{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T10:56:13Z","timestamp":1766400973661,"version":"3.46.0"},"reference-count":80,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Int J Imaging Syst Tech"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>The increasing global burden of lung diseases necessitates the development of improved diagnostic tools. According to the WHO, hundreds of millions of individuals worldwide are currently affected by various forms of lung disease. The rapid advancement of artificial neural networks has revolutionized lung disease diagnosis, enabling the development of highly effective detection and classification systems. This article presents dual channel neural networks in image feature extraction based on classical CNN and vision transformers for multi\u2010label lung disease diagnosis. Two separate subnetworks are employed to capture both global and local feature representations, thereby facilitating the extraction of more informative and discriminative image features. The global network analyzes all\u2010organ regions, while the local network simultaneously focuses on multiple single\u2010organ regions. We then apply a novel feature fusion operation, leveraging a multi\u2010head attention mechanism to weight global features according to the significance of localized features. Through this multi\u2010channel approach, the framework is designed to identify complicated and subtle features within images, which often go unnoticed by the human eye. Evaluation on the ChestX\u2010ray14 benchmark dataset demonstrates that our hybrid model consistently outperforms established state\u2010of\u2010the\u2010art architectures, including ResNet\u201050, DenseNet\u2010121, and CheXNet, by achieving significantly higher AUC scores across multiple thoracic disease classification tasks. By incorporating test\u2010time augmentation, the model achieved an average accuracy of 95.7% and a specificity of 99%. The experimental findings indicated that our model attained an average testing AUC of 87%. In addition, our method tackles a more practical clinical problem, and preliminary results suggest its feasibility and effectiveness. It could assist clinicians in making timely decisions about lung diseases.<\/jats:p>","DOI":"10.1002\/ima.70227","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T19:31:45Z","timestamp":1760556705000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Hybrid Deep Learning Approach for Enhanced Classification of Lung Pathologies From Chest X\u2010Ray"],"prefix":"10.1002","volume":"35","author":[{"given":"Samira","family":"Sajed","sequence":"first","affiliation":[{"name":"Artificial Intelligence and Intelligent Healthcare Lab, Artificial Intelligence and Data Mining Research Group, ICT Research Institute, Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University  Bushehr Iran"},{"name":"ADiT\u2010LAB Instituto Polit\u00e9cnico de Viana do Castelo  Viana do Castelo Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5396-6517","authenticated-orcid":false,"given":"Habib","family":"Rostami","sequence":"additional","affiliation":[{"name":"Artificial Intelligence and Intelligent Healthcare Lab, Artificial Intelligence and Data Mining Research Group, ICT Research Institute, Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University  Bushehr Iran"},{"name":"Computer Engineering Department, Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University  Bushehr Iran"}]},{"given":"Jorge Esparteiro","family":"Garcia","sequence":"additional","affiliation":[{"name":"ADiT\u2010LAB Instituto Polit\u00e9cnico de Viana do Castelo  Viana do Castelo Portugal"},{"name":"Institute for Systems and Computer Engineering, Technology and Science INESC TEC  Porto Porto Portugal"}]},{"given":"Ahmad","family":"Keshavarz","sequence":"additional","affiliation":[{"name":"IoT and Signal Processing Research Group, ICT Research Institute, Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University  Bushehr Iran"}]},{"given":"Andreia","family":"Teixeira","sequence":"additional","affiliation":[{"name":"ADiT\u2010LAB Instituto Polit\u00e9cnico de Viana do Castelo  Viana do Castelo Portugal"},{"name":"MEDCIDS\u2014Department of Community Medicine, Information and Decision in Health, Faculty of Medicine University of Porto  Porto Portugal"},{"name":"CINTESIS@RISE\u2014Center for Health Technology and Services Research, Faculty of Medicine University of Porto  Porto Portugal"}]}],"member":"311","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-65981-7_12"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32606-7_3"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.02.010"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.54216\/JAIM.090104"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/su15075949"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1364\/BOE.10.006204"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00417-018-04224-8"},{"key":"e_1_2_9_9_1","first-page":"181","volume-title":"Intelligent Robotics and Applications: 15th International Conference, ICIRA","author":"Yu D.","year":"2022"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.3390\/biom10081123"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5714-1"},{"key":"e_1_2_9_12_1","article-title":"Optimized Deep Learning Ensemble for Accurate Oral Cancer Detection Using CNNs and Metaheuristic Tuning","volume":"11","author":"Dharani R.","year":"2025","journal-title":"Intelligent Medicine"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-025-00771-6"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics10060417"},{"key":"e_1_2_9_15_1","unstructured":"P.Rajpurkar J.Irvin K.Zhu et\u00a0al. \u201cChexnet: Radiologist\u2010Level Pneumonia Detection on Chest x\u2010Rays With Deep Learning \u201darXiv1711.05225 2017."},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.12.010"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2021.018179"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110817"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12112892"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1152\/ajplung.00261.2022"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.04.016"},{"key":"e_1_2_9_22_1","doi-asserted-by":"crossref","unstructured":"B.Jamshidi N.Ghorbani andM.Rostamy\u2010Malkhalifeh \u201cOptimizing Lung Cancer Detection in CT Imaging: A Wavelet Multi\u2010Layer Perceptron (WMLP) Approach Enhanced by Dragonfly Algorithm (DA) \u201darXiv2408.15355 2024.","DOI":"10.4236\/ojmi.2025.153010"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/0146-664X(73)90005-1"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12539-023-00562-2"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-023-00801-4"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.22266\/ijies2021.0831.15"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916849"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/4168538"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2020.100391"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106646"},{"key":"e_1_2_9_31_1","first-page":"2936","article-title":"Multiple Lung Diseases Classification From Chest X\u2010Ray Images Using Deep Learning Approach","volume":"10","author":"Yimer F.","year":"2021","journal-title":"International Journal"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3310429"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13122038"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3298955"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.3390\/e24030313"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3196660"},{"issue":"3","key":"e_1_2_9_38_1","first-page":"665","article-title":"Classification and Predictions of Lung Diseases From Chest x\u2010Rays Using MobileNet","volume":"12","author":"Sivasamy J.","year":"2020","journal-title":"International Journal of Analytical and Experimental Modal Analysis"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20915-5_25"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.3390\/su15075930"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinimag.2022.11.003"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2021.11.004"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.541"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2019.04.031"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3269068"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.3390\/e23060653"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11062751"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-42294-8"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.113"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1002686"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-019-00180-9"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.3390\/app9194130"},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3020802"},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2875406"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109266"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.106924"},{"key":"e_1_2_9_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15937-4_65"},{"key":"e_1_2_9_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105605"},{"key":"e_1_2_9_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04570-z"},{"key":"e_1_2_9_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122147"},{"key":"e_1_2_9_61_1","doi-asserted-by":"publisher","DOI":"10.54216\/MOR.030204"},{"key":"e_1_2_9_62_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12040915"},{"key":"e_1_2_9_63_1","first-page":"2097","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Wang X.","year":"2017"},{"key":"e_1_2_9_64_1","first-page":"234","volume-title":"Medical Image Computing and Computer\u2010Assisted Intervention\u2013MICCAI","author":"Ronneberger O.","year":"2015"},{"key":"e_1_2_9_65_1","doi-asserted-by":"publisher","DOI":"10.32604\/csse.2023.025195"},{"key":"e_1_2_9_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2019.105162"},{"key":"e_1_2_9_67_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.01.023"},{"key":"e_1_2_9_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_9_69_1","unstructured":"A.Dosovitskiy L.Beyer A.Kolesnikov et\u00a0al. \u201cAn Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale \u201darXiv 2010.11929 2020."},{"key":"e_1_2_9_70_1","doi-asserted-by":"publisher","DOI":"10.3390\/su15054543"},{"key":"e_1_2_9_71_1","doi-asserted-by":"crossref","unstructured":"K.Nair A.Deshpande R.Guntuka andA.Patil \u201cAnalysing X\u2010Ray Images to Detect Lung Diseases Using DenseNet\u2010169 Technique \u201d2022.","DOI":"10.2139\/ssrn.4111864"},{"key":"e_1_2_9_72_1","unstructured":"J.\u2010B.Cordonnier A.Loukas andM.Jaggi \u201cMulti\u2010Head Attention: Collaborate Instead of Concatenate \u201darXiv2006.16362 2020."},{"key":"e_1_2_9_73_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.e4483"},{"issue":"1","key":"e_1_2_9_74_1","first-page":"11","article-title":"Test for Significance of Pearson's Correlation Coefficient","volume":"6","author":"Obilor E. I.","year":"2018","journal-title":"International Journal of Innovative Mathematics, Statistics & Energy Policies"},{"key":"e_1_2_9_75_1","first-page":"2980","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Ross T.\u2010Y.","year":"2017"},{"key":"e_1_2_9_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_9_77_1","doi-asserted-by":"publisher","DOI":"10.1148\/51.1.58"},{"key":"e_1_2_9_78_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiographics.19.6.g99no211507"},{"key":"e_1_2_9_79_1","first-page":"558","volume-title":"International Conference on Neural Information Processing","author":"Kimura M.","year":"2021"},{"key":"e_1_2_9_80_1","unstructured":"H.Lu D.Shanmugam H.Suresh andJ.Guttag \u201cImproved Text Classification via Test\u2010Time Augmentation \u201darXiv2206.13607 2022."},{"key":"e_1_2_9_81_1","unstructured":"Q.Guan Y.Huang Z.Zhong Z.Zheng L.Zheng andY.Yang \u201cDiagnose Like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification \u201darXiv1801.09927 2018."}],"container-title":["International Journal of Imaging Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ima.70227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T11:15:07Z","timestamp":1764155707000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/ima.70227"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":80,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1002\/ima.70227"],"URL":"https:\/\/doi.org\/10.1002\/ima.70227","archive":["Portico"],"relation":{},"ISSN":["0899-9457","1098-1098"],"issn-type":[{"type":"print","value":"0899-9457"},{"type":"electronic","value":"1098-1098"}],"subject":[],"published":{"date-parts":[[2025,10,15]]},"assertion":[{"value":"2025-03-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70227"}}