{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:53:44Z","timestamp":1776750824030,"version":"3.51.2"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Basic public welfare projects in Zhejiang province","award":["LGF22H010006"],"award-info":[{"award-number":["LGF22H010006"]}]},{"name":"Ningbo Key Research and Development Program","award":["2024Z207"],"award-info":[{"award-number":["2024Z207"]}]},{"name":"Zhejiang Province Medical and Health Science and Technology Plan Project","award":["2023KY1026"],"award-info":[{"award-number":["2023KY1026"]}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Differentiating non-tuberculous mycobacterial lung disease (NTM-LD) from pulmonary tuberculosis (PTB) remains a significant clinical challenge owing to their overlapping clinical and imaging features, despite markedly different therapeutic strategies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A total of 409 patients with microbiologically confirmed diagnoses were retrospectively enrolled and randomly divided into a training set (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f329; NTM-LD: 171, PTB: 158) and an independent test set (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f80; NTM-LD: 41, PTB: 39). After lung segmentation with nnU-Net, images were intensity-normalized and resampled to 256\u202f\u00d7\u202f256\u202f\u00d7\u202f128 voxels. A 3D ResNeXt-based classifier was developed and compared against six mainstream deep learning architectures: ResNet, SENet, DenseNet, ShuffleNet, Transformer, and Swin Transformer. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and F1 score.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The proposed 3D ResNeXt model achieved the highest performance, with an AUC of 0.89 and accuracy of 0.89 on the training set, and an AUC of 0.83 and accuracy of 0.84 on the independent test set. DeLong\u2019s test confirmed statistically significant superiority over all six comparator architectures on the test set (all\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.05). Gradient-weighted Class Activation Mapping (Grad-CAM) visualizations highlighted disease-specific features, including nodular bronchiectasis and tree-in-bud opacities in NTM-LD, as well as thick-walled cavitary lesions in PTB.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The 3D ResNeXt model demonstrated superior and interpretable performance in differentiating NTM-LD from PTB on chest CT. It holds promise as a valuable clinical decision-support tool, although prospective multicenter validation is warranted.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1786346","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:34:49Z","timestamp":1776749689000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning-based differentiation of non-tuberculous mycobacterial lung disease and pulmonary tuberculosis using chest CT"],"prefix":"10.3389","volume":"13","author":[{"given":"Bingchuan","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Thoracic Surgery, The Affiliated Lihuili Hospital of Ningbo University","place":["Ningbo, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Medical Science, Ningbo University","place":["Ningbo, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuwei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery, The Affiliated Lihuili Hospital of Ningbo University","place":["Ningbo, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zherui","family":"Shao","sequence":"additional","affiliation":[{"name":"College of Medical Science, Ningbo University","place":["Ningbo, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingning","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery, The Affiliated Lihuili Hospital of Ningbo University","place":["Ningbo, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binyu","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery, The Affiliated Lihuili Hospital of Ningbo University","place":["Ningbo, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Yu","sequence":"additional","affiliation":[{"name":"Hangzhou Fuyangyan Medical Imaging Technical Service Studio","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery, The Affiliated Lihuili Hospital of Ningbo University","place":["Ningbo, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1038\/s41573-024-00897-5","article-title":"Therapeutic developments for tuberculosis and nontuberculous mycobacterial lung disease","volume":"23","author":"Dartois","year":"2024","journal-title":"Nat Rev Drug Discov"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"7348","DOI":"10.1038\/s41598-023-34576-z","article-title":"The factors associated with mortality and progressive disease of nontuberculous mycobacterial lung disease: a systematic review and meta-analysis","volume":"13","author":"Hwang","year":"2023","journal-title":"Sci Rep"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"116254","DOI":"10.1016\/j.diagmicrobio.2024.116254","article-title":"Advances in diagnosis and treatment of non-tuberculous mycobacterial lung disease","volume":"109","author":"Ying","year":"2024","journal-title":"Diagn Microbiol Infect Dis"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"3527","DOI":"10.2147\/IDR.S529466","article-title":"Phenotyping nontuberculous mycobacterial lung disease: comparative analysis of clinical and imaging features in a TB-endemic setting","volume":"18","author":"Feng","year":"2025","journal-title":"Infect Drug Resist"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"988","DOI":"10.3390\/pathogens12080988","article-title":"Trends from the last decade with nontuberculous mycobacteria lung disease (NTM-LD): clinicians\u2019 perspectives in regional center of pulmonology in Bydgoszcz, Poland","volume":"12","author":"Przybylski","year":"2023","journal-title":"Pathogens"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e0301659","DOI":"10.1371\/journal.pone.0301659","article-title":"Multiparameter immunoprofiling for the diagnosis and differentiation of progressive versus nonprogressive nontuberculous mycobacterial lung disease\u2013a pilot study","volume":"19","author":"Marty","year":"2024","journal-title":"PLoS One"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.1016\/j.chest.2023.06.014","article-title":"Risk factors for nontuberculous mycobacterial pulmonary disease: a systematic literature review and meta-analysis","volume":"164","author":"Loebinger","year":"2023","journal-title":"Chest"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1186\/s12931-023-02612-1","article-title":"Treatable traits and challenges in the clinical management of non-tuberculous mycobacteria lung disease in people with cystic fibrosis","volume":"24","author":"Gramegna","year":"2023","journal-title":"Respir Res"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.3390\/biomedinformatics4030111","article-title":"Pulmonary nodule detection, segmentation and classification using deep learning: a comprehensive literature review","volume":"4","author":"Marinakis","year":"2024","journal-title":"BioMedInformatics"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/s00330-024-10907-0","article-title":"Deep learning in pulmonary nodule detection and segmentation: a systematic review","volume":"35","author":"Gao","year":"2025","journal-title":"Eur Radiol"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-025-11829-1","article-title":"Performance of a screening-trained DL model for pulmonary nodule malignancy estimation of incidental clinical nodules","volume":"36","author":"Dinnessen","year":"2025","journal-title":"Eur Radiol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"24101","DOI":"10.1007\/s11042-023-16419-1","article-title":"A systematic literature review on deep learning approaches for pneumonia detection using chest X-ray images","volume":"83","author":"Sharma","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1139\/bcb-2023-0265","article-title":"ChestCovidNet: an effective DL-based approach for COVID-19, lung opacity, and pneumonia detection using chest radiographs images","volume":"104","author":"Ullah","year":"2024","journal-title":"Biochem Cell Biol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1721949","DOI":"10.3389\/fmed.2026.1721949","article-title":"Distinguishing nontuberculous mycobacterial lung disease from pulmonary tuberculosis using radiomics machine learning models from CT images","volume":"13","author":"Zheng","year":"2026","journal-title":"Front Med"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"112","DOI":"10.3892\/etm.2024.12400","article-title":"CT-based radiomics analysis of consolidation characteristics in differentiating pulmonary disease of non-tuberculous mycobacterium from pulmonary tuberculosis","volume":"27","author":"Yan","year":"2024","journal-title":"Exp Ther Med"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1002\/mp.17537","article-title":"Lung CT-based multi-lesion radiomic model to differentiate between nontuberculous mycobacteria and Mycobacterium tuberculosis","volume":"52","author":"Hu","year":"2025","journal-title":"Med Phys"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.3390\/s20061652","article-title":"Three-dimensional resnext network using feature fusion and label smoothing for hyperspectral image classification","volume":"20","author":"Wu","year":"2020","journal-title":"Sensors"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"5389","DOI":"10.1007\/s00330-024-10585-y","article-title":"Deep learning\u2013based multimodal segmentation of oropharyngeal squamous cell carcinoma on CT and MRI using self-configuring nnU-net","volume":"34","author":"Choi","year":"2024","journal-title":"Eur Radiol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"9802","DOI":"10.3390\/app13179802","article-title":"FPN-SE-ResNet model for accurate diagnosis of kidney tumors using CT images","volume":"13","author":"Abdelrahman","year":"2023","journal-title":"Appl Sci"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"25747","DOI":"10.1007\/s11042-023-14581-0","article-title":"Lung nodule detection of CT images based on combining 3D-CNN and squeeze-and-excitation networks","volume":"82","author":"Mkindu","year":"2023","journal-title":"Multimed Tools Appl"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"106330","DOI":"10.1016\/j.bspc.2024.106330","article-title":"Lung cancer classification using optimized attention-based convolutional neural network with DenseNet-201 transfer learning model on CT image","volume":"95","author":"Mohandass","year":"2024","journal-title":"Biomed Signal Process Control"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"162","DOI":"10.3390\/diagnostics13010162","article-title":"A holistic approach to identify and classify COVID-19 from chest radiographs, ECG, and CT-scan images using shufflenet convolutional neural network","volume":"13","author":"Ullah","year":"2023","journal-title":"Diagnostics"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"107162","DOI":"10.1016\/j.compbiomed.2023.107162","article-title":"A novel denoising method for low-dose CT images based on transformer and CNN","volume":"163","author":"Zhang","year":"2023","journal-title":"Comput Biol Med"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"981463","DOI":"10.3389\/fphys.2022.981463","article-title":"COVID-19 CT image segmentation method based on swin transformer","volume":"13","author":"Sun","year":"2022","journal-title":"Front Physiol"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1186\/s12879-023-08537-w","article-title":"Non-tuberculous mycobacteria lung disease due to Mycobacterium chimaera in a 67-year-old man treated with immune checkpoint inhibitors for lung adenocarcinoma: infection due to dysregulated immunity?","volume":"23","author":"Azzar\u00e0","year":"2023","journal-title":"BMC Infect Dis"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/j.chest.2022.09.025","article-title":"The other nontuberculous mycobacteria: clinical aspects of lung disease caused by less common slowly growing nontuberculous mycobacteria species","volume":"163","author":"Yan","year":"2023","journal-title":"Chest"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"ofae427","DOI":"10.1093\/ofid\/ofae427","article-title":"Clinical predictors of nontuberculous mycobacteria lung disease and Coisolates of potential pathogenic microorganisms in noncystic fibrosis bronchiectasis","volume":"11","author":"Wang","year":"2024","journal-title":"Open Forum Infect Dis"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"e59","DOI":"10.69854\/jcq.2025.0005","article-title":"Clinical features of simultaneous diagnoses of lung cancer and nontuberculous mycobacterial lung disease: a systematic review and pooled analysis","volume":"2","author":"Kashizaki","year":"2025","journal-title":"J Clin Quest"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1007\/s00330-024-10987-y","article-title":"Evaluation of treatment response with serial CT in patients with non-tuberculous mycobacterial pulmonary disease","volume":"35","author":"Dettmer","year":"2025","journal-title":"Eur Radiol"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1273253","DOI":"10.3389\/fpubh.2023.1273253","article-title":"Medical image analysis using deep learning algorithms","volume":"11","author":"Li","year":"2023","journal-title":"Front Public Health"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"26731","DOI":"10.1007\/s11042-022-14305-w","article-title":"Machine learning and deep learning approach for medical image analysis: diagnosis to detection","volume":"82","author":"Rana","year":"2023","journal-title":"Multimed Tools Appl"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"100567","DOI":"10.1016\/j.cobme.2024.100567","article-title":"Generalizable and explainable deep learning for medical image computing: an overview","volume":"33","author":"Chaddad","year":"2025","journal-title":"Curr Opin Biomed Eng"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1186\/s12879-023-07996-5","article-title":"Distinguishing nontuberculous mycobacterial lung disease and Mycobacterium tuberculosis lung disease on X-ray images using deep transfer learning","volume":"23","author":"Park","year":"2023","journal-title":"BMC Infect Dis"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"927","DOI":"10.18553\/jmcp.2023.22417","article-title":"Identifying potentially undiagnosed nontuberculous mycobacterial lung disease among patients with chronic obstructive pulmonary disease: development of a predictive algorithm using claims data","volume":"29","author":"Wang","year":"2023","journal-title":"J Manag Care Spec Pharm"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"111064","DOI":"10.1016\/j.intimp.2023.111064","article-title":"Building a model for the differential diagnosis of non-tuberculous mycobacterial lung disease and pulmonary tuberculosis: a case-control study based on immunological and radiological features","volume":"124","author":"Liu","year":"2023","journal-title":"Int Immunopharmacol"},{"key":"ref36","author":"Liu","year":"2026"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1186\/s13244-025-02131-1","article-title":"AI-assisted differentiation of nontuberculous mycobacterial pulmonary disease from colonization: a multi-center tudy","volume":"16","author":"Liu","year":"2025","journal-title":"Insights Imaging"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1786346\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:34:51Z","timestamp":1776749691000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1786346\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":37,"alternative-id":["10.3389\/fmed.2026.1786346"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1786346","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]},"article-number":"1786346"}}