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

doi:10.1371/journal.pcbi.1012231

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

Fig 4

(A) MNAE_S values of the Image2Flow predictions compared to the ground truth on the test set (n = 15) for pressure and velocity. (B) Difference in MNAE_S values between CFD_I2F and CFD_DL-seg.

doi: https://doi.org/10.1371/journal.pcbi.1012231.g004