A framework for modelling whole-lung and regional TLCOusing hyperpolarised¹²⁹Xe lung MRI

Pulmonary gas exchange is assessed by the transfer factor of the lungs (T L) for carbon monoxide (T LCO), and can also be measured with inhaled xenon-129 (129Xe) magnetic resonance imaging (MRI). A model has been proposed to estimate T L from 129Xe MRI metrics, but this approach has not been fully validated and does not utilise the spatial information provided by three-dimensional 129Xe MRI. Three models for predicting T L from 129Xe 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 129Xe images to yield regional T L 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-1·kPa-1, 2) 1.01±0.06 mmol·min-1·kPa-1, 3) 0.995±0.129 mmol·min-1·kPa-1. 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-1·kPa-1), suggesting good generalisability. The feasibility of producing regional maps of predicted T L was demonstrated and the whole-lung sum of the T L maps agreed with measured T LCO (MAE=1.18 mmol·min-1·kPa-1). The best prediction of T LCO from 129Xe MRI metrics was with a random forest regression framework. Applying this model on a voxel-wise level to create parametric T L maps provides a useful tool for regional visualisation and clinical interpretation of 129Xe gas exchange MRI.