Meeting Banner
Abstract #1187

Respiratory System Resistance Explained using Hyperpolarized 129Xe MRI Texture Features and Machine Learning

Marrissa J McIntosh1,2, Maksym Sharma1,2, Alexander M Matheson1,2, Harkiran K Kooner1,2, Rachel L Eddy3, Christopher Licskai4, David G McCormack4, Michael Nicholson4, Cory Yamashita4, and Grace Parraga1,2,4,5
1Department of Medical Biophysics, Western University, London, ON, Canada, 2Robarts Research Institute, London, ON, Canada, 3Centre for Heart Lung Innovation, University of British Columbia, Vancouver, BC, Canada, 4Division of Respirology, Department of Medicine, Western University, London, ON, Canada, 5School of Biomedical Engineering, Western University, London, ON, Canada


129Xe MRI ventilation images consist of embedded texture features that may help explain ventilation heterogeneity. We previously showed that 129Xe MRI ventilation features predicted response to biologic therapy in asthma and thus, we postulated that texture features may help explain central and peripheral airways resistance. We employed machine-learning techniques to identify specific 129Xe MRI features that were related to airway resistance. Ventilation texture analysis yielded four unique and two common features that independently explained central and peripheral airways resistance, respectively. These promising results suggest that 129Xe ventilation texture analysis may reveal hidden anatomic-physiologic measurements that lead to ventilation heterogeneity.

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

Join Here