{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T20:00:37Z","timestamp":1790625637801,"version":"4.1.0"},"reference-count":41,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"China Medical University Hsinchu Hospital","award":["CMUHCH-DMR-112-023"],"award-info":[{"award-number":["CMUHCH-DMR-112-023"]}]},{"name":"China Medical University Hsinchu Hospital","award":["CMUHCH-DMR-112-001"],"award-info":[{"award-number":["CMUHCH-DMR-112-001"]}]},{"name":"China Medical University Hsinchu Hospital","award":["CMUHCH-DMR-112-003"],"award-info":[{"award-number":["CMUHCH-DMR-112-003"]}]},{"name":"Taiwan National Science and Technology Council","award":["NSTC 113-2314-B-016-027-MY2"],"award-info":[{"award-number":["NSTC 113-2314-B-016-027-MY2"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: To develop and externally evaluate a deep learning framework for multi-label thoracic disease classification on chest radiographs using hybrid convolutional neural network (CNN)\u2013transformer architectures, hierarchical scalar-weighted fusion, and ensemble strategies. Methods: This retrospective, multi-center study utilized publicly available datasets: NIH ChestX-ray14 (112,120 images; 30,805 patients) for model development and internal testing, and CheXpert (223,415 images) plus ChestX-Det10 (3578 images) for external validation. Nine CNN\u2013transformer hybrids were systematically benchmarked, and the proposed model incorporated multi-scale DenseNet121 features, scalar-weighted fusion, positional encodings, and cross-attention. Four post hoc ensemble methods were explored, including a class-wise Top-3 Grid Search. Performance was evaluated using AUROC as the primary metric, along with precision, recall, F1-score, accuracy, specificity, positive predictive value, and negative predictive value. Statistical comparisons were performed using bootstrapped resampling and appropriate parametric or non-parametic tests. Results: On the NIH internal test set, the proposed hybrid model achieved a mean AUROC of 0.8495, which was significantly higher than that of the DenseNet121 baseline (0.8441, p = 0.032). The Top-3 Grid Search ensemble further improved internal performance, achieving a mean AUROC of 0.8577 (p &lt; 0.00001). On external validation, the ensemble consistently outperformed DenseNet121, achieving mean AUROCs of 0.6500 on CheXpert (p &lt; 0.001) and 0.6592 on ChestX-Det10 (p &lt; 0.001). Per-class analysis revealed significant improvements for clinically important conditions such as cardiomegaly, mass, and pneumothorax. Grad-CAM visualizations demonstrated the strong alignment of predicted abnormalities with radiologically relevant regions. Conclusions: This CNN\u2013transformer framework, particularly when combined with class-wise ensemble strategies, provided modest but statistically significant improvements in multi-label chest X-ray classification. External validation suggested partial generalizability across datasets, although performance remained moderate under domain shift.<\/jats:p>","DOI":"10.3390\/diagnostics16081227","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T12:01:22Z","timestamp":1776686482000},"page":"1227","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An Adaptive Deep Learning Framework for Multi-Label Chest X-Ray Diagnosis Using a Hybrid CNN\u2013Transformer Architecture and Class-Wise Ensemble Fusion"],"prefix":"10.3390","volume":"16","author":[{"given":"Chi-Feng","family":"Hsieh","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu 300, Taiwan"},{"name":"Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu 302, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6318-1377","authenticated-orcid":false,"given":"Hsu-Hsia","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu 300, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Hsiang","family":"Tsai","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu 302, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chia-Ching","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu 302, Taiwan"},{"name":"Department of Management Science, National Yang Ming Chiao Tung University, Hsinchu 300, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Hsuan","family":"Juan","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging, China Medical University Hospital, Taichung 404, Taiwan"},{"name":"Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei 106, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsian-He","family":"Hsu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Tri-Service General Hospital and National Defense Medical University, Taipei 114, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5219-0406","authenticated-orcid":false,"given":"Chun-Jung","family":"Juan","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu 300, Taiwan"},{"name":"Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu 302, Taiwan"},{"name":"Department of Medical Imaging, China Medical University Hospital, Taichung 404, Taiwan"},{"name":"Department of Radiology, School of Medicine, College of Medicine, China Medical University, Taichung 406, Taiwan"},{"name":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei 106, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"ref_1","first-page":"185","article-title":"Imaging the Chest: The Chest Radiograph","volume":"5","author":"Sanders","year":"2011","journal-title":"Diagnostic Imaging for the Emergency Physician"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"110195","DOI":"10.1016\/j.ejrad.2022.110195","article-title":"Trend in radiologist workload compared to number of admissions in the emergency department","volume":"149","author":"Lantsman","year":"2022","journal-title":"Eur. J. Radiol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e232625","DOI":"10.1148\/radiol.232625","article-title":"The Growing Nationwide Radiologist Shortage: Current Opportunities and Ongoing Challenges for International Medical Graduate Radiologists","volume":"314","author":"Mirak","year":"2025","journal-title":"Radiology"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Elemraid, M.A., Muller, M., Spencer, D.A., Rushton, S.P., Gorton, R., Thomas, M.F., Eastham, K.M., Hampton, F., Gennery, A.R., and Clark, J.E. (2014). Accuracy of the interpretation of chest radiographs for the diagnosis of paediatric pneumonia. PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0106051"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"5876","DOI":"10.1007\/s00330-024-10676-w","article-title":"Artificial intelligence-assisted double reading of chest radiographs to detect clinically relevant missed findings: A two-centre evaluation","volume":"34","author":"Topff","year":"2024","journal-title":"Eur. Radiol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"7255","DOI":"10.1007\/s00330-024-10794-5","article-title":"Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload","volume":"34","author":"Schalekamp","year":"2024","journal-title":"Eur. Radiol."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Xiong, K., Tu, Y., Rao, X., Zou, X., and Du, Y. (2025). Multi-Label Disease Detection in Chest X-Ray Imaging Using a Fine-Tuned ConvNeXtV2 with a Customized Classifier. Informatics, 12.","DOI":"10.3390\/informatics12030080"},{"key":"ref_8","unstructured":"Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C., and Shpanskaya, K. (2017). CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Tekerek, A., and Al-Rawe, I.A.M. (2023). A Novel Approach for Prediction of Lung Disease Using Chest X-ray Images Based on DenseNet and MobileNet. Wirel. Pers. Commun.","DOI":"10.1007\/s11277-023-10489-y"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e2686","DOI":"10.7717\/peerj-cs.2686","article-title":"A multi-scale CNN with atrous spatial pyramid pooling for enhanced chest-based disease detection","volume":"11","author":"Bukhari","year":"2025","journal-title":"PeerJ Comput. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Gtifa, W., Mhaouch, A., Alsharif, N., Althobaiti, T., and Sakly, A. (2025). Nature-Inspired Multi-Level Thresholding Integrated with CNN for Accurate COVID-19 and Lung Disease Classification in Chest X-Ray Images. Diagnostics, 15.","DOI":"10.3390\/diagnostics15121500"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Rana, N., Coulibaly, Y., Noor, A., Noor, T.H., Alam, I., Khan, Z., Tahir, A., and Khan, M.Z. (2025). Improved swin transformer-based thorax disease classification with optimal feature selection using chest X-ray. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0327099"},{"key":"ref_13","first-page":"742","article-title":"LungNet-ViT: Efficient lung disease classification using a multistage vision transformer model from chest radiographs","volume":"33","author":"Padmavathi","year":"2025","journal-title":"J. Xray Sci. Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2539","DOI":"10.21037\/qims-23-1280","article-title":"Research and implementation of multi-disease diagnosis on chest X-ray based on vision transformer","volume":"14","author":"Huang","year":"2024","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"100701","DOI":"10.1016\/j.ejro.2025.100701","article-title":"Diagnostic accuracy of AI in chest radiography for pneumonia and lung cancer: A meta-analysis","volume":"15","author":"Essa","year":"2025","journal-title":"Eur. J. Radiol. Open"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., and Summers, R.M. (2017). ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21\u201326 July 2017, IEEE.","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., Marklund, H., Haghgoo, B., Ball, R., and Shpanskaya, K. (2019). CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison. Proceedings of the 33rd AAAI Conference on Artificial Intelligence, Honolulu, HI, USA, 27 January\u20131 February 2019, AAAI Press.","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref_18","unstructured":"Liu, J., Lian, J., and Yu, Y. (2020). ChestX-Det10: Chest X-ray dataset on detection of thoracic abnormalities. arXiv."},{"key":"ref_19","unstructured":"(2025, January 21). Scope of Human Research Cases Exempt from Review by the Research Ethics Committee: Wei-Shu-Yi-Zi No. 1010265075, Available online: https:\/\/gazette.nat.gov.tw\/EG_FileManager\/eguploadpub\/eg018127\/ch08\/type1\/gov70\/num35\/Eg.htm."},{"key":"ref_20","unstructured":"(2025, January 21). Scope of Human Research Cases Exempt from Obtaining the Research Subject\u2019s Consent: Wei-Shu-Yi-Zi No. 1010265083, Available online: https:\/\/gazette.nat.gov.tw\/EG_FileManager\/eguploadpub\/eg018127\/ch08\/type1\/gov70\/num36\/Eg.pdf."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Maaten, L.V.D., and Weinberger, K.Q. (2017). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21\u201326 July 2017, IEEE.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_22","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017). Attention is all you need. arXiv."},{"key":"ref_23","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., and Zhou, Y. (2021). TransUNet: Transformers make strong encoders for medical image segmentation. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1111\/j.1365-2753.2005.00598.x","article-title":"Measuring diagnostic and predictive accuracy in disease management: An introduction to receiver operating characteristic (ROC) analysis","volume":"12","author":"Linden","year":"2006","journal-title":"J. Eval. Clin. Pract."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Process. Manag."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","article-title":"Index for rating diagnostic tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer"},{"key":"ref_27","unstructured":"Loshchilov, I., and Hutter, F. (2016). SGDR: Stochastic gradient descent with warm restarts. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollar, P. (2017). Focal loss for dense object detection. Proceedings of the IEEE Int Conf. Comput Vis (ICCV), Venice, Italy, 22\u201329 October 2017, IEEE.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1093\/biomet\/52.3-4.591","article-title":"An analysis of variance test for normality (complete samples)","volume":"52","author":"Shapiro","year":"1965","journal-title":"Biometrika"},{"key":"ref_30","unstructured":"Kotz, S., and Johnson, N.L. (1925). Statistical methods for research workers. Breakthroughs in Statistics Volume II, Genesis Publishing Pvt Ltd."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1080\/01621459.1952.10483441","article-title":"Use of ranks in one-criterion variance analysis","volume":"47","author":"Kruskal","year":"1952","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"99","DOI":"10.2307\/3001913","article-title":"Comparing individual means in the analysis of variance","volume":"5","author":"Tukey","year":"1949","journal-title":"Biometrics"},{"key":"ref_33","unstructured":"Singh, S. (2024). Computer-Aided Diagnosis of Thoracic Diseases in Chest X-rays using hybrid CNN-Transformer Architecture. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ashraf, S.N., Mamun, M.A., Abdullah, H.M., and Alam, M.G.R. (2023). SynthEnsemble: A Fusion of CNN, Vision Transformer, and Hybrid Models for Multi-Label Chest X-Ray Classification. arXiv.","DOI":"10.1109\/ICCIT60459.2023.10441433"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"6650","DOI":"10.1038\/s41598-025-90607-x","article-title":"Explainable hybrid transformer for multi-classification of lung disease using chest X-rays","volume":"15","author":"Fu","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1109\/JBHI.2019.2928369","article-title":"Thorax-Net: An Attention Regularized Deep Neural Network for Classification of Thoracic Diseases on Chest Radiography","volume":"24","author":"Wang","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"e220012","DOI":"10.1148\/ryai.220012","article-title":"Visual Transformers and Convolutional Neural Networks for Disease Classification on Radiographs: A Comparison of Performance, Sample Efficiency, and Hidden Stratification","volume":"4","author":"Murphy","year":"2022","journal-title":"Radiol. Artif. Intell."},{"key":"ref_38","first-page":"64","article-title":"Chest X-Ray Classification using DenseNet","volume":"Volume 13","author":"Karna","year":"2023","journal-title":"Proceedings of 13th IOE Graduate Conference"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1007\/s10554-023-03039-x","article-title":"CheXNet and feature pyramid network: A fusion deep learning architecture for multilabel chest X-Ray clinical diagnoses classification","volume":"40","author":"Hasanah","year":"2024","journal-title":"Int. J. Cardiovasc. Imaging"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Ahmad, Z., Malik, A.K., Qamar, N., and Islam, S.U. (2023). Efficient Thorax Disease Classification and Localization Using DCNN and Chest X-ray Images. Diagnostics, 13.","DOI":"10.3390\/diagnostics13223462"},{"key":"ref_41","unstructured":"Taslimi, S., Taslimi, S., Fathi, N., Salehi, M., and Rohban, M.H. (2022). SwinCheX: Multi-label classification on chest X-ray images with transformers. arXiv."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/8\/1227\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T12:17:18Z","timestamp":1776687438000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/8\/1227"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":41,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["diagnostics16081227"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16081227","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,20]]}}}