Meeting Banner
Abstract #1728

A Real-Time Centralized Pipeline for Reconstructing and Quantifying Hyperpolarized 129Xe Gas Exchange MRI

Ziyi Wang1, Mu He2, Alexander Culbert1, John Nouls3, Elianna A Bier1, and Bastiaan Driehuys1,3

1Biomedical Engineering, Duke University, Durham, NC, United States, 2Electrical and Computer Engineering, Duke University, Durham, NC, United States, 3Radiology, Duke University Medical Center, Durham, NC, United States

Hyperpolarized 129Xe MRI is emerging as a powerful means to provide 3D quantitative mapping of ventilation, interstitial barrier uptake, and red blood cell transfer. However, this capability requires non-standard radial reconstruction and accurate lung segmentation to enable quantitative analysis. Such reconstruction and image processing would ideally be standardized and centralized to facilitate using 129Xe gas exchange MRI in multi-center clinical trials. To this end, we developed a neural-network based lung segmentation approach that automatically generates accurate masks. With this capability, we demonstrate a fully centralized processing pipeline for real-time reconstruction and quantitative reporting of 129Xe gas exchange MRI.

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

Join Here