Meeting Banner
Abstract #0776

Fully Automated Multivendor and Multisite Artificial Intelligence-based 3D Segmentation of the Proximal Arteries from 4D flow MRI

Haben Berhane1, Michael Scott2, Takashi Fujiwara3, Lorna Browne3, Joshua Robinson1, Cynthia Rigsby1, Michael Markl2, and Alex Barker3
1Lurie Children's Hospital of Chicago, Chicago, IL, United States, 2Northwestern University, Chicago, IL, United States, 3University of Colorado, Anschutz Medical Campus, Aurora, CO, United States

We trained and validated a multi-label convolutional neural network for the segmentation of the aorta and pulmonary arteries from 4D flow MRI for rapid flow analysis across multiple vendors and centers. Using 67 whole-heart 4D flow MRI scans, including 29 with cardiac pathologies, across two institutions and vendors, we trained and tested our CNN using 10-fold cross validation. For flow analysis, We calculated net flow, peak velocity, and Qp-Qs. Across all flow metrics, we found that automated segmentations showed moderate to strong agreement with the manual segmentations, while taking a fraction of the time.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here