Utilizing Deep Learning and Computed Tomography to Determine Pulmonary Nodule Activity in Patients With Nontuberculous Mycobacterial-Lung Disease.
Journal
Journal of thoracic imaging
ISSN: 1536-0237
Titre abrégé: J Thorac Imaging
Pays: United States
ID NLM: 8606160
Informations de publication
Date de publication:
01 May 2024
01 May 2024
Historique:
medline:
19
4
2024
pubmed:
19
4
2024
entrez:
19
4
2024
Statut:
ppublish
Résumé
To develop and evaluate a deep convolutional neural network (DCNN) model for the classification of acute and chronic lung nodules from nontuberculous mycobacterial-lung disease (NTM-LD) on computed tomography (CT). We collected a data set of 650 nodules (316 acute and 334 chronic) from the CT scans of 110 patients with NTM-LD. The data set was divided into training, validation, and test sets in a ratio of 4:1:1. Bounding boxes were used to crop the 2D CT images down to the area of interest. A DCNN model was built using 11 convolutional layers and trained on these images. The performance of the model was evaluated on the hold-out test set and compared with that of 3 radiologists who independently reviewed the images. The DCNN model achieved an area under the receiver operating characteristic curve of 0.806 for differentiating acute and chronic NTM-LD nodules, corresponding to sensitivity, specificity, and accuracy of 76%, 68%, and 72%, respectively. The performance of the model was comparable to that of the 3 radiologists, who had area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy of 0.693 to 0.771, 61% to 82%, 59% to 73%, and 60% to 73%, respectively. This study demonstrated the feasibility of using a DCNN model for the classification of the activity of NTM-LD nodules on chest CT. The model performance was comparable to that of radiologists. This approach can potentially and efficiently improve the diagnosis and management of NTM-LD.
Identifiants
pubmed: 38640144
doi: 10.1097/RTI.0000000000000745
pii: 00005382-202405000-00008
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
194-199Informations de copyright
Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
C.T.L. is currently receiving research support from Siemens and Carestream. The remaining authors declare no conflicts of interest.
Références
Prevots DR, Marras TK. Epidemiology of human pulmonary infection with nontuberculous mycobacteria: a review. Clin Chest Med. 2015;36:13–34.
Kwak N, Lee CH, Lee H, et al. Non-tuberculous mycobacterial lung disease: diagnosis based on computed tomography of the chest. Eur Radiol. 2016;26:4449–4456.
Lee G, Lee KS, Moon JW, et al. Nodular bronchiectatic Mycobacterium avium complex pulmonary disease. Natural course on serial computed tomographic scans. Ann Am Thorac Soc. 2013;10:299–306.
Miller WTJ. Spectrum of pulmonary nontuberculous mycobacterial infection. Radiology. 1994;191:343–350.
Haworth CS, Banks J, Capstick T, et al. British Thoracic Society guidelines for the management of non-tuberculous mycobacterial pulmonary disease (NTM-PD). Thorax. 2017;72:ii1–ii64.
Lam PK, Griffith DE, Aksamit TR, et al. Factors related to response to intermittent treatment of Mycobacterium avium complex lung disease. Am J Respir Crit Care Med. 2006;173:1283–1289.
Wang YH, Lin AS, Lai YF, et al. The high value of high-resolution computed tomography in predicting the activity of pulmonary tuberculosis. Int J Tuberc Lung Dis. 2003;7:563–568.
Wang Y, Shang X, Wang L, et al. Clinical characteristics and chest computed tomography findings related to the infectivity of pulmonary tuberculosis. BMC Infect Dis. 2021;21:1197–2.
Hwang EJ, Park S, Jin K, et al. Development and validation of a deep learning-based automatic detection algorithm for active pulmonary tuberculosis on chest radiographs. Clin Infect Dis. 2019;69:739–747.
Xing Z, Ding W, Zhang S, et al. Machine learning-based differentiation of nontuberculous mycobacteria lung disease and pulmonary tuberculosis using CT images. Biomed Res Int. 2020;2020:6287545.
Wang L, Ding W, Mo Y, et al. Distinguishing nontuberculous mycobacteria from Mycobacterium tuberculosis lung disease from CT images using a deep learning framework. Eur J Nucl Med Mol Imaging. 2021;48:4293–4306.
Lee S, Lee HW, Kim H, et al. Deep learning-based prediction model using radiography in nontuberculous mycobacterial pulmonary disease. Chest. 2022;162:995–1005.
Provoost J, Valour F, Gamondes D, et al. A retrospective study of factors associated with treatment decision for nontuberculous mycobacterial lung disease in adults without altered systemic immunity. BMC Infect Dis. 2018;18:659–665.
Kroft LJM, van der Velden L, Giron IH, et al. Added value of ultra-low-dose computed tomography, dose equivalent to chest x-ray radiography, for diagnosing chest pathology. J Thorac Imaging. 2019;34:179–186.
Higashiguchi M, Nishioka K, Kimura H, et al. Prediction of the duration needed to achieve culture negativity in patients with active pulmonary tuberculosis using convolutional neural networks and chest radiography. Respir Investig. 2021;59:421–427.
Lee S, Yim J, Kwak N, et al. Deep learning to determine the activity of pulmonary tuberculosis on chest radiographs. Radiology. 2021;301:435–442.
Kazemzadeh S, Yu J, Jamshy S, et al. Deep learning detection of active pulmonary tuberculosis at chest radiography matched the clinical performance of radiologists. Radiology. 2023;306:124–137.
Wang P, Pan S, Shu C, et al. Clinical course and risk factors of mortality in Mycobacterium avium complex lung disease without initial treatment. Respir Med. 2020;171:106070.
Pan S, Shu C, Feng J, et al. Microbiological Persistence in patients with mycobacterium avium complex lung disease: the predictors and the impact on radiographic progression. Clin Infect Dis. 2017;65:927–934.
Thomson RM, Yew W. When and how to treat pulmonary non-tuberculous mycobacterial diseases. Respirology. 2009;14:12–26.