Image2Flow: A proof-of-concept hybrid image and graph convolutional neural network for rapid patient-specific pulmonary artery segmentation and CFD flow field calculation from 3D cardiac MRI data.

Computational fluid dynamics (CFD) can be used for non-invasive 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 proof-of-concept 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 110/10/15 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, taking a specific inlet velocity as an additional input. Image2Flow was evaluated in terms of segmentation, and the accuracy of predicted CFD was assessed using node-wise comparisons. In addition, the ability of Image2Flow to respond to increasing inlet velocities was also evaluated. Image2Flow achieved excellent segmentation accuracy with a median Dice score of 0.91 (IQR: 0.86-0.92). The median node-wise normalized absolute error for pressure and velocity magnitude was 11.75% (IQR: 9.60-15.30%) and 9.90% (IQR: 8.47-11.90), respectively. Image2Flow also showed an expected response to increased inlet velocities with increasing pressure and velocity values. This proof-of-concept study has shown that it is possible to simultaneously perform patient-specific volume-mesh based segmentation and pressure and flow field estimation using Image2Flow. Image2Flow completes segmentation and CFD in ~330ms, which is ~5000 times faster than manual methods, making it more feasible in a clinical environment.

Shape-driven deep neural networks for fast acquisition of aortic 3D pressure and velocity flow fields.

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 reasonable accuracy.

Use of virtual reality in complex double outlet right ventricle cases.

Virtual reality has been incorporated into clinical practice for planning complex congenital cardiac operations at the Great Ormond Street Hospital for Children since 2018 [1]. Virtual reality allows for 3-dimensional exploration of patient-specific models, created through the segmentation of 3-dimensional imaging data sets. Along with 3-dimensional printed models and 3-dimensional PDFs, this technology has enabled a new approach in planning and reviewing surgical interventions. It is particularly important in intracardiac repairs involving ventricular septal defects [2] and double outlet right ventricle cases presenting with various phenotypes of interventricular communication [3,4]. We present the virtual reality environment of two complex cases of double outlet right ventricle, illustrating the potential of virtual reality as a clinical tool to aid anatomical understanding and surgical planning of complex congenital heart disease.

Automatic segmentation of the great arteries for computational hemodynamic assessment.

BACKGROUND: Computational fluid dynamics (CFD) is increasingly used for the assessment of blood flow conditions in patients with congenital heart disease (CHD). This requires patient-specific anatomy, typically obtained from segmented 3D cardiovascular magnetic resonance (CMR) images. However, segmentation is time-consuming and requires expert input. This study aims to develop and validate a machine learning (ML) method for segmentation of the aorta and pulmonary arteries for CFD studies. METHODS: 90 CHD patients were retrospectively selected for this study. 3D CMR images were manually segmented to obtain ground-truth (GT) background, aorta and pulmonary artery labels. These were used to train and optimize a U-Net model, using a 70-10-10 train-validation-test split. Segmentation performance was primarily evaluated using Dice score. CFD simulations were set up from GT and ML segmentations using a semi-automatic meshing and simulation pipeline. Mean pressure and velocity fields across 99 planes along the vessel centrelines were extracted, and a mean average percentage error (MAPE) was calculated for each vessel pair (ML vs GT). A second observer (SO) segmented the test dataset for assessment of inter-observer variability. Friedman tests were used to compare ML vs GT, SO vs GT and ML vs SO metrics, and pressure/velocity field errors. RESULTS: The network's Dice score (ML vs GT) was 0.945 (interquartile range: 0.929-0.955) for the aorta and 0.885 (0.851-0.899) for the pulmonary arteries. Differences with the inter-observer Dice score (SO vs GT) and ML vs SO Dice scores were not statistically significant for either aorta or pulmonary arteries (p = 0.741, p = 0.061). The ML vs GT MAPEs for pressure and velocity in the aorta were 10.1% (8.5-15.7%) and 4.1% (3.1-6.9%), respectively, and for the pulmonary arteries 14.6% (11.5-23.2%) and 6.3% (4.3-7.9%), respectively. Inter-observer (SO vs GT) and ML vs SO pressure and velocity MAPEs were of a similar magnitude to ML vs GT (p > 0.2). CONCLUSIONS: ML can successfully segment the great vessels for CFD, with errors similar to inter-observer variability. This fast, automatic method reduces the time and effort needed for CFD analysis, making it more attractive for routine clinical use.

Enhanced 3D visualization for planning biventricular repair of double outlet right ventricle: a pilot study on the advantages of virtual reality.

Aims: We aim to determine any additional benefit of virtual reality (VR) experience if compared to conventional cross-sectional imaging and standard three-dimensional (3D) modelling when deciding on surgical strategy in patients with complex double outlet right ventricle (DORV). Methods and results: We retrospectively selected 10 consecutive patients with DORV and complex interventricular communications, who underwent biventricular repair. An arterial switch operation (ASO) was part of the repair in three of those. Computed tomography (CT) or cardiac magnetic resonance imaging images were used to reconstruct patient-specific 3D anatomies, which were then presented using different visualization modalities: 3D pdf, 3D printed models, and VR models. Two experienced paediatric cardiac surgeons, blinded to repair performed, reviewed each case evaluating the suitability of repair following assessment of each visualization modalities. In addition, they had to identify those who had ASO as part of the procedure. Answers of the two surgeons were compared to the actual operations performed. There was no mortality during the follow-up (mean = 2.5 years). Two patients required reoperations. After review of CT/cardiac magnetic resonance images, the evaluators identified the surgical strategy in accordance with the actual surgical plan in 75% of the cases. When using 3D pdf this reached only 70%. Accordance improved to 85% after revision of 3D printed models and to 95% after VR. Use of 3D printed models and VR facilitated the identification of patients who required ASO. Conclusion: Virtual reality can enhance understanding of suitability for biventricular repair in patients with complex DORV if compared to cross-sectional images and other 3D modelling techniques.