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

• Published in: PLoS computational biology Vol. 20; no. 6; p. e1012231
• Main Authors: Yao, Tina, Pajaziti, Endrit, Quail, Michael, Schievano, Silvia, Steeden, Jennifer, Muthurangu, Vivek
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 20.06.2024; Public Library of Science (PLoS)
• Subjects: Accuracy; Artificial neural networks; Biology and Life Sciences; Computational fluid dynamics; Congenital diseases; CT imaging; Datasets; Deep learning; Feasibility studies; Fluid dynamics; Fluid flow; Graph neural networks; Health aspects; Heart; Hemodynamics; Hydrodynamics; Image processing; Image segmentation; Magnetic resonance imaging; Medicine and Health Sciences; Neural networks; Noninvasive evaluation; Physical Sciences; Pulmonary artery; Research and Analysis Methods; Segmentation; Specific volume; Technology application; Three dimensional flow; Veins & arteries; Velocity; United Kingdom; United Kingdom > UK
• ISSN: 1553-7358; 1553-734X; 1553-7358
• DOI: 10.1371/journal.pcbi.1012231

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.