{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T21:36:22Z","timestamp":1793396182050,"version":"4.5.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:00:00Z","timestamp":1773878400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:00:00Z","timestamp":1777852800000},"content-version":"vor","delay-in-days":46,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Manipal Academy of Higher Education, Manipal"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate and reliable classification of lung diseases from medical imaging remains challenging due to overlapping radiological patterns, disease heterogeneity, and variations in image quality. To address these challenges, this paper proposes an Adaptive Dual-Stream Attention Fusion (ADSAF) framework for automated lung disease classification. The proposed model integrates convolutional neural networks and vision transformers to jointly capture fine-grained local textures and long-range global contextual dependencies. An adaptive attention fusion mechanism dynamically learns image-specific weighting between the two feature streams, overcoming the limitations of static fusion strategies. In addition, a Self-Attention Refinement Module enhances disease-relevant regions while suppressing background noise, improving both discriminative capability and interpretability. ADSAF is designed as a general multi-class lung disease classification framework and is validated in this study through task-specific evaluations on pneumonia and COVID-19 datasets, demonstrating strong accuracy, robustness, and generalization. Experimental results demonstrate consistent performance gains over state-of-the-art CNN, transformer, and ensemble models in terms of accuracy, F-score, sensitivity, and robustness under noisy conditions and domain shifts, achieving up to 98.3% accuracy. Grad-CAM visualizations further confirm the model\u2019s focus on clinically meaningful lung regions, highlighting its potential for reliable clinical decision support.<\/jats:p>","DOI":"10.1038\/s41598-026-44441-4","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T04:57:01Z","timestamp":1773896221000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Entropy-regularized dual-stream attention fusion for multi-disease lung classification"],"prefix":"10.1038","volume":"16","author":[{"given":"Vivekanand","family":"Thakare","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shailendra S.","family":"Aote","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jayesh","family":"Gangrade","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Manoj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"44441_CR1","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1177\/1460458217723169","volume":"25","author":"D Spathis","year":"2019","unstructured":"Spathis, D. & Vlamos, P. Diagnosing asthma and chronic obstructive pulmonary disease with machine learning. Health Inf. J. 25, 811\u2013827 (2019).","journal-title":"Health Inf. J."},{"key":"44441_CR2","doi-asserted-by":"publisher","first-page":"1805","DOI":"10.1109\/JBHI.2016.2642944","volume":"24","author":"J Ying","year":"2020","unstructured":"Ying, J. et al. Classification of exacerbation frequency in the COPDGene cohort using deep learning with deep belief networks. IEEE J. Biomed. Health Inf. 24, 1805\u20131813 (2020).","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"44441_CR3","doi-asserted-by":"publisher","first-page":"38907","DOI":"10.1109\/ACCESS.2020.2974617","volume":"8","author":"R Du","year":"2020","unstructured":"Du, R. et al. Identification of COPD from multi-view snapshots of 3D lung airway tree via deep CNN. IEEE Access. 8, 38907\u201338919 (2020).","journal-title":"IEEE Access."},{"key":"44441_CR4","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1007\/s00521-017-3048-y","volume":"31","author":"PPR Filho","year":"2019","unstructured":"Filho, P. P. R. et al. Automated recognition of lung diseases in CT images based on the optimum-path forest classifier. Neural Comput. Appl. 31, 901\u2013914 (2019).","journal-title":"Neural Comput. Appl."},{"key":"44441_CR5","doi-asserted-by":"publisher","first-page":"34691","DOI":"10.1109\/ACCESS.2024.3372588","volume":"12","author":"M Ali","year":"2024","unstructured":"Ali, M. et al. Pneumonia detection using chest radiographs with novel efficientNetV2L model. IEEE Access. 12, 34691\u201334707 (2024).","journal-title":"IEEE Access."},{"key":"44441_CR6","doi-asserted-by":"publisher","first-page":"35716","DOI":"10.1109\/ACCESS.2024.3371151","volume":"12","author":"TS Arulananth","year":"2024","unstructured":"Arulananth, T. S. et al. Classification of paediatric pneumonia using modified DenseNet-121 deep-learning model. IEEE Access. 12, 35716\u201335727 (2024).","journal-title":"IEEE Access."},{"key":"44441_CR7","doi-asserted-by":"publisher","first-page":"328","DOI":"10.3390\/jpm14030328","volume":"14","author":"D Jaganathan","year":"2024","unstructured":"Jaganathan, D., Balsubramaniam, S., Sureshkumar, V. & Dhanasekaran, S. concatenated modified LeNet approach for classifying pneumonia images. J. Pers. Med. 14, 328 (2024).","journal-title":"J. Pers. Med."},{"key":"44441_CR8","doi-asserted-by":"publisher","first-page":"42839","DOI":"10.1109\/ACCESS.2023.3270774","volume":"11","author":"VTQ Huy","year":"2023","unstructured":"Huy, V. T. Q. & Lin, C. M. An improved densenet deep neural network model for tuberculosis detection using chest X-ray images. IEEE Access. 11, 42839\u201342849 (2023).","journal-title":"IEEE Access."},{"key":"44441_CR9","doi-asserted-by":"publisher","first-page":"P10011","DOI":"10.1088\/1748-0221\/15\/10\/P10011","volume":"15","author":"SH Yoo","year":"2020","unstructured":"Yoo, S. H. et al. Study on the TB and non-TB diagnosis using two-step deep learning-based binary classifier. J. Instrum. 15, P10011\u2013P10011 (2020).","journal-title":"J. Instrum."},{"key":"44441_CR10","doi-asserted-by":"publisher","first-page":"62110","DOI":"10.1109\/ACCESS.2022.3182498","volume":"10","author":"M Yaseliani","year":"2022","unstructured":"Yaseliani, M., Hamadani, A. Z., Maghsoodi, A. I. & Mosavi, A. Pneumonia detection proposing a hybrid deep convolutional neural network based on two parallel visual geometry group architectures and machine learning classifiers. IEEE Access. 10, 62110\u201362128 (2022).","journal-title":"IEEE Access."},{"key":"44441_CR11","doi-asserted-by":"publisher","first-page":"1344","DOI":"10.1109\/JBHI.2019.2931395","volume":"24","author":"G Altan","year":"2020","unstructured":"Altan, G., Kutlu, Y. & Allahverdi, N. Deep learning on computerized analysis of chronic obstructive pulmonary disease. IEEE J. Biomed. Health Inf. 24, 1344\u20131350 (2020).","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"44441_CR12","doi-asserted-by":"publisher","first-page":"1743","DOI":"10.1007\/s11042-021-11409-7","volume":"81","author":"S Singh","year":"2022","unstructured":"Singh, S. & Tripathi, B. K. Pneumonia classification using quaternion deep learning. Multimed Tools Appl. 81, 1743\u20131764 (2022).","journal-title":"Multimed Tools Appl."},{"key":"44441_CR13","doi-asserted-by":"publisher","first-page":"517","DOI":"10.3390\/e22050517","volume":"22","author":"AM Hasan","year":"2020","unstructured":"Hasan, A. M. et al. Classification of Covid-19 coronavirus, pneumonia and healthy lungs in CT scans using q-deformed entropy and deep learning features. Entropy 22, 517 (2020).","journal-title":"Entropy"},{"key":"44441_CR14","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1002\/ima.22427","volume":"30","author":"RS Chithra","year":"2020","unstructured":"Chithra, R. S. & Jagatheeswari, P. Severity detection and infection level identification of tuberculosis using deep learning. Int. J. Imaging Syst. Technol. 30, 994\u20131011 (2020).","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"44441_CR15","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/s42979-021-00695-5","volume":"2","author":"A Shelke","year":"2021","unstructured":"Shelke, A. et al. Chest X-ray classification using deep learning for automated COVID-19 screening. SN Comput. Sci. 2, 300 (2021).","journal-title":"SN Comput. Sci."},{"key":"44441_CR16","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1007\/s00530-021-00826-1","volume":"28","author":"V Ravi","year":"2022","unstructured":"Ravi, V., Narasimhan, H., Chakraborty, C. & Pham, T. D. Deep learning-based meta-classifier approach for COVID-19 classification using CT scan and chest X-ray images. Multimed Syst. 28, 1401\u20131415 (2022).","journal-title":"Multimed Syst."},{"key":"44441_CR17","doi-asserted-by":"publisher","first-page":"1391","DOI":"10.1016\/j.bbe.2020.08.008","volume":"40","author":"G Jain","year":"2020","unstructured":"Jain, G., Mittal, D., Thakur, D. & Mittal, M. K. A deep learning approach to detect Covid-19 coronavirus with X-Ray images. Biocybern Biomed. Eng. 40, 1391\u20131405 (2020).","journal-title":"Biocybern Biomed. Eng."},{"key":"44441_CR18","doi-asserted-by":"publisher","first-page":"104961","DOI":"10.1016\/j.compbiomed.2021.104961","volume":"139","author":"N Faruqui","year":"2021","unstructured":"Faruqui, N. et al. LungNet: A hybrid deep-CNN model for lung cancer diagnosis using CT and wearable sensor-based medical IoT data. Comput. Biol. Med. 139, 104961 (2021).","journal-title":"Comput. Biol. Med."},{"key":"44441_CR19","doi-asserted-by":"publisher","first-page":"100195","DOI":"10.1016\/j.health.2023.100195","volume":"3","author":"S Wankhade","year":"2023","unstructured":"Wankhade, S. A novel hybrid deep learning method for early detection of lung cancer using neural networks. Healthc. Analytics. 3, 100195 (2023).","journal-title":"Healthc. Analytics"},{"key":"44441_CR20","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.2174\/1573405617666210204210500","volume":"17","author":"N Ayd\u0131n","year":"2021","unstructured":"Ayd\u0131n, N. et al. Detection of lung cancer on computed tomography using artificial intelligence applications developed by deep learning methods and the contribution of deep learning to the classification of lung carcinoma. Curr. Med. Imaging Former. Curr. Med. Imaging Reviews. 17, 1137\u20131141 (2021).","journal-title":"Curr. Med. Imaging Former. Curr. Med. Imaging Reviews"},{"key":"44441_CR21","first-page":"100588","volume":"24","author":"R Pandian","year":"2022","unstructured":"Pandian, R., Vedanarayanan, V., Ravi Kumar, D. N. S. & Rajakumar, R. Detection and classification of lung cancer using CNN and Google net. Measurement: Sens. 24, 100588 (2022).","journal-title":"Measurement: Sens."},{"key":"44441_CR22","doi-asserted-by":"publisher","first-page":"3266","DOI":"10.1158\/1078-0432.CCR-18-2495","volume":"25","author":"Y Xu","year":"2019","unstructured":"Xu, Y. et al. Deep Learning predicts lung cancer treatment response from serial medical imaging. Clin. Cancer Res. 25, 3266\u20133275 (2019).","journal-title":"Clin. Cancer Res."},{"key":"44441_CR23","doi-asserted-by":"publisher","first-page":"103819","DOI":"10.1016\/j.media.2025.103819","volume":"107","author":"X Li","year":"2026","unstructured":"Li, X. et al. Knowledge distillation and teacher\u2013student learning in medical imaging: Comprehensive overview, pivotal role, and future directions. Med. Image Anal. 107, 103819 (2026).","journal-title":"Med. Image Anal."},{"key":"44441_CR24","doi-asserted-by":"publisher","first-page":"102995","DOI":"10.1016\/j.inffus.2025.102995","volume":"118","author":"X Li","year":"2025","unstructured":"Li, X. et al. Vision-Language Models in medical image analysis: From simple fusion to general large models. Inform. Fusion. 118, 102995 (2025).","journal-title":"Inform. Fusion"},{"key":"44441_CR25","doi-asserted-by":"publisher","first-page":"717","DOI":"10.3390\/diagnostics15060717","volume":"15","author":"S Muksimova","year":"2025","unstructured":"Muksimova, S., Umirzakova, S., Baltayev, J. & Cho, Y. I. Multi-modal fusion and longitudinal analysis for alzheimer\u2019s disease classification using deep learning. Diagnostics 15, 717 (2025).","journal-title":"Diagnostics"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44441-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44441-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44441-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T20:27:03Z","timestamp":1781641623000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44441-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,19]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["44441"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-44441-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,19]]},"assertion":[{"value":"7 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"14141"}}