Log in to MyKarger to check if you already have access to this content.

Buy FullText & PDF Unlimited re-access via MyKarger Unrestricted printing, no saving restrictions for personal use read more

CHF 38.00 *
EUR 35.00 *
USD 39.00 *

Select

KAB

Buy a Karger Article Bundle (KAB) and profit from a discount!

If you would like to redeem your KAB credit, please log in.

Save over 20% compared to the individual article price.

Learn more

Rent via DeepDyve Unlimited fulltext viewing of this article Organize, annotate and mark up articles Printing and downloading restrictions apply

Start free trial

Subscribe Access to all articles of the subscribed year(s) guaranteed for 5 years Unlimited re-access via Subscriber Login or MyKarger Unrestricted printing, no saving restrictions for personal use read more

Subcription rates

Select

* The final prices may differ from the prices shown due to specifics of VAT rules.

Article / Publication Details

First-Page Preview

Received: July 20, 2022
Accepted: December 31, 2022
Published online: January 19, 2023

Number of Print Pages: 10
Number of Figures: 5
Number of Tables: 4

ISSN: 0025-7931 (Print)
eISSN: 1423-0356 (Online)

For additional information: https://www.karger.com/RES

Abstract

Background: Manual measurement of endobronchial optical coherence tomography (EB-OCT) images means a heavy workload in the clinical practice, which can also introduce bias if the subjective opinions of doctors are involved. Objective: We aim to develop a convolutional neural network (CNN)-based EB-OCT image analysis algorithm to automatically identify and measure EB-OCT parameters of airway morphology. Methods: The ResUNet, MultiResUNet, and Siamese network were used for analyzing airway inner area (Ai), airway wall area (Aw), airway wall area percentage (Aw%), and airway bifurcate segmentation obtained from EB-OCT imaging, respectively. The accuracy of the automatic segmentations was verified by comparing with manual measurements. Results: Thirty-three patients who were diagnosed with asthma (n = 13), chronic obstructive pulmonary disease (COPD, n = 13), and normal airway (n = 7) were enrolled. EB-OCT was performed in RB9 segment (lateral basal segment of the right lower lobe), and a total of 17,820 OCT images were collected for CNN training, validation, and testing. After training, the Ai, Aw, and airway bifurcate were readily identified in both normal airway and airways of asthma and COPD. The ResUNet and the MultiResUNet resulted in a mean dice similarity coefficient of 0.97 and 0.95 for Ai and Aw segmentation. The accuracy Siamese network in identifying airway bifurcate was 96.6%. Bland-Altman analysis indicated there was a negligible bias between manual and CNN measurements for Ai (bias = −0.02 to 0.01, 95% CI = −0.12 to 0.14) and Aw% (bias = −0.06 to 0.12, 95% CI = −1.98 to 2.14). Conclusion: EB-OCT imaging in conjunction with ResUNet, MultiResUNet, and Siamese network could automatically measure normal and diseased airway structure with an accurate performance.

© 2023 S. Karger AG, Basel

References Saglani S, Lloyd CM. Novel concepts in airway inflammation and remodelling in asthma. Eur Respir J. 2015;46(6):1796–804. Coxson HO, Quiney B, Sin DD, Xing L, McWilliams AM, Mayo JR, et al. Airway wall thickness assessed using computed tomography and optical coherence tomography. Am J Respir Crit Care Med. 2008;177(11):1201–6. Chen Y, Ding M, Guan WJ, Wang W, Luo WZ, Zhong CH, et al. Validation of human small airway measurements using endobronchial optical coherence tomography. Respir Med. 2015;109(11):1446–53. Ding M, Chen Y, Guan WJ, Zhong CH, Jiang M, Luo WZ, et al. Measuring airway remodeling in patients with different COPD staging using endobronchial optical coherence tomography. Chest. 2016;150(6):1281–90. Su ZQ, Zhou ZQ, Guan WJ, Fan MY, Rao WY, Chen Y, et al. Airway remodeling and bronchodilator responses in asthma assessed by endobronchial optical coherence tomography. Allergy. 2022;77(2):646–9. Wang Y, Zhang Y, Yao Z, Zhao R, Zhou F. Machine learning based detection of age-related macular degeneration (AMD) and diabetic macular edema (DME) from optical coherence tomography (OCT) images. Biomed Opt Express. 2016;7(12):4928–40. Devalla SK, Subramanian G, Pham TH, Wang X, Perera S, Tun TA, et al. A deep learning approach to denoise optical coherence tomography images of the optic nerve head. Sci Rep. 2019;9(1):14454. Luo Y, Wang X, Yu X, Jin R, Liu L. Imaging sebaceous gland using optical coherence tomography with deep learning assisted automatic identification. J Biophotonics. 2021;14(6):e202100015. Roman-Rodriguez M, Kaplan A. GOLD 2021 strategy report: implications for asthma-COPD overlap. Int J Chron Obstruct Pulmon Dis. 2021;16:1709–15. Reddel HK, Bacharier LB, Bateman ED, Brightling CE, Brusselle GG, Buhl R, et al. Global initiative for asthma strategy 2021: executive summary and rationale for key changes. Am J Respir Crit Care Med. 2022;205(1):17–35. Fujii K, Kawakami R, Hirota S. Histopathological validation of optical coherence tomography findings of the coronary arteries. J Cardiol. 2018;72(3):179–85. Kirby M, Ohtani K, Nickens T, Lisbona RML, Lee AMD, Shaipanich T, et al. Reproducibility of optical coherence tomography airway imaging. Biomed Opt Express. 2015;6(11):4365–77. Su ZQ, Guan WJ, Li SY, Feng JX, Zhou ZQ, Chen Y, et al. Evaluation of the normal airway morphology using optical coherence tomography. Chest. 2019;156(5):915–25. Eelbode T, Bertels J, Berman M, Vandermeulen D, Maes F, Bisschops R, et al. Optimization for medical image segmentation: theory and practice when evaluating with dice score or jaccard index. IEEE Trans Med Imaging. 2020;39(11):3679–90. Cortiñas-Lorenzo B, Pérez-González F. Adam and the ants: on the influence of the optimization algorithm on the detectability of DNN watermarks. Entropy. 2020;22 Gao W, Ma Z, Gan W, Liu S. Dimensionality reduction of SPD data based on riemannian manifold tangent spaces and isometry. Entropy. 2021;23(9):1117. Ibtehaz N, Rahman MS. MultiResUNet : rethinking the U-Net architecture for multimodal biomedical image segmentation. Neural Netw. 2020;121:74–87. Kuo TC, Cheng TW, Lin CK, Chang MC, Cheng KY, Cheng YC. Using DeepLab v3+: based semantic segmentation to evaluate platelet activation. Med Biol Eng Comput. 2022;60(6):1775–85. Huang Z, Chen Z, Chen J, Lu P, Quan G, Du Y, et al. DaNet: dose-aware network embedded with dose-level estimation for low-dose CT imaging. Phys Med Biol. 2021;66(1):015005. Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. Cham: Springer International Publishing; 2015. p. 234–41. Shaukat Z, Farooq QUA, Tu S, Xiao C, Ali S. A state-of-the-art technique to perform cloud-based semantic segmentation using deep learning 3D U-Net architecture. BMC Bioinformatics. 2022;23(1):251. Yang T, Song J, Li L, Tang Q. Improving brain tumor segmentation on MRI based on the deep U-net and residual units. J Xray Sci Technol. 2020;28(1):95–110. Cheng YK, Lin CL, Huang YC, Chen JC, Lan TP, Lian ZY, et al. Automatic segmentation of specific intervertebral discs through a two-stage MultiResUNet model. J Clin Med. 2021;10(20):4760. Chicco D. Siamese neural networks: an overview. Methods Mol Biol. 2021;2190:73–94. Article / Publication Details

First-Page Preview

Received: July 20, 2022
Accepted: December 31, 2022
Published online: January 19, 2023

Number of Print Pages: 10
Number of Figures: 5
Number of Tables: 4

ISSN: 0025-7931 (Print)
eISSN: 1423-0356 (Online)

For additional information: https://www.karger.com/RES