{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T10:04:40Z","timestamp":1790071480424,"version":"4.0.1"},"reference-count":36,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T00:00:00Z","timestamp":1789862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Accurate differentiation of benign and malignant lung nodules in computed tomography (CT) is important for early lung cancer diagnosis and reliable clinical decision-making. Many existing deep learning methods emphasize either nodule-centred morphology or broader anatomical context and provide limited insight into the radiological information represented by the model. This study proposes a Dual-Scale Hybrid Concept Bottleneck Network (DS-HCBN) for explainable 3D lung nodule malignancy classification. The framework processes a local nodule-centred patch and a larger contextual patch using a shared residual 3D convolutional encoder and a lightweight contextual Transformer. The resulting representations are integrated through gated cross-attention, while eight radiological attributes are learned as supervised intermediate representations within the hybrid classifier. The model was developed on LIDC-IDRI using a leakage-controlled patient-wise split and evaluated on a held-out internal test set. External evaluation was performed on the publicly annotated LNDb cohort using the same frozen model without retraining or fine-tuning. On the LIDC-IDRI internal test set, DS-HCBN achieved 87.34% accuracy, an F1-score of 80.39%, and a ROC-AUC of 94.35%. On LNDb, the model achieved 80.41% accuracy and a ROC-AUC of 78.65%. These results show strong internal discrimination but a clear reduction in cross-dataset performance. The findings support the use of local morphology, anatomical context, and radiological concept supervision for concept-guided lung nodule classification, while highlighting the need for improved domain generalization before broader clinical application.<\/jats:p>","DOI":"10.3390\/jimaging12090455","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T08:17:54Z","timestamp":1790065074000},"page":"455","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-Scale Hybrid Concept Bottleneck Network for Explainable 3D Lung Nodule Malignancy Classification in CT Imaging"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2252-9833","authenticated-orcid":false,"given":"Ahmad","family":"Ali","sequence":"first","affiliation":[{"name":"Department of Computer Science, COMSATS University Islamabad, Lahore 54000, Pakistan"},{"name":"Department of Artificial Intelligence, The University of Lahore, Lahore 54000, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5324-2041","authenticated-orcid":false,"given":"Muhammad Aksam","family":"Iftikhar","sequence":"additional","affiliation":[{"name":"Department of Computer Science, COMSATS University Islamabad, Lahore 54000, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"}]},{"given":"Ghulam","family":"Farooque","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Technology, The University of Lahore, Lahore 54000, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"software","vocabulary":"credit"}]},{"given":"Allah Bux","family":"Sargano","sequence":"additional","affiliation":[{"name":"Department of Linguistics, Literary and Aesthetic Studies, University of Bergen, 5007 Bergen, Norway"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"96317","DOI":"10.1109\/ACCESS.2025.3572423","article-title":"An End-to-End Concatenated CNN Attention Model for the Classification of Lung Cancer with XAI Techniques","volume":"13","author":"Haque","year":"2025","journal-title":"IEEE Access"},{"key":"ref_2","first-page":"229","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"104305","DOI":"10.1016\/j.medengphy.2025.104305","article-title":"A multi-attention deep architecture to stratify lung nodule malignancy from CT scans","volume":"137","author":"Moreno","year":"2025","journal-title":"Med. Eng. Phys."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"36047","DOI":"10.1007\/s11042-025-20627-2","article-title":"Enhancing lung cancer diagnostic accuracy and reliability with LCDViT: An expressly developed vision transformer model featuring explainable AI","volume":"84","author":"Satsangi","year":"2025","journal-title":"Multimed. Tools Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"113854","DOI":"10.1016\/j.knosys.2025.113854","article-title":"LungCT-NET: An explainable transfer learning-based robust ensemble model for lung cancer diagnosis","volume":"324","author":"Noman","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"76773","DOI":"10.1007\/s11042-024-18381-y","article-title":"Enhancing the detection of airway disease by applying deep learning and explainable artificial intelligence","volume":"83","author":"Koul","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"15330338251370239","DOI":"10.1177\/15330338251370239","article-title":"Cost-Efficient Early Diagnostic Tool for Lung Cancer: Explainable AI in Clinical Systems","volume":"24","author":"Sebastian","year":"2025","journal-title":"Technol. Cancer Res. Treat."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/s42979-022-01032-0","article-title":"Improving deep neural network interpretation for neuroimaging using multivariate modeling","volume":"3","author":"Williamson","year":"2022","journal-title":"SN Comput. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"101805","DOI":"10.1016\/j.inffus.2023.101805","article-title":"Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence","volume":"99","author":"Ali","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_10","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_11","first-page":"1097","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going Deeper with Convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 22\u201325). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_14","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"104930","DOI":"10.1016\/j.bspc.2023.104930","article-title":"An ensemble method for the detection and classification of lung cancer using Computed Tomography images utilizing a capsule network with Visual Geometry Group","volume":"85","author":"Bushara","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2987","DOI":"10.1038\/s41598-023-29656-z","article-title":"Deep learning ensemble 2D CNN approach towards the detection of lung cancer","volume":"13","author":"Shah","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1080\/03091902.2020.1853837","article-title":"Classification of malignant lung cancer using deep learning","volume":"45","author":"Kumar","year":"2021","journal-title":"J. Med. Eng. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"88323","DOI":"10.1007\/s11042-024-19098-8","article-title":"Transfer learning-based classification model for the Computed Tomography scan pulmonary images","volume":"83","author":"Bishnoi","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"100316","DOI":"10.1016\/j.health.2024.100316","article-title":"A novel deep learning architecture for lung cancer detection and diagnosis from computed tomography image analysis","volume":"5","author":"Crasta","year":"2024","journal-title":"Healthc. Anal."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"118672","DOI":"10.1016\/j.eswa.2022.118672","article-title":"An attentive and adaptive 3D CNN for automatic pulmonary nodule detection in CT image","volume":"211","author":"Zhao","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3860","DOI":"10.1109\/JBHI.2022.3171851","article-title":"Self-supervised transfer learning based on domain adaptation for benign-malignant lung nodule classification on thoracic CT","volume":"26","author":"Huang","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1905","DOI":"10.1002\/mp.16221","article-title":"3D multi-view squeeze-and-excitation convolutional neural network for lung nodule classification","volume":"50","author":"Yang","year":"2023","journal-title":"Med. Phys."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"114645","DOI":"10.1016\/j.asoc.2026.114645","article-title":"3D-NoduleNet: A comprehensive framework for benign and malignant pulmonary nodule classification","volume":"191","author":"Yu","year":"2026","journal-title":"Appl. Soft Comput."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, S., Wang, S., Wang, Q., and Luo, J. (2023, January 24\u201326). Classification of Benign and Malignant Pulmonary Nodules Based on Mixed Features. Proceedings of the 2023 42nd Chinese Control Conference (CCC), Tianjin, China.","DOI":"10.23919\/CCC58697.2023.10240557"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"108505","DOI":"10.1016\/j.compbiomed.2024.108505","article-title":"Nodule-CLIP: Lung nodule classification based on multi-modal contrastive learning","volume":"175","author":"Sun","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Saboor, A., Li, J.P., Haq, A.U., Khan, S., Tabassum, A., Haq, A., and Ahmad, S. (2024, January 14\u201316). Deep learning model for lung cancer detection. Proceedings of the 2024 21st International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), Chengdu, China.","DOI":"10.1109\/ICCWAMTIP64812.2024.10873732"},{"key":"ref_27","first-page":"100492","article-title":"Enhancing lung abnormalities detection and classification using a Deep Convolutional Neural Network and GRU with explainable AI: A promising approach for accurate diagnosis","volume":"14","author":"Islam","year":"2023","journal-title":"Mach. Learn. Appl."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ahammed, S.Z., Baskar, R., and Nalinipriya, G. (2024, January 19\u201320). Advanced Deep Learning Framework for Automated Lung Cancer Detection Using DeepResNet. Proceedings of the 2024 IEEE 6th International Conference on Cybernetics, Cognition and Machine Learning Applications (ICCCMLA), Hamburg, Germany.","DOI":"10.1109\/ICCCMLA63077.2024.10871810"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"6","DOI":"10.60084\/ijcr.v2i1.150","article-title":"Explainable artificial intelligence in medical imaging: A case study on enhancing lung cancer detection through CT images","volume":"2","author":"Noviandy","year":"2024","journal-title":"Indones. J. Case Rep."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"107879","DOI":"10.1016\/j.cmpb.2023.107879","article-title":"DeepXplainer: An interpretable deep learning based approach for lung cancer detection using explainable artificial intelligence","volume":"243","author":"Wani","year":"2024","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"104918","DOI":"10.1016\/j.imavis.2024.104918","article-title":"Enhancing lung abnormalities diagnosis using hybrid DCNN-ViT-GRU model with explainable AI: A deep learning approach","volume":"142","author":"Islam","year":"2024","journal-title":"Image Vis. Comput."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"100499","DOI":"10.1016\/j.dajour.2024.100499","article-title":"An explainable artificial intelligence model for multiple lung diseases classification from chest X-ray images using fine-tuned transfer learning","volume":"12","author":"Mahamud","year":"2024","journal-title":"Decis. Anal. J."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"105646","DOI":"10.1016\/j.bspc.2023.105646","article-title":"Towards reliable and explainable AI model for pulmonary nodule diagnosis","volume":"88","author":"Wang","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Rafferty, A., Ramaesh, R., and Rajan, A. (2025, January 18\u201321). Leveraging Expert Input for Robust and Explainable AI-Assisted Lung Cancer Detection in Chest X-rays. Proceedings of the 2025 IEEE 13th International Conference on Healthcare Informatics (ICHI), Rende, Italy.","DOI":"10.1109\/ICHI64645.2025.00071"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1118\/1.3528204","article-title":"The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A completed reference database of lung nodules on CT scans","volume":"38","author":"Armato","year":"2011","journal-title":"Med. Phys."},{"key":"ref_36","first-page":"3697","article-title":"LNDb: A Lung Nodule Database on Computed Tomography","volume":"47","author":"Pedrosa","year":"2020","journal-title":"Med. Phys."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/9\/455\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T09:21:12Z","timestamp":1790068872000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/9\/455"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,20]]},"references-count":36,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["jimaging12090455"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12090455","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,20]]}}}