{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T16:24:19Z","timestamp":1787502259355,"version":"build-2736575974"},"reference-count":39,"publisher":"BMJ","issue":"5","funder":[{"DOI":"10.13039\/100000125","name":"National Institute for Occupational Safety and Health","doi-asserted-by":"publisher","award":["1 R21OH012384"],"award-info":[{"award-number":["1 R21OH012384"]}],"id":[{"id":"10.13039\/100000125","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Occup Environ Med"],"accepted":{"date-parts":[[2026,7,6]]},"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To develop and evaluate different deep learning (DL) models for clinically relevant screening and classification of pneumoconiosis based on chest radiographs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study used B-reader labelled pneumoconiosis lung images from US workers. After pre-processing the images, DL models were trained and evaluated for four classification tasks: (1) parenchymal abnormalities present versus absent, (2) parenchymal and\/or pleural abnormalities present versus absent, (3) small parenchymal opacities grade 1 versus grade 0 and (4) progressive massive fibrosis versus simple pneumoconiosis versus no pneumoconiosis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 2968 lung images were divided as follows: 2294 for training, 287 for validation, 287 for independent in-distribution testing and 100 for out-of-distribution testing from a separate scanner manufacturer dataset. On the in-distribution testing data set, the DL models achieved an accuracy of 0.93 (SD=0.01), 0.92 (SD=0.02) and 0.91 (SD=0.02) for task 1, 2 and 3, respectively. DL had comparable or better performance compared with certified B-readers who had average accuracies of 0.9 (SD=0.11), 0.91 (SD=0.10) and 0.77 (SD=0.21). For task 4, the DL model achieved an accuracy of 0.83 (SD=0.02), which is similar to B-readers' performance (average accuracy of 0.86 (SD=0.12)). Performance was markedly lower on the out-of-distribution test set, with reduced accuracy and AUC.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>On independent, in-distribution test images, DL models performed comparably to certified B-readers for tasks 1\u20134, supporting their potential to augment pneumoconiosis screening and classification. Reduced performance on challenging out-of-distribution cases warrants further study to improve generalisation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/oemed-2026-111040","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:25:23Z","timestamp":1784136323000},"page":"276-282","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Pneumoconiosis screening and classification using deep learning models"],"prefix":"10.1136","volume":"83","author":[{"given":"Meiqi","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Statistics and Probability, Michigan State University, East Lansing, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zenas","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Computational Mathematics, Science, and Engineering, Michigan State University, East Lansing, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michal","family":"Borek","sequence":"additional","affiliation":[{"name":"Department of Computational Mathematics, Science, and Engineering, Michigan State University, East Lansing, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ian","family":"Loveless","sequence":"additional","affiliation":[{"name":"Department of Computational Mathematics, Science, and Engineering, Michigan State University, East Lansing, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2053-4849","authenticated-orcid":false,"given":"Kenneth","family":"Rosenman","sequence":"additional","affiliation":[{"name":"Department of Medicine, Michigan State University, East Lansing, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Alessio","sequence":"additional","affiliation":[{"name":"Department of Computational Mathematics, Science, and Engineering, Michigan State University, East Lansing, Michigan, USA"},{"name":"Department of Biomedical Engineering, Michigan State University, East Lansing, Michigan, USA"},{"name":"Department of Radiology, Michigan State University, East Lansing, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2452-6691","authenticated-orcid":false,"given":"Ling","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Medicine, Michigan State University, East Lansing, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"2026082308400585000_83.5.276.1","doi-asserted-by":"publisher","DOI":"10.1097\/JOM.0000000000001735"},{"key":"2026082308400585000_83.5.276.2","unstructured":"International Labour Office . Guidelines for the use of the ILO International Classification of Radiographs of Pneumoconioses. Revised edition 2022. Geneva, 2022."},{"key":"2026082308400585000_83.5.276.3","unstructured":"National Institute for Occupational Safety and Health (NIOSH) . Radiographic screening and B readers. Available: https:\/\/www.cdc.gov\/niosh\/chestradiography\/php\/breader [Accessed 14 Mar 2026]."},{"key":"2026082308400585000_83.5.276.4","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0274(199809)34:3<261::AID-AJIM8>3.0.CO;2-Y"},{"key":"2026082308400585000_83.5.276.5","doi-asserted-by":"publisher","DOI":"10.1378\/chest.114.6.1740"},{"key":"2026082308400585000_83.5.276.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2009.12.003"},{"key":"2026082308400585000_83.5.276.7","doi-asserted-by":"crossref","first-page":"1634","DOI":"10.1513\/AnnalsATS.202010-1350OC","article-title":"Association between financial conflicts of interest and International Labor Office classifications for black lung disease","volume":"18","author":"Friedman","year":"2021","journal-title":"Ann Am Thorac Soc"},{"key":"2026082308400585000_83.5.276.8","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.1513\/AnnalsATS.202107-764ED","article-title":"To be (B read) or not to be (B read), that is the question: conflict of interest and radiographic interpretation","volume":"18","author":"Redlich","year":"2021","journal-title":"Ann Am Thorac Soc"},{"key":"2026082308400585000_83.5.276.9","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1109\/TBME.1975.324475","article-title":"Computer classification of pneumoconiosis from radiographs of coal workers","volume":"BME-22","author":"Hall","year":"1975","journal-title":"IEEE Trans Biomed Eng"},{"key":"2026082308400585000_83.5.276.10","doi-asserted-by":"crossref","first-page":"108516","DOI":"10.1016\/j.engappai.2024.108516","article-title":"Artificial intelligence for computer aided detection of pneumoconiosis: a succinct review since 1974","volume":"133","author":"Mushtaq","year":"2024","journal-title":"Eng Appl Artif Intell"},{"key":"2026082308400585000_83.5.276.11","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1007\/s10278-010-9276-7","article-title":"An automatic computer-aided detection scheme for pneumoconiosis on digital chest radiographs","volume":"24","author":"Yu","year":"2011","journal-title":"J Digit Imaging"},{"key":"2026082308400585000_83.5.276.12","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1007\/s10278-017-9942-0","article-title":"Computerized classification of pneumoconiosis on digital chest radiography: artificial neural network with three stages","volume":"30","author":"Okumura","year":"2017","journal-title":"J Digit Imaging"},{"key":"2026082308400585000_83.5.276.13","doi-asserted-by":"crossref","first-page":"100391","DOI":"10.1016\/j.imu.2020.100391","article-title":"Hybrid deep learning for detecting lung diseases from X-ray images","volume":"20","author":"Bharati","year":"2020","journal-title":"Inform Med Unlocked"},{"key":"2026082308400585000_83.5.276.14","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.neucom.2020.03.127","article-title":"Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels","volume":"437","author":"Pham","year":"2021","journal-title":"Neurocomputing"},{"key":"2026082308400585000_83.5.276.15","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1609\/aaai.v33i01.3301590","article-title":"CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison","volume":"33","author":"Irvin","year":"2019","journal-title":"AAAI"},{"key":"2026082308400585000_83.5.276.16","doi-asserted-by":"publisher","DOI":"10.1136\/oemed-2019-106386"},{"key":"2026082308400585000_83.5.276.17","doi-asserted-by":"crossref","first-page":"146533","DOI":"10.1109\/ACCESS.2019.2946000","article-title":"Pulmonary image classification based on Inception-v3 transfer learning model","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE Access"},{"key":"2026082308400585000_83.5.276.18","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph18179091","article-title":"Balanced convolutional neural networks for pneumoconiosis detection","volume":"18","author":"Hao","year":"2021","journal-title":"Int J Environ Res Public Health"},{"key":"2026082308400585000_83.5.276.19","doi-asserted-by":"crossref","DOI":"10.1186\/s12880-021-00723-z","article-title":"Pneumoconiosis computer aided diagnosis system based on X-rays and deep learning","volume":"21","author":"Yang","year":"2021","journal-title":"BMC Med Imaging"},{"key":"2026082308400585000_83.5.276.20","doi-asserted-by":"crossref","first-page":"5154","DOI":"10.1109\/JBHI.2022.3190923","article-title":"A fully deep learning paradigm for pneumoconiosis staging on chest radiographs","volume":"26","author":"Sun","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"2026082308400585000_83.5.276.21","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/s44196-021-00046-5","article-title":"Computer-aided diagnosis for pneumoconiosis staging based on multi-scale feature mapping","volume":"14","author":"Zhang","year":"2021","journal-title":"Int J Comput Intell Syst"},{"key":"2026082308400585000_83.5.276.22","doi-asserted-by":"crossref","DOI":"10.1186\/s12880-024-01337-x","article-title":"Deep learning pneumoconiosis staging and diagnosis system based on multi-stage joint approach","volume":"24","author":"Liu","year":"2024","journal-title":"BMC Med Imaging"},{"key":"2026082308400585000_83.5.276.23","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-020-77924-z","article-title":"A deep learning-based model for screening and staging pneumoconiosis","volume":"11","author":"Zhang","year":"2021","journal-title":"Sci Rep"},{"key":"2026082308400585000_83.5.276.24","doi-asserted-by":"crossref","DOI":"10.1097\/MD.0000000000038478","article-title":"Potential of digital chest radiography-based deep learning in screening and diagnosing pneumoconiosis: An observational study","volume":"103","author":"Zhang","year":"2024","journal-title":"Medicine (Baltimore)"},{"key":"2026082308400585000_83.5.276.25","doi-asserted-by":"publisher","DOI":"10.1007\/BF02888156"},{"key":"2026082308400585000_83.5.276.26","doi-asserted-by":"crossref","first-page":"104125","DOI":"10.1016\/j.compbiomed.2020.104125","article-title":"Automated detection of pneumoconiosis with multilevel deep features learned from chest X-Ray radiographs","volume":"129","author":"Devnath","year":"2021","journal-title":"Comput Biol Med"},{"key":"2026082308400585000_83.5.276.27","doi-asserted-by":"crossref","first-page":"11193","DOI":"10.3390\/ijerph191811193","article-title":"Detection and visualisation of pneumoconiosis using an ensemble of multi-dimensional deep features learned from chest X-rays","volume":"19","author":"Devnath","year":"2022","journal-title":"IJERPH"},{"key":"2026082308400585000_83.5.276.28","doi-asserted-by":"crossref","first-page":"110153","DOI":"10.1016\/j.compbiomed.2025.110153","article-title":"Automated engineered-stone silicosis screening and staging using deep learning with X-rays","volume":"191","author":"Priego-Torres","year":"2025","journal-title":"Comput Biol Med"},{"key":"2026082308400585000_83.5.276.29","doi-asserted-by":"crossref","first-page":"103828","DOI":"10.1016\/j.media.2025.103828","article-title":"Ark+: Supervised training a single high-performance AI foundation model from many differently labeled datasets-no label consolidation required","volume":"108","author":"Ma","year":"2026","journal-title":"Med Image Anal"},{"key":"2026082308400585000_83.5.276.30","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103248"},{"key":"2026082308400585000_83.5.276.31","doi-asserted-by":"crossref","first-page":"2042","DOI":"10.1109\/TMI.2021.3070847","article-title":"A structure-aware relation network for thoracic diseases detection and segmentation","volume":"40","author":"Lian","year":"2021","journal-title":"IEEE Trans Med Imaging"},{"key":"2026082308400585000_83.5.276.32","unstructured":"Cohen JP , Viviano JD , Bertin P , et al . TorchXRayVision: a library of chest x-ray datasets and models. n.d. Available: https:\/\/github.com\/mlmed\/torchxrayvision"},{"key":"2026082308400585000_83.5.276.33","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1007\/s10044-023-01181-9","article-title":"Deep neural networks for rank-consistent ordinal regression based on conditional probabilities","volume":"26","author":"Shi","year":"2023","journal-title":"Pattern Anal Applic"},{"key":"2026082308400585000_83.5.276.34","doi-asserted-by":"crossref","unstructured":"He K , Zhang X , Ren S , et al . Delving deep into rectifiers: surpassing human-level performance on imagenet classification. 2015 IEEE International Conference on Computer Vision (ICCV); 1026\u201334. Santiago, Chile. doi:10.1109\/ICCV.2015.123","DOI":"10.1109\/ICCV.2015.123"},{"key":"2026082308400585000_83.5.276.35","unstructured":"Kokhlikyan N , Miglani V , Martin M , et al . Captum: a unified and generic model interpretability library for PyTorch, 2020. Available: https:\/\/arxiv.org\/abs\/2009.07896"},{"key":"2026082308400585000_83.5.276.36","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-019-0189-7","article-title":"Human-machine partnership with artificial intelligence for chest radiograph diagnosis","volume":"2","author":"Patel","year":"2019","journal-title":"NPJ Digit Med"},{"key":"2026082308400585000_83.5.276.37","doi-asserted-by":"publisher","DOI":"10.1378\/chest.120.1.64"},{"key":"2026082308400585000_83.5.276.38","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1038\/s42256-021-00338-7","article-title":"AI for radiographic COVID-19 detection selects shortcuts over signal","volume":"3","author":"DeGrave","year":"2021","journal-title":"Nat Mach Intell"},{"key":"2026082308400585000_83.5.276.39","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16529-w"}],"container-title":["Occupational and Environmental Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/oemed-2026-111040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T15:40:58Z","timestamp":1787499658000},"score":1,"resource":{"primary":{"URL":"https:\/\/oem.bmj.com\/lookup\/doi\/10.1136\/oemed-2026-111040"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":39,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,8,23]]},"published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1136\/oemed-2026-111040"],"URL":"https:\/\/doi.org\/10.1136\/oemed-2026-111040","relation":{},"ISSN":["1351-0711","1470-7926"],"issn-type":[{"value":"1351-0711","type":"print"},{"value":"1470-7926","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]}}}