A framework for modelling whole-lung and regional TL_CO using hyperpolarised ¹²⁹Xe lung MRI

Background Pulmonary gas exchange is assessed by the transfer factor of the lungs (TL) for carbon monoxide (TL_CO), and can also be measured with inhaled xenon-129 (¹²⁹Xe) MRI. A model has been proposed to estimate TL from ¹²⁹Xe MRI metrics, but this approach has not been fully validated and does not utilise the spatial information provided by 3D ¹²⁹Xe MRI.

Methods Three models for predicting TL 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 chronic obstructive pulmonary disease. The random forest model was applied voxel-wise to ¹²⁹Xe images to yield regional TL maps.

Results 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 TL was demonstrated and the whole-lung sum of the TL maps agreed with measured TL_CO (MAE=1.18 mmol·min⁻¹·kPa⁻¹).

Conclusion The best prediction of TL_CO from ¹²⁹Xe MRI metrics was with a random forest regression framework. Applying this model on a voxel-wise level to create parametric TL maps provides a useful tool for regional visualisation and clinical interpretation of ¹²⁹Xe gas exchange MRI.