Meeting Banner
Abstract #3573

Quality-of-life Worsening Predicted Using Baseline Hyperpolarized 3He MRI Ventilation Texture Features and Machine-Learning

Maksym Sharma1,2, Harkiran K Kooner1,2, Marrissa J McIntosh1,2, David G McCormack3, and Grace Parraga1,2,3,4
1Department of Medical Biophysics, Western University, London, ON, Canada, 2Robarts Research Institute, Western University, London, ON, Canada, 3Division of Respirology, Department of Medicine, Western University, London, ON, Canada, 4School of Biomedical Engineering, Western University, London, ON, Canada


Texture analysis may be used to extract quantitative information from hyperpolarized 3He MR ventilation images to help explain clinically-relevant outcomes and disease progression. We aimed to combine texture analysis with machine-learning to generate classification models for predicting worsening quality-of-life in ex-smokers with and without COPD. We identified six texture feature contributors, which outperformed standard imaging and clinical variables, with the top machine-learning model achieving a classification accuracy of 80.2% at predicting worsening quality-of-life within 2-3 years. These pilot results suggest that 3He MRI texture features may provide additional prognostic information to predict clinically-relevant changes in quality-of-life in ex-smokers.

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

Join Here