Automatic segmentation of the great arteries for computational hemodynamic assessment

Abstract

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.

HyperSLICE: HyperBand optimized spiral for low‐latency interactive cardiac examination

“…The optimized spiral raw data were also retrospectively reconstructed using (1) a simple gridded reconstruction (the equivalent to the input to the network); (2) navigator‐less spiral SToRM, 27 which is a state‐of‐the‐art compressed‐sensing reconstruction; and (3) spiral VarNet 28 reconstruction, which is an unrolled ML network architecture including data consistency. The gridded, SToRM, and VarNet reconstructions were performed offline using open‐source codes 27–29 . VarNet was retrained on the same data set and same optimized trajectory as the proposed HyperSLICE network.…”

“…The gridded, SToRM, and VarNet reconstructions were performed offline using open-source codes. [27][28][29] VarNet was retrained on the same data set and same optimized trajectory as the proposed HyperSLICE network. The Cartesian data sets used for comparison were reconstructed on the scanner platform using the scanner software reconstructions (including GRAPPA).…”

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

“…Specifically, each of the 35 coefficients in a synthetic vector was generated by randomly sampling a Gaussian distribution (within 2 standard deviations) based on the distribution of weights in the US matrix. Following concatenation of all the lower dimensional deformation vectors, the matrix X [3000,35] was transformed into a matrix L [3000, 516] by matrix multiplication (L = XSV T ), thus reversing PCA and mapping the matrix X onto the original axes. Standardisation was then reversed in all columns of L using the previously computed standard deviations and means in the M matrix.…”

“…It has been seen in previous studies that aortic CFD flow fields are highly sensitive to geometric and topological variation [35,36]. For this reason, using shape vectors that are accurate PLOS COMPUTATIONAL BIOLOGY descriptors of the aortic surfaces is of critical importance.…”

2D sodium MRI of the human calf using half‐sinc excitation pulses and compressed sensing

“…Conventional reconstruction for 2D and 3D acquisitions consisted of nonuniform fast Fourier transform (NUFFT) with density compensation. 23,24 In vivo 2D half-sinc data with retrospectively reduced NSAs was also reconstructed using CS by solving the following minimization problem 25 :…”