Abstract #0391

Deep learning-based thoracic cavity segmentation for hyperpolarized 129Xe MRI

Suphachart Leewiwatwong¹, Junlan Lu², David Mummy³, Isabelle Dummer^3,4, Kevin Yarnall⁵, Ziyi Wang¹, and Bastiaan Driehuys^1,2,3

¹Biomedical Engineering, Duke University, Durham, NC, United States, ²Medical Physics, Duke University, Durham, NC, United States, ³Radiology, Duke University, Durham, NC, United States, ⁴Bioengineering, McGill University, Montréal, QC, Canada, ⁵Mechanical Engineering and Materials Science, Duke University, Durham, NC, United States

Quantifying hyperpolarized ¹²⁹Xe MRI of pulmonary ventilation and gas exchange requires accurate segmentation of the thoracic cavity. This is typically done either manually or semi-automatically using an additional proton scan volume-matched to the gas image. These methods are prone to operator subjectivity, image artifacts, alignment/registration issues, and SNR. Here we demonstrate using a 3D convolutional neural network (CNN) to automatically and directly delineate the thoracic cavity from ¹²⁹Xe MRI alone. This 3D-CNN uses a combination of Dice-Focal, perceptual loss, and training with template-based data augmentation to demonstrate thoracic cavity segmentation with a Dice score of 0.955 vs. expert readers.

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

Join Here