Physics-Informed Neural Networks for Brain Hemodynamic Predictions Using Medical Imaging

• Published in: IEEE transactions on medical imaging Vol. 41; no. 9; pp. 2285 - 2303
• Main Authors: Sarabian, Mohammad, Babaee, Hessam, Laksari, Kaveh
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 4D flow MRI; Accuracy; Angiography; Arteries; Blood; Blood flow; Blood vessels; Boundary conditions; Brain; brain hemodynamics; Brain mapping; Brain modeling; Cerebrovascular diseases; Computational modeling; Computational neuroscience; Deep learning; Deep neural networks; Diameters; Doppler effect; Flow velocity; Hemodynamics; Image acquisition; Image resolution; Magnetic resonance imaging; Medical imaging; Neural networks; Neuroimaging; Physics; Reduced order models; Stenosis; transcranial Doppler ultrasound; Ultrasound; Vascular diseases; Vasoconstriction; Velocity; Velocity measurement; Workflow

Determining brain hemodynamics plays a critical role in the diagnosis and treatment of various cerebrovascular diseases. In this work, we put forth a physics-informed deep learning framework that augments sparse clinical measurements with one-dimensional (1D) reduced-order model (ROM) simulations to...