{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T18:58:57Z","timestamp":1785265137003,"version":"3.55.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s11760-026-05524-x","type":"journal-article","created":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:47:28Z","timestamp":1783151248000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Clinically explainable cross-attention CNN\u2013ViT framework for automated multi-class retinal disease screening using OCT"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6919-3028","authenticated-orcid":false,"given":"Sabib","family":"Ahmed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jannatul Ferdus","family":"Aspia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Tanver Rana","family":"Sobur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2379-2253","authenticated-orcid":false,"given":"Md. Khabir Uddin","family":"Ahamed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,4]]},"reference":[{"key":"5524_CR1","doi-asserted-by":"publisher","unstructured":"Hee, M.R., Izatt, J.A., Swanson, E.A., Huang, D., Schuman, J.S., Lin, C.P., Puliafito, C.A., Fujimoto, J.G.: Optical coherence tomography of the human retina. Arch. Ophthalmol. 113, 325\u2013332 (1995). https:\/\/doi.org\/10.1001\/archopht.1995.01100030081025","DOI":"10.1001\/archopht.1995.01100030081025"},{"key":"5524_CR2","doi-asserted-by":"publisher","unstructured":"George, N., Shine, L., Abraham, B., Ramachandran, S.: A two-stage cnn model for the classification and severity analysis of retinal and choroidal diseases in oct images. Int. J. Intell. Netw. 5, 10\u201318 (2024). https:\/\/doi.org\/10.1016\/j.ijin.2024.01.002","DOI":"10.1016\/j.ijin.2024.01.002"},{"key":"5524_CR3","doi-asserted-by":"publisher","first-page":"9171","DOI":"10.1007\/s00521-024-09564-7","volume":"36","author":"G Hemalakshmi","year":"2024","unstructured":"Hemalakshmi, G., Murugappan, M., Sikkandar, M.Y., Begum, S.S., Prakash, N.: Automated retinal disease classification using hybrid transformer model (svit) using optical coherence tomography images. Neural Comput. Appl. 36, 9171\u20139188 (2024). https:\/\/doi.org\/10.1007\/s00521-024-09564-7","journal-title":"Neural Comput. Appl."},{"key":"5524_CR4","doi-asserted-by":"publisher","unstructured":"Kim, J., Tran, L.: Retinal disease classification from oct images using deep learning algorithms. In: 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), pp. 1\u20136 (2021). https:\/\/doi.org\/10.1109\/CIBCB49929.2021.9562919 . IEEE","DOI":"10.1109\/CIBCB49929.2021.9562919"},{"key":"5524_CR5","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2022.876927","volume":"16","author":"Z Ai","year":"2022","unstructured":"Ai, Z., Huang, X., Feng, J., Wang, H., Tao, Y., Zeng, F., Lu, Y.: Fn-oct: disease detection algorithm for retinal optical coherence tomography based on a fusion network. Front. Neuroinform. 16, 876927 (2022). https:\/\/doi.org\/10.3389\/fninf.2022.876927","journal-title":"Front. Neuroinform."},{"key":"5524_CR6","doi-asserted-by":"publisher","unstructured":"Choudhary, A., Ahlawat, S., Urooj, S., Pathak, N., Lay-Ekuakille, A., Sharma, N.: A deep learning-based framework for retinal disease classification. In: Healthcare, vol. 11, p. 212 (2023). https:\/\/doi.org\/10.3390\/healthcare11020212 . MDPI","DOI":"10.3390\/healthcare11020212"},{"key":"5524_CR7","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1167\/tvst.9.2.46","volume":"9","author":"L Wang","year":"2020","unstructured":"Wang, L., Wang, G., Zhang, M., Fan, D., Liu, X., Guo, Y., Wang, R., Lv, B., Lv, C., Wei, J., et al.: An intelligent optical coherence tomography-based system for pathological retinal cases identification and urgent referrals. Transl. Vis. Sci. Technol. 9, 46\u201346 (2020). https:\/\/doi.org\/10.1167\/tvst.9.2.46","journal-title":"Transl. Vis. Sci. Technol."},{"key":"5524_CR8","doi-asserted-by":"publisher","unstructured":"Fan, D., Zhang, C., Lv, B., Wang, L., Wang, G., Wang, M., Lv, C., Xie, G.: Positive-aware lesion detection network with cross-scale feature pyramid for oct images. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, vol. 12265, pp. 685\u2013693 (2020). https:\/\/doi.org\/10.1007\/978-3-030-59722-1_66 . Springer","DOI":"10.1007\/978-3-030-59722-1_66"},{"key":"5524_CR9","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1007\/s10916-024-02105-8","volume":"48","author":"S Takahashi","year":"2024","unstructured":"Takahashi, S., Sakaguchi, Y., Kouno, N., Takasawa, K., Ishizu, K., Akagi, Y., Aoyama, R., Teraya, N., Bolatkan, A., Shinkai, N., et al.: Comparison of vision transformers and convolutional neural networks in medical image analysis: a systematic review. J. Med. Syst. 48, 84 (2024). https:\/\/doi.org\/10.1007\/s10916-024-02105-8","journal-title":"J. Med. Syst."},{"key":"5524_CR10","doi-asserted-by":"publisher","first-page":"3928","DOI":"10.1007\/s10278-025-01481-y","volume":"38","author":"S Aburass","year":"2025","unstructured":"Aburass, S., Dorgham, O., Al Shaqsi, J., Abu Rumman, M., Al-Kadi, O.: Vision transformers in medical imaging: a comprehensive review of advancements and applications across multiple diseases. J. Imaging Inform. Med. 38, 3928\u20133971 (2025). https:\/\/doi.org\/10.1007\/s10278-025-01481-y","journal-title":"J. Imaging Inform. Med."},{"key":"5524_CR11","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.imed.2022.07.002","volume":"3","author":"K He","year":"2023","unstructured":"He, K., Gan, C., Li, Z., Rekik, I., Yin, Z., Ji, W., Gao, Y., Wang, Q., Zhang, J., Shen, D.: Transformers in medical image analysis. Intell. Med. 3, 59\u201378 (2023). https:\/\/doi.org\/10.1016\/j.imed.2022.07.002","journal-title":"Intell. Med."},{"key":"5524_CR12","doi-asserted-by":"publisher","DOI":"10.2147\/OPTH.S321764","author":"C Chase","year":"2021","unstructured":"Chase, C., Elsawy, A., Eleiwa, T., Ozcan, E., Tolba, M., Abou Shousha, M.: Comparison of autonomous as-oct deep learning algorithm and clinical dry eye tests in diagnosis of dry eye disease. Clin. Ophthalmol. (2021). https:\/\/doi.org\/10.2147\/OPTH.S321764","journal-title":"Clin. Ophthalmol."},{"key":"5524_CR13","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1002\/ima.22673","volume":"32","author":"N Saleh","year":"2022","unstructured":"Saleh, N., Abdel Wahed, M., Salaheldin, A.M.: Transfer learning-based platform for detecting multi-classification retinal disorders using optical coherence tomography images. Int. J. Imaging Syst. Technol. 32, 740\u2013752 (2022). https:\/\/doi.org\/10.1002\/ima.22673","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"5524_CR14","doi-asserted-by":"publisher","unstructured":"Subramanian, M., Shanmugavadivel, K., Naren, O.S., Premkumar, K., Rankish, K.: Classification of retinal oct images using deep learning. In: 2022 International Conference on Computer Communication and Informatics (ICCCI), pp. 1\u20137 (2022). https:\/\/doi.org\/10.1109\/ICCCI54379.2022.9740985 . IEEE","DOI":"10.1109\/ICCCI54379.2022.9740985"},{"key":"5524_CR15","doi-asserted-by":"publisher","first-page":"5393","DOI":"10.3390\/s23125393","volume":"23","author":"E Hassan","year":"2023","unstructured":"Hassan, E., Elmougy, S., Ibraheem, M.R., Hossain, M.S., AlMutib, K., Ghoneim, A., AlQahtani, S.A., Talaat, F.M.: Enhanced deep learning model for classification of retinal optical coherence tomography images. Sensors 23, 5393 (2023). https:\/\/doi.org\/10.3390\/s23125393","journal-title":"Sensors"},{"key":"5524_CR16","doi-asserted-by":"publisher","first-page":"1252295","DOI":"10.3389\/fcomp.2023.1252295","volume":"5","author":"M Elkholy","year":"2024","unstructured":"Elkholy, M., Marzouk, M.A.: Deep learning-based classification of eye diseases using convolutional neural network for oct images. Front. Comput. Sci. 5, 1252295 (2024). https:\/\/doi.org\/10.3389\/fcomp.2023.1252295","journal-title":"Front. Comput. Sci."},{"key":"5524_CR17","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1167\/tvst.13.6.16","volume":"13","author":"C-H Yeh","year":"2024","unstructured":"Yeh, C.-H., Graham, A.D., Stella, X.Y., Lin, M.C.: Enhancing meibography image analysis through artificial intelligence-driven quantification and standardization for dry eye research. Transl. Vision Sci. Technol. 13, 16\u201316 (2024). https:\/\/doi.org\/10.1167\/tvst.13.6.16","journal-title":"Transl. Vision Sci. Technol."},{"key":"5524_CR18","doi-asserted-by":"publisher","unstructured":"Puneet, Kumar, R., Gupta, M.: Optical coherence tomography image based eye disease detection using deep convolutional neural network. Health Inform. Sci. Syst. 10, 13 (2022) https:\/\/doi.org\/10.1007\/s13755-022-00182-y","DOI":"10.1007\/s13755-022-00182-y"},{"key":"5524_CR19","doi-asserted-by":"publisher","unstructured":"Naik, G., Narvekar, N., Agarwal, D., Nandanwar, N., Pande, H.: Eye disease prediction using ensemble learning and attention on oct scans. In: Future of Information and Communication Conference, vol. 919, pp. 21\u201336 (2024). https:\/\/doi.org\/10.1007\/978-3-031-53960-2_3 . Springer","DOI":"10.1007\/978-3-031-53960-2_3"},{"key":"5524_CR20","unstructured":"Naren, O.S.: Retinal OCT Image Classification - C8. Kaggle. Dataset, (2021). https:\/\/doi.org\/10.34740\/KAGGLE\/DSV\/2736749"},{"key":"5524_CR21","doi-asserted-by":"publisher","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"5524_CR22","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020) https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"5524_CR23","doi-asserted-by":"crossref","unstructured":"Chea, N., Nam, Y.: Classification of fundus images based on deep learning for detecting eye diseases. Comput. Mater. Continua 67, 411 (2021) https:\/\/doi.org\/10.32604\/cmc.2021.013390","DOI":"10.32604\/cmc.2021.013390"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05524-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-026-05524-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05524-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T18:17:12Z","timestamp":1785262632000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-026-05524-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":23,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["5524"],"URL":"https:\/\/doi.org\/10.1007\/s11760-026-05524-x","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"30 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Ethics approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors used ChatGPT solely to improve language clarity and readability.","order":3,"name":"Ethics","label":"Declaration of generative AI and AI-assisted technologies in the writing process","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"479"}}