Skip to main content
Advertisement

< Back to Article

Fig 1.

Segmentation and mesh-preprocessing pipeline.

The aorta segmentation of each subject is re-meshed and smoothed in an automatic pipeline. This is followed by clipping of the inlets/outlets and head & neck vessels.

More »

Fig 1 Expand

Fig 2.

Mesh registration with SSM.

An example aortic shape approximation using our SSM is shown. Individual surface or volumes can be reconstructed using a mean aortic shape and applied deformation field initialised on a set of control points (n = 172).

More »

Fig 2 Expand

Fig 3.

CFD Pipeline.

Surfaces have flow extensions added before volume meshing. The same simulation set-up is applied to the final volume mesh for each synthetic subject.

More »

Fig 3 Expand

Fig 4.

CFD data interpolation.

CFD results are interpolated onto a point-correspondence mesh (generated by the SSM), thus restoring node concordance.

More »

Fig 4 Expand

Fig 5.

DNN general architecture.

The general sequential, fully-connected DNN set-up used to build both pressure and velocity predictors (’CFD vector’ can be either pressure or velocity PCA vectors).

More »

Fig 5 Expand

Fig 6.

CFD gradient extraction method.

Using subject centrelines, 99 plane-averaged pressure or velocity points along the length of the aorta are extracted by sampling the 3D flow fields. The origin is always the aortic root (excluding the extension).

More »

Fig 6 Expand

Fig 7.

Modes of deformation.

Left: first three modes of deformation from the SSM (SD = standard deviation). Right: examples of synthetic post-CoA aortas from the test set (using combinations of all 35 shape modes).

More »

Fig 7 Expand

Table 1.

Comparison of aorta dimensions between original real cohort (n = 67) and synthetic cohort (n = 3000).

More »

Table 1 Expand

Fig 8.

Nodal error analysis.

Left: Distribution of mean nodal errors (MNAEN), computed on the test set (n = 200). Errors are absolute values and are projected on the template aorta. Right: Bland-Altman plots for the overall aorta. Normalised error (%) refers to the NAE of each node in every test case, without taking the absolute value (n = 5,800,000). Only 1,000 randomly selected points were drawn to improve graph readability.

More »

Fig 8 Expand

Fig 9.

Best, median and worst test-set predictions.

Comparisons between ground truth (CFD) and predicted (ML) in the test set (n = 200). Best, median and worst cases for both pressure and velocity-magnitude are shown, ranked using the mean node-to-node error (MNAES). Pressure/velocity gradients are also displayed (black lines = CFD, red = ML).

More »

Fig 9 Expand

Fig 10.

Shape modes vs. ML error.

Scatter plot comparing the shape PCA mode values against subject error (MNAES) in the test set (n = 200). Pearson R coefficients and p-values were computed for each subplot.

More »

Fig 10 Expand

Fig 11.

Testing on prospective data.

Best and worst pressure and velocity predictions on the real patient test cohort (n = 10). FD (SSM) is the error between the predicted (red) and SSM CFD (dashed black) gradients. FD (real) is the error between the predicted (red) and true CFD (solid black) gradients.

More »

Fig 11 Expand