic resonance (PCMR) data. Trained on 260 CMR exams (5 PCMR scans per exam), it achieved an average Dice score of 0.91 on 50 unseen test cases. The method was then integrated into an automated pipeline where it processed over 5,500 registry exams without human assistance, in exams with all 5 vessels it achieved 98% classification and 90% segmentation accuracy. Flow curves from successful segmentations were used to train MultiFlowDTC, which applied deep temporal clustering to identify distinct flow phenotypes. Survival analysis revealed distinct phenotypes were significantly associated with increased risk of death/transplantation and liver disease, demonstrating the potential of the framework.

Anirudh Raman, Olivier Jaubert, Mark Wrobel et al.

Purpose: To investigate whether synthetically generated fractal data can be used to train deep learning (DL) models for dynamic MRI reconstruction, thereby avoiding the privacy, licensing, and availability limitations associated with cardiac MR training datasets. Methods: A training dataset was generated using quaternion Julia fractals to produce 2D+time images. Multi-coil MRI acquisition was simulated to generate paired fully sampled and radially undersampled k-space data. A 3D UNet deep artefact suppression model was trained using these fractal data (F-DL) and compared with an identical model trained on cardiac MRI data (CMR-DL). Both models were evaluated on prospectively acquired radial real-time cardiac MRI from 10 patients. Reconstructions were compared against compressed sensing(CS) and low-rank deep image prior (LR-DIP). All reconstrctuions were ranked for image quality, while ventricular volumes and ejection fraction were compared with reference breath-hold cine MRI. Results: There was no significant difference in qualitative ranking between F-DL and CMR-DL (p=0.9), while both outperformed CS and LR-DIP (p<0.001). Ventricular volumes and function derived from F-DL were similar to CMR-DL, showing no significant bias and accptable limits of agreement compared to reference cine imaging. However, LR-DIP had a signifcant bias (p=0.016) and wider lmits of agreement. Conclusion: DL models trained using synthetic fractal data can reconstruct real-time cardiac MRI with image quality and clinical measurements comparable to models trained on true cardiac MRI data. Fractal training data provide an open, scalable alternative to clinical datasets and may enable development of more generalisable DL reconstruction models for dynamic MRI.

Javier Montalt-Tordera, Vivek Muthurangu, Andreas Hauptmann et al.

Magnetic Resonance Imaging (MRI) plays a vital role in diagnosis, management and monitoring of many diseases. However, it is an inherently slow imaging technique. Over the last 20 years, parallel imaging, temporal encoding and compressed sensing have enabled substantial speed-ups in the acquisition of MRI data, by accurately recovering missing lines of k-space data. However, clinical uptake of vastly accelerated acquisitions has been limited, in particular in compressed sensing, due to the time-consuming nature of the reconstructions and unnatural looking images. Following the success of machine learning in a wide range of imaging tasks, there has been a recent explosion in the use of machine learning in the field of MRI image reconstruction. A wide range of approaches have been proposed, which can be applied in k-space and/or image-space. Promising results have been demonstrated from a range of methods, enabling natural looking images and rapid computation. In this review article we summarize the current machine learning approaches used in MRI reconstruction, discuss their drawbacks, clinical applications, and current trends.

Jennifer A. Steeden, Michael Quail, Alexander Gotschy et al.

Background: Three-dimensional, whole heart, balanced steady state free precession (WH-bSSFP) sequences provide delineation of intra-cardiac and vascular anatomy. However, they have long acquisition times. Here, we propose significant speed ups using a deep learning single volume super resolution reconstruction, to recover high resolution features from rapidly acquired low resolution WH-bSSFP images. Methods: A 3D residual U-Net was trained using synthetic data, created from a library of high-resolution WH-bSSFP images by simulating 0.5 slice resolution and 0.5 phase resolution. The trained network was validated with synthetic test data, as well as prospective low-resolution data. Results: Synthetic low-resolution data had significantly better image quality after super-resolution reconstruction. Qualitative image scores showed super-resolved images had better edge sharpness, fewer residual artefacts and less image distortion than low-resolution images, with similar scores to high-resolution data. Quantitative image scores showed super-resolved images had significantly better edge sharpness than low-resolution or high-resolution images, with significantly better signal-to-noise ratio than high-resolution data. Vessel diameters measurements showed over-estimation in the low-resolution measurements, compared to the high-resolution data. No significant differences and no bias was found in the super-resolution measurements. Conclusion: This paper demonstrates the potential of using a residual U-Net for super-resolution reconstruction of rapidly acquired low-resolution whole heart bSSFP data within a clinical setting. The resulting network can be applied very quickly, making these techniques particularly appealing within busy clinical workflow. Thus, we believe that this technique may help speed up whole heart CMR in clinical practice.

Andreas Hauptmann, Simon Arridge, Felix Lucka et al.

PURPOSE: Real-time assessment of ventricular volumes requires high acceleration factors. Residual convolutional neural networks (CNN) have shown potential for removing artifacts caused by data undersampling. In this study we investigated the effect of different radial sampling patterns on the accuracy of a CNN. We also acquired actual real-time undersampled radial data in patients with congenital heart disease (CHD), and compare CNN reconstruction to Compressed Sensing (CS). METHODS: A 3D (2D plus time) CNN architecture was developed, and trained using 2276 gold-standard paired 3D data sets, with 14x radial undersampling. Four sampling schemes were tested, using 169 previously unseen 3D 'synthetic' test data sets. Actual real-time tiny Golden Angle (tGA) radial SSFP data was acquired in 10 new patients (122 3D data sets), and reconstructed using the 3D CNN as well as a CS algorithm; GRASP. RESULTS: Sampling pattern was shown to be important for image quality, and accurate visualisation of cardiac structures. For actual real-time data, overall reconstruction time with CNN (including creation of aliased images) was shown to be more than 5x faster than GRASP. Additionally, CNN image quality and accuracy of biventricular volumes was observed to be superior to GRASP for the same raw data. CONCLUSION: This paper has demonstrated the potential for the use of a 3D CNN for deep de-aliasing of real-time radial data, within the clinical setting. Clinical measures of ventricular volumes using real-time data with CNN reconstruction are not statistically significantly different from the gold-standard, cardiac gated, BH techniques.