Convolutional Neural Networks with Template-Based Data Augmentation for Functional Lung Image Quantification
- PMID: 30195415
- PMCID: PMC6397788
- DOI: 10.1016/j.acra.2018.08.003
Convolutional Neural Networks with Template-Based Data Augmentation for Functional Lung Image Quantification
Abstract
Rationale and objectives: We propose an automated segmentation pipeline based on deep learning for proton lung MRI segmentation and ventilation-based quantification which improves on our previously reported methodologies in terms of computational efficiency while demonstrating accuracy and robustness. The large data requirement for the proposed framework is made possible by a novel template-based data augmentation strategy. Supporting this work is the open-source ANTsRNet-a growing repository of well-known deep learning architectures first introduced here.
Materials and methods: Deep convolutional neural network (CNN) models were constructed and trained using a custom multilabel Dice metric loss function and a novel template-based data augmentation strategy. Training (including template generation and data augmentation) employed 205 proton MR images and 73 functional lung MRI. Evaluation was performed using data sets of size 63 and 40 images, respectively.
Results: Accuracy for CNN-based proton lung MRI segmentation (in terms of Dice overlap) was left lung: 0.93 ± 0.03, right lung: 0.94 ± 0.02, and whole lung: 0.94 ± 0.02. Although slightly less accurate than our previously reported joint label fusion approach (left lung: 0.95 ± 0.02, right lung: 0.96 ± 0.01, and whole lung: 0.96 ± 0.01), processing time is <1 second per subject for the proposed approach versus ∼30 minutes per subject using joint label fusion. Accuracy for quantifying ventilation defects was determined based on a consensus labeling where average accuracy (Dice multilabel overlap of ventilation defect regions plus normal region) was 0.94 for the CNN method; 0.92 for our previously reported method; and 0.90, 0.92, and 0.94 for expert readers.
Conclusion: The proposed framework yields accurate automated quantification in near real time. CNNs drastically reduce processing time after offline model construction and demonstrate significant future potential for facilitating quantitative analysis of functional lung MRI.
Keywords: ANTsRNet; Advanced Normalization Tools; Hyperpolarized gas imaging; Neural networks; Proton lung MRI; U-net.
Copyright © 2018 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.
Figures
Similar articles
-
Deep Learning Approaches for Quantifying Ventilation Defects in Hyperpolarized Gas Magnetic Resonance Imaging of the Lung: A Review.Bioengineering (Basel). 2023 Nov 23;10(12):1349. doi: 10.3390/bioengineering10121349. Bioengineering (Basel). 2023. PMID: 38135940 Free PMC article. Review.
-
Combining neural networks and image synthesis to enable automatic thoracic cavity segmentation of hyperpolarized 129Xe MRI without proton scans.Magn Reson Imaging. 2023 Nov;103:145-155. doi: 10.1016/j.mri.2023.07.001. Epub 2023 Jul 4. Magn Reson Imaging. 2023. PMID: 37406744
-
Pulmonary Ventilation Maps Generated with Free-breathing Proton MRI and a Deep Convolutional Neural Network.Radiology. 2021 Feb;298(2):427-438. doi: 10.1148/radiol.2020202861. Epub 2020 Dec 8. Radiology. 2021. PMID: 33289613
-
A hybrid model- and deep learning-based framework for functional lung image synthesis from multi-inflation CT and hyperpolarized gas MRI.Med Phys. 2023 Sep;50(9):5657-5670. doi: 10.1002/mp.16369. Epub 2023 Apr 1. Med Phys. 2023. PMID: 36932692 Free PMC article.
-
3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study.Neuroimage. 2018 Apr 15;170:456-470. doi: 10.1016/j.neuroimage.2017.04.039. Epub 2017 Apr 24. Neuroimage. 2018. PMID: 28450139 Review.
Cited by
-
Automatic segmentation of lower limb muscles from MR images of post-menopausal women based on deep learning and data augmentation.PLoS One. 2024 Apr 2;19(4):e0299099. doi: 10.1371/journal.pone.0299099. eCollection 2024. PLoS One. 2024. PMID: 38564618 Free PMC article.
-
Pulmonary MRI with hyperpolarized xenon-129 demonstrates novel alterations in gas transfer across the air-blood barrier in asthma.Med Phys. 2024 Apr;51(4):2413-2423. doi: 10.1002/mp.17009. Epub 2024 Mar 3. Med Phys. 2024. PMID: 38431967
-
Deep Learning Approaches for Quantifying Ventilation Defects in Hyperpolarized Gas Magnetic Resonance Imaging of the Lung: A Review.Bioengineering (Basel). 2023 Nov 23;10(12):1349. doi: 10.3390/bioengineering10121349. Bioengineering (Basel). 2023. PMID: 38135940 Free PMC article. Review.
-
Acquiring Hyperpolarized 129Xe Magnetic Resonance Images of Lung Ventilation.J Vis Exp. 2023 Nov 21;(201):10.3791/65982. doi: 10.3791/65982. J Vis Exp. 2023. PMID: 38078603 Free PMC article.
-
Combining neural networks and image synthesis to enable automatic thoracic cavity segmentation of hyperpolarized 129Xe MRI without proton scans.Magn Reson Imaging. 2023 Nov;103:145-155. doi: 10.1016/j.mri.2023.07.001. Epub 2023 Jul 4. Magn Reson Imaging. 2023. PMID: 37406744
References
Publication types
MeSH terms
Substances
Grants and funding
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical