Abstract #1962

Deep Spatiotemporal Phase Unwrapping of Phase-Contrast MRI Data

Jiacheng Jason He¹, Christopher Sandino¹, David Zeng¹, Shreyas Vasanawala^1,2, and Joseph Cheng²

¹Electrical Engineering, Stanford University, Stanford, CA, United States, ²Radiology, Stanford University, Stanford, CA, United States

This work demonstrates the advantage temporal information provides for deep phase unwrapping of phase-contrast MRI data. Using a patch-based, three-dimensional ResNet architecture, our model performs better than state-of-the-art single-step algorithms. Our deep spatiotemporal phase unwrapping model continues the quest to lower V_enc values to increase dynamic range and velocity-to-noise ratio (VNR) of 4D flow data by providing a robust method for phase unwrapping.

This abstract and the presentation materials are available to members only; a login is required.

Join Here