Meeting Banner
Abstract #0450

Fully-automated 1H MRI Thoracic Cavity Segmentation for Hyperpolarized Gas Imaging using a Convolutional Neural Network

Alexander M Matheson1, Rachel L Eddy1, Jonathan L MacNeil2, Marrissa L McIntosh1, and Grace Parraga1,2
1Medical Biophysics, Robarts Research Institute, Western University, London, ON, Canada, 2School of Biomedical Engineering, Robarts Research Institute, Western University, London, ON, Canada

Thoracic segmentations are crucial for accurate measurements of normalized lung ventilation, perfusion and gas exchange. Current semi-automated methods are time consuming, require experienced readers, and lack the standardization of fully-automated methods, such as convolutional neural networks. We retrospectively pooled data from 449 healthy and respiratory disease participants, resulting in a 55,000 slice augmented data set to train a dense v-net neural network. The network produced segmentations qualitatively matching semi-automated methods, with high Dice scores and an area under the receiver operating characteristic curve of 0.997. Implementation on the NiftyNet platform permits quick model dissemination for multi-site validation.

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

Join Here