Academic Journal
Multiclass lung cancer detection using a hybrid capsule inspired deep neural network.
| Τίτλος: | Multiclass lung cancer detection using a hybrid capsule inspired deep neural network. |
|---|---|
| Συγγραφείς: | Bhattacharee A; Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University), Pune, Maharashtra, 412115, India. ananya.bhattacharjee@sitpune.edu.in., Bhattacharjee A; Department of Pharmaceutical Sciences, Assam University (A Central University), Silchar, 788011, Assam, India., Swain RP; GITAM School of Pharmacy, GITAM (Deemed to be University), Visakhapatnam, Andhra Pradesh, 530045, India., Sahu RK; Department of Pharmaceutical Sciences, Hemvati Nandan Bahuguna Garhwal University (A Central University), Tehri Garhwal, 249161, Uttarakhand, India. |
| Πηγή: | Scientific reports [Sci Rep] 2026 Apr 22; Vol. 16 (1). Date of Electronic Publication: 2026 Apr 22. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : Nature Publishing Group, copyright 2011- |
| Ιατρικοί όροι (MeSH): | Lung Neoplasms*/diagnostic imaging , Lung Neoplasms*/diagnosis , Classification Algorithms*, Tomography, X-Ray Computed/methods ; Humans ; Convolutional Neural Networks |
| Περίληψη: | Convolutional Neural Networks are widely used in lung cancer detection for more than a decade. However, it suffers from preserving spatial relationships among features, leading to dead units in deeper layers. This is overcome by the capsule network (CapsNet), which estimates various instantaneous parameters. Nevertheless, the dynamic algorithm implemented in CapsNet is prone to computational complexity because of its higher-end matrix multiplication between primary and secondary capsules. In this study, a light weight attention (LWA)-based EfficientNetB0 and Capsule-inspired feature encoding module is proposed to reduce computational complexity. The role of the LWA lies in its filtering capabilities, thus strengthening the important features and reducing the redundancy. This helps the proposed architecture work more effectively without requiring the computationally intensive routing algorithm. The proposed model targets multiclass classification of benign, normal, and malignant computed tomography images. Unlike CapsNet, no decoder network is present in the proposed architecture. Moreover, a simplified matrix multiplication is computed, which results in fewer floating point operations (FLOPs) of 0.01 GFLOPS. Although the proposed model attained 100% F1 score, accuracy, precision, and recall on the test set, the experiments proved that there is no data leakage. These results indicate its potential to support radiologists in lung cancer detection, though its real-world utility requires prospective clinical evaluation. (© 2026. The Author(s).) |
| Competing Interests: | Declarations. Competing interests: The authors declare no competing interests. |
| References: | Siegel, R. L., Giaquinto, A. N. & Jemal, A. Cancer statistics, 2024. CA Cancer J. Clin. https://doi.org/10.3322/caac.21820 (2024). (PMID: 10.3322/caac.2182039352042) Arandhara, A., Bhuyan, P. & Das, B. K. Exploring lung cancer microenvironment: Pathways and nanoparticle-based therapies. Discover. Oncol. 16, 1–25 (2025). Gayap, H. T. & Akhloufi, M. A. Deep machine learning for medical diagnosis, application to lung cancer detection: A review. BioMedInformatics 4, 236–284 (2024). (PMID: 10.3390/biomedinformatics4010015) Al-qaness, M. A. et al. Chest x-ray images for lung disease detection using deep learning techniques: A comprehensive survey. Arch. Comput. Methods Eng. https://doi.org/10.1007/s11831-024-10081-y (2024). (PMID: 10.1007/s11831-024-10081-y) Ramasamy, P., Alabdulkreem, E., Alruwais, N. & Gladis Pushparathi, V. An attention-based neural network for lung cancer classification and gradient in MRI. Automatika 65, 1379–1390 (2024). (PMID: 10.1080/00051144.2024.2376776) Crasta, L. J., Neema, R. & Pais, A. R. A novel deep learning architecture for lung cancer detection and diagnosis from computed tomography image analysis. Healthcare Analytics 5, 100316 (2024). (PMID: 10.1016/j.health.2024.100316) Chen, G. et al. Prediction of chronic kidney disease using adaptive hybridized deep convolutional neural network on the internet of medical things platform. IEEE Access 8, 100497–100508 (2020). (PMID: 10.1109/ACCESS.2020.2995310) Gautam, N., Basu, A. & Sarkar, R. Lung cancer detection from thoracic ct scans using an ensemble of deep learning models. Neural Comput. Appl. 36, 2459–2477 (2024). (PMID: 10.1007/s00521-023-09130-7) Sabour, S., Frosst, N. & Hinton, G. E. Dynamic routing between capsules. Advances in neural information processing systems 30 (2017). Garau, N. & Conci, N. Capsulepose: A variational capsnet for real-time end-to-end 3d human pose estimation. Neurocomputing 523, 81–91 (2023). (PMID: 10.1016/j.neucom.2022.11.097) Mobiny, A. et al. Memory-augmented capsule network for adaptable lung nodule classification. IEEE Transactions on Medical Imaging 40, 2869–2879 (2021). (PMID: 10.1109/TMI.2021.305108933434126) Xu, Y., She, Q., Sun, S., Xi, X. & Du, S. Attribute-enhanced capsule network for pulmonary nodule classification. J. Med. Biol. Eng. 44, 79–89 (2024). (PMID: 10.1007/s40846-024-00846-y) Vijayakumar, S., Aarthy, S., Deepa, D. & Suresh, P. Sustainable framework for automated segmentation and prediction of lung cancer in ct image using capsnet with u-net segmentation. Biomed. Signal Process. Control 99, 106873 (2025). (PMID: 10.1016/j.bspc.2024.106873) Ar, B., Rs, V. K. & Ss, K. Lcd-capsule network for the detection and classification of lung cancer on computed tomography images. Multimedia Tools Appl. 82, 37573–37592 (2023). (PMID: 10.1007/s11042-023-14893-1) Afshar, P. et al. Mixcaps: A capsule network-based mixture of experts for lung nodule malignancy prediction. Pattern Recognit. 116, 107942 (2021). (PMID: 10.1016/j.patcog.2021.107942) Bushara, A., Kumar, R. V. & Kumar, S. Classification of benign and malignancy in lung cancer using capsule networks with dynamic routing algorithm on computed tomography images. Journal of Artificial Intelligence and Technology 4, 40–48 (2024). Afshar, P. et al. 3d-mcn: A 3d multi-scale capsule network for lung nodule malignancy prediction. Sci. Rep. 10, 7948 (2020). (PMID: 10.1038/s41598-020-64824-5324097157224210) Ramana, K. et al. Early prediction of lung cancers using deep saliency capsule and pre-trained deep learning frameworks. Front. Oncol. 12, 886739 (2022). (PMID: 10.3389/fonc.2022.886739357851849247339) Raza, R. et al. Lung-effnet: Lung cancer classification using efficientnet from ct-scan images. Eng. Appl. Artif. Intell. 126, 106902 (2023). (PMID: 10.1016/j.engappai.2023.106902) Reddy, S., Bhuvaneshwari, V., Tikariha, A. K., Amballa, Y. S. & Raj, B. S. S. Automatic pulmonary nodule detection in ct scans using xception, resnet50 and advanced convolutional neural networks models. Int Res J EngTechnol 9, 3226–3237 (2022). Bhattacharjee, A. et al. A multi-class deep learning model for early lung cancer and chronic kidney disease detection using computed tomography images. Front. Oncol. 13, 1193746 (2023). (PMID: 10.3389/fonc.2023.11937463733382510272771) Kareem, H. F. The iq-oth/nccd lung cancer dataset, version 1, retrieved on 1st january, 2025. https://www.kaggle.com/hamdallak/the-iqothnccd-lung-cancer-dataset/metadata (2025). Hammad, M. et al. Explainable AI for lung cancer detection via a custom CNN on CT images. Sci. Rep. 15, 12707 (2025). (PMID: 10.1038/s41598-025-97645-54022315311994823) Al-Kababji, A., Bensaali, F. & Dakua, S. P. Scheduling techniques for liver segmentation: Reducelronplateau vs onecyclelr. In International conference on intelligent systems and pattern recognition, 204–212 (Springer, 2022). Armato, S. G. III. et al. The lung image database consortium (lidc) and image database resource initiative (idri): a completed reference database of lung nodules on ct scans. Medical physics 38, 915–931 (2011). (PMID: 10.1118/1.3528204214527283041807) Hany, M. Chest ct-scan images dataset, version 1, retrieved on 1st may. https://www.https://www.kaggle.com/datasets/mohamedhanyyy/chest-ctscan-images (2025). Mehta, K. et al. Lung nodule classification using biomarkers, volumetric radiomics, and 3D cnns. J. Digit. Imaging 34, 647–666 (2021). (PMID: 10.1007/s10278-020-00417-y335328938329152) Bhattacharjee, A., Shankar, K., Murugan, R. & Goel, T. A powerful transfer learning technique for multiclass classification of lung cancer ct images. In 2022 International Conference on Engineering and Emerging Technologies (ICEET), 1–6 (IEEE, 2022). Choi, J., Seo, H., Im, S. & Kang, M. Attention routing between capsules. In Proceedings of the IEEE/CVF international conference on computer vision workshops, 0–0 (2019). Mazzia, V., Salvetti, F. & Chiaberge, M. Efficient-capsnet: Capsule network with self-attention routing. Sci. Rep. 11, 14634 (2021). (PMID: 10.1038/s41598-021-93977-0342821648290018) Yuan, J. et al. Dpdh-capnet: A novel lightweight capsule network with non-routing for COVID-19 diagnosis using x-ray images. J. Digit. Imaging 36, 988–1000 (2023). (PMID: 10.1007/s10278-023-00791-3368139789946284) |
| Contributed Indexing: | Keywords: Capsule network; Classification; Computed tomography; Lightweight; Lung cancer; Multiclass |
| Entry Date(s): | Date Created: 20260421 Date Completed: 20260615 Latest Revision: 20260726 |
| Update Code: | 20260726 |
| PubMed Central ID: | PMC13269817 |
| DOI: | 10.1038/s41598-026-49378-2 |
| PMID: | 42014820 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 2045-2322 |
|---|---|
| DOI: | 10.1038/s41598-026-49378-2 |