Journal article
Deep convolutional neural networks with multiplane consensus labeling for lung function quantification using UTE proton MRI
Journal of magnetic resonance imaging, Vol.50(4), pp.1169-1181
10/2019
DOI: 10.1002/jmri.26734
PMCID: PMC7039686
PMID: 30945385
Abstract
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 labor‐intensive lung segmentation.
Purpose
To evaluate a deep learning (DL) approach for automated lung segmentation to extract image‐based biomarkers from functional lung imaging using 3D radial UTE oxygen‐enhanced (OE) MRI.
Study Type
Retrospective study aimed to evaluate a technical development.
Population
Forty‐five 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 encoder‐decoder based DL method, and the subsequent functional quantification via adaptive K‐means 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, two‐sided Wilcoxon signed‐rank test for computation time, and Bland–Altman 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). Bland–Altman analysis showed nonsignificant intermethod differences of volumetric (P ≥ 0.12) and functional measurements (P ≥ 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;50:1169–1181.
Details
- Title: Subtitle
- Deep convolutional neural networks with multiplane consensus labeling for lung function quantification using UTE proton MRI
- Creators
- Wei Zha - University of Wisconsin–MadisonSean B. Fain - University of Wisconsin–MadisonMark L. Schiebler - University of Wisconsin–MadisonMichael D. Evans - University of MinnesotaScott K. Nagle - University of Wisconsin–MadisonFang Liu - University of Wisconsin–Madison
- Resource Type
- Journal article
- Publication Details
- Journal of magnetic resonance imaging, Vol.50(4), pp.1169-1181
- DOI
- 10.1002/jmri.26734
- PMID
- 30945385
- PMCID
- PMC7039686
- NLM abbreviation
- J Magn Reson Imaging
- ISSN
- 1053-1807
- eISSN
- 1522-2586
- Publisher
- John Wiley & Sons, Inc
- Number of pages
- 13
- Grant note
- National Heart, Lung, and Blood Institute (R01 HL126771; U10 HL109168) National Center for Advancing Translational Sciences (UL1TR002373) National Institutes of Health (S10 OD016394) National Institute of Arthritis and Musculoskeletal and Skin Diseases (R01 AR068373‐01)
- Language
- English
- Date published
- 10/2019
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Health, Sport, and Human Physiology
- Record Identifier
- 9984275056102771
Metrics
30 Record Views