Background
Ultrashort echo time (UTE) proton MRI has gained popularity for assessing lung structure and function in pulmonary imaging; however, the development of rapid biomarker extraction and regional quantification has lagged behind due to laborâintensive lung segmentation.
Purpose
To evaluate a deep learning (DL) approach for automated lung segmentation to extract imageâbased biomarkers from functional lung imaging using 3D radial UTE oxygenâenhanced (OE) MRI.
Study Type
Retrospective study aimed to evaluate a technical development.
Population
Fortyâfive human subjects, including 16 healthy volunteers, 5 asthma, and 24 patients with cystic fibrosis.
Field Strength/Sequence
1.5T MRI, 3D radial UTE (TE = 0.08 msec) sequence.
Assessment
Two 3D radial UTE volumes were acquired sequentially under normoxic (21% O2) and hyperoxic (100% O2) conditions. Automated segmentation of the lungs using 2D convolutional encoderâdecoder based DL method, and the subsequent functional quantification via adaptive Kâmeans were compared with the results obtained from the reference method, supervised region growing.
Statistical Tests
Relative to the reference method, the performance of DL on volumetric quantification was assessed using Dice coefficient with 95% confidence interval (CI) for accuracy, twoâsided Wilcoxon signedârank test for computation time, and BlandâAltman analysis on the functional measure derived from the OE images.
Results
The DL method produced strong agreement with supervised region growing for the right (Dice: 0.97; 95% CI = [0.96, 0.97]; P < 0.001) and left lungs (Dice: 0.96; 95% CI = [0.96, 0.97]; P < 0.001). The DL method averaged 46 seconds to generate the automatic segmentations in contrast to 1.93 hours using the reference method (P < 0.001). BlandâAltman analysis showed nonsignificant intermethod differences of volumetric (P â„ 0.12) and functional measurements (P â„ 0.34) in the left and right lungs.
Data Conclusion
DL provides rapid, automated, and robust lung segmentation for quantification of regional lung function using UTE proton MRI.
Level of Evidence: 2
Technical Efficacy: Stage 1
J. Magn. Reson. Imaging 2019;50:1169â1181.