Publication date: Jan 01, 2025

Pulmonary gas exchange is assessed by the transfer factor of the lungs (T ) for carbon monoxide (T ), and can also be measured with inhaled xenon-129 (Xe) magnetic resonance imaging (MRI). A model has been proposed to estimate T from Xe MRI metrics, but this approach has not been fully validated and does not utilise the spatial information provided by three-dimensional Xe MRI. Three models for predicting T from Xe MRI metrics were compared: 1) a previously-published physiology-based model, 2) multivariable linear regression and 3) random forest regression. Models were trained on data from 150 patients with asthma and/or COPD. The random forest model was applied voxel-wise to Xe images to yield regional T maps. Coefficients of the physiological model were found to differ from previously reported values. All models had good prediction accuracy with small mean absolute error (MAE): 1) 1. 24+/-0. 15 mmol.min.kPa, 2) 1. 01+/-0. 06 mmol.min.kPa, 3) 0. 995+/-0. 129 mmol.min.kPa. The random forest model performed well when applied to a validation group of post-COVID-19 patients and healthy volunteers (MAE=0. 840 mmol.min.kPa), suggesting good generalisability. The feasibility of producing regional maps of predicted T was demonstrated and the whole-lung sum of the T maps agreed with measured T (MAE=1. 18 mmol.min.kPa). The best prediction of T from Xe MRI metrics was with a random forest regression framework. Applying this model on a voxel-wise level to create parametric T maps provides a useful tool for regional visualisation and clinical interpretation of Xe gas exchange MRI.

Open Access PDF

Semantics

Original Article