Uncertainty-Aware, End-to-End Deep Learning for Functional Lung MRI Quantification Using ¹²⁹Xe and ¹H MRI

Purpose To develop an automatic end-to-end deep learning pipeline for predicting the ventilation defect percentage (VDP) from coregistered functional hyperpolarized xenon 129 (¹²⁹Xe) MRI and structural proton (¹H) MRI scans without manual intervention. Materials and Methods In this retrospective study (2015-2024), ¹²⁹Xe MRI and ¹H MRI scans from healthy participants and patients with a range of pulmonary diseases were used to predict VDP and its associated prediction confidence via an uncertainty-aware convolutional neural network framework. Monte Carlo dropout was used to quantify model uncertainty. Model robustness was assessed using test-time augmentation to simulate test-retest repeatability. The proposed approach was evaluated on a stratified testing set via the median absolute error. Results The dataset comprised 574 paired ¹²⁹Xe MRI and ¹H MRI scans from 47 healthy participants (mean ± SD age, 28.3 years ± 17.3; 28 female participants) and 527 patients with a range of pulmonary pathologies (mean ± SD age, 44.9 years ± 21.9; 295 female patients). The proposed framework produced a median absolute error of 1.01% (IQR, 0.49-2.47) VDP compared with manually corrected, segmentation-derived VDPs; no evidence of difference was found (P = .70). Twenty Monte Carlo dropout iterations were completed, producing VDP prediction distributions that were subsequently clustered into confidence groupings. The proposed approach demonstrated clinical classification accuracy of 91% (95% CI: 68, 94; 32 of 35). Conclusion An uncertainty-aware, end-to-end deep learning approach enabled accurate prediction of VDP without manual segmentation, with performance comparable to segmentation-based methods and quantification of prediction uncertainty. Keywords: Functional Imaging, Lung, Multi-Modal, MRI, Uncertainty-Aware Supplemental material is available for this article. © RSNA, 2026.