{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T22:53:45Z","timestamp":1781650425303,"version":"3.54.5"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:00:00Z","timestamp":1776211200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T00:00:00Z","timestamp":1780876800000},"content-version":"vor","delay-in-days":54,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The primary driver or cause of cognitive decline and stroke is Cerebral Small Vessel Disease (CSVD), which currently requires neuroimaging tests, which are expensive to obtain and inaccessible in standard clinical settings. Low-cost retinal imaging techniques offer non-invasive assessments that mirror the condition of the brain\u2019s small blood vessels (cerebral microvasculature). State-of-the-art diagnostic methods currently have no accessible, non-invasive, or cost-effective solution to identify CSVD at its earliest stages through visual assessment of retinal biomarkers. This study presents the Retino-Neuro Vision Transformer (RNV-T) framework as a proposed method to detect CSVD utilizing multimodality retinal imaging. The model system comprises five fundamental phases, beginning with Local Vascular Extraction (LVE), followed by Global Transformer-based Encoding (GTE), then proceeding to Graph-Based Relational Learning through Graph-based Convolutional Attention Network (G-CAN) before implementing Local-Global Attention Fusion (LGAF) as well as Optimized training procedures to obtain precise micro-vascular abnormality detection. The diagnostic performance of this model reaches 98.8% accuracy and shows 97.4% sensitivity along with 98.1% specificity, surpassing previous detection approaches. This diagnostic system represents a major leap forward in neuro-ophthalmic care because it enables early prediction of CSVD while expanding medical accessibility through retinal scans that are easy to conduct.<\/jats:p>","DOI":"10.1038\/s41598-026-48421-6","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:17:26Z","timestamp":1776277046000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning for early detection of cerebral small vessel disease using self-supervised graph embeddings and retinal image analysis"],"prefix":"10.1038","volume":"16","author":[{"given":"S.","family":"Nandhini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"K.","family":"Vanitha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,15]]},"reference":[{"key":"48421_CR1","doi-asserted-by":"publisher","first-page":"24","DOI":"10.3390\/ijms21249729","volume":"21","author":"J Litak","year":"2020","unstructured":"Litak, J., Mazurek, M., Kulesza, B., Szmygin, P. & Litak, J., Kamieniak, P. & Grochowski, C. Cerebral small vessel disease. Int. J. Mol. Sci. 21, 24 (2020).","journal-title":"Int. J. Mol. Sci."},{"issue":"1","key":"48421_CR2","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1177\/17474930221144911","volume":"18","author":"HS Markus","year":"2023","unstructured":"Markus, H. S. & de Leeuw, F. E. Cerebral small vessel disease: recent advances and future directions. Int. J. Stroke. 18 (1), 4\u201314 (2023).","journal-title":"Int. J. Stroke"},{"issue":"1","key":"48421_CR3","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1177\/17474930221091879","volume":"18","author":"D Van Brink","year":"2023","unstructured":"Van Brink, D., Hilde, F. N., Doubal & Duering, M. Advanced MRI in cerebral small vessel disease. Int. J. stroke. 18 (1), 28\u201335 (2023).","journal-title":"Int. J. stroke"},{"key":"48421_CR4","doi-asserted-by":"crossref","unstructured":"Chandra, A., Li, W. A., Stone, C. R., Geng, X. & Ding, Y. The cerebral circulation and cerebrovascular disease I: Anatomy. Brain Circ. 3(2), 45\u201356 (2017).","DOI":"10.4103\/bc.bc_10_17"},{"issue":"11","key":"48421_CR5","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.3928\/23258160-20161031-05","volume":"47","author":"M Peres","year":"2016","unstructured":"Peres, M. et al. Comparison of optical coherence tomography angiography and fluorescein angiography for the identification of retinal vascular changes in eyes with diabetic macular edema. Ophthalmic Surg. Lasers Imaging Retina. 47 (11), 1013\u20131019 (2016).","journal-title":"Ophthalmic Surg. Lasers Imaging Retina"},{"issue":"12","key":"48421_CR6","doi-asserted-by":"publisher","first-page":"5314","DOI":"10.3390\/app14125314","volume":"14","author":"M Moriche Carretero","year":"2024","unstructured":"Moriche Carretero, M., Parejo, A. R. S., P\u00e9rez, C. M., Amores, R. R., G\u00f3mez, A. P., & P\u00e9rez, M. B. Study of diagnostic accuracy: fundus photography vs. optical coherence tomography. Appl. Sci. 14 (12), 5314 (2024).","journal-title":"Appl. Sci."},{"key":"48421_CR7","doi-asserted-by":"publisher","first-page":"1393899","DOI":"10.3389\/fneur.2024.1393899","volume":"15","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Zhao, T., Ye, L. & Shentu, S. Y. W. Advances in retinal imaging biomarkers for the diagnosis of cerebrovascular disease. Front. Neurol. 15, 1393899 (2024).","journal-title":"Front. Neurol."},{"key":"48421_CR8","doi-asserted-by":"crossref","unstructured":"Schreiber, S., Scheumann, V., Perosa, V., Vielhaber, S. & Assmann, A. Reader response: serum neurofilament light is sensitive to active cerebral small vessel disease. Neurology 90(24), 1126\u20131126 (2018).","DOI":"10.1212\/WNL.0000000000005672"},{"key":"48421_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40662-018-0120-3","volume":"5","author":"D Qu","year":"2018","unstructured":"Qu, D. et al. Retinal nerve fiber layer (RNFL) integrity and its relations to retinal microvasculature and microcirculation in myopic eyes. Eye Vis. 5, 1\u201310 (2018).","journal-title":"Eye Vis."},{"issue":"4","key":"48421_CR10","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1111\/j.1469-7580.2005.00395.x","volume":"206","author":"N Patton","year":"2005","unstructured":"Patton, N. et al. Retinal vascular image analysis as a potential screening tool for cerebrovascular disease: a rationale based on homology between cerebral and retinal microvasculatures. J. Anat. 206 (4), 319\u2013348 (2005).","journal-title":"J. Anat."},{"key":"48421_CR11","doi-asserted-by":"crossref","unstructured":"Hsieh, Y. Z. et al. Cerebral small vessel disease biomarkers detection on MRI-sensor-based image and deep learning. Sensors 19(11), 2573 (2019).","DOI":"10.3390\/s19112573"},{"key":"48421_CR12","doi-asserted-by":"publisher","first-page":"100179","DOI":"10.1016\/j.cccb.2023.100179","volume":"5","author":"R Li","year":"2023","unstructured":"Li, R. et al. Predicting incident dementia in cerebral small vessel disease: comparison of machine learning and traditional statistical models. Cereb. Circulation-Cognition Behav. 5, 100179 (2023).","journal-title":"Cereb. Circulation-Cognition Behav."},{"issue":"1","key":"48421_CR13","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1186\/s12938-023-01164-1","volume":"22","author":"R Wu","year":"2023","unstructured":"Wu, R. et al. Deep learning based on susceptibility-weighted MR sequence for detecting cerebral microbleeds and classifying cerebral small vessel disease. Biomed. Eng. Online. 22 (1), 99 (2023).","journal-title":"Biomed. Eng. Online"},{"issue":"7","key":"48421_CR14","doi-asserted-by":"publisher","first-page":"e14841","DOI":"10.1111\/cns.14841","volume":"30","author":"X Hu","year":"2024","unstructured":"Hu, X., Liu, L., Xiong, M. & Lu, J. Application of artificial intelligence-based magnetic resonance imaging in diagnosis of cerebral small vessel disease. CNS Neurosci. Ther. 30 (7), e14841 (2024).","journal-title":"CNS Neurosci. Ther."},{"key":"48421_CR15","doi-asserted-by":"crossref","unstructured":"Ji, C. et al. Predicting cerebral small vessel disease through retinal scans and demographic data with Bayesian feature selection. In Medical Imaging 2024: Computer-Aided Diagnosis, vol. 12927, 830\u2013837. SPIE, (2024).","DOI":"10.1117\/12.3006453"},{"key":"48421_CR16","doi-asserted-by":"crossref","unstructured":"Wang, Q. et al. Distinctive Imaging characteristics of retinal and cerebral vessels between central and branch retinal vein occlusion by MRI and AI-Based image analyzer. Diagnostics 14(3), 267 (2024).","DOI":"10.3390\/diagnostics14030267"},{"key":"48421_CR17","doi-asserted-by":"crossref","unstructured":"Zhang, Z. et al. Quantitative analysis of multimodal MRI Markers and Clinical risk factors for cerebral small vessel disease based on deep learning. Int. J. Gen. Med. : 739\u2013750. (2024).","DOI":"10.2147\/IJGM.S446531"},{"issue":"12","key":"48421_CR18","doi-asserted-by":"publisher","first-page":"108070","DOI":"10.1016\/j.jstrokecerebrovasdis.2024.108070","volume":"33","author":"Y Zhuo","year":"2024","unstructured":"Zhuo, Y. et al. Evaluating retinal blood vessels for predicting white matter hyperintensities in ischemic stroke: A deep learning approach. J. Stroke Cerebrovasc. Dis. 33 (12), 108070 (2024).","journal-title":"J. Stroke Cerebrovasc. Dis."},{"issue":"1","key":"48421_CR19","first-page":"1989","volume":"14","author":"A Safar","year":"2023","unstructured":"Safar, A., Abdulrahman, D. M., Salih & Asim, M. Murshid. Pattern recognition using the multi-layer perceptron (MLP) for medical disease: A survey. Int. J. Nonlinear Anal. Appl. 14 (1), 1989\u20131998 (2023).","journal-title":"Int. J. Nonlinear Anal. Appl."},{"key":"48421_CR20","doi-asserted-by":"crossref","unstructured":"Johnson, R. C. Hadamard products of matrices. Linear Multilinear Algebra 1(4), 295\u2013307 (1974).","DOI":"10.1080\/03081087408817030"},{"key":"48421_CR21","doi-asserted-by":"crossref","unstructured":"Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. Transformers in vision: A survey. ACM Comput. Surveys (CSUR) 54(10s), 1\u201341 (2022).","DOI":"10.1145\/3505244"},{"key":"48421_CR22","doi-asserted-by":"crossref","unstructured":"Li, J. et al. Lei Lei, and Spatially adaptive self-supervised learning for real-world image denoising. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9914\u20139924. (2023).","DOI":"10.1109\/CVPR52729.2023.00956"},{"issue":"1","key":"48421_CR23","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1109\/COMST.2023.3330910","volume":"26","author":"X Liu","year":"2023","unstructured":"Liu, X., Deng, Y., Nallanathan, A. & Mehdi Bennis. Federated learning and meta learning: Approaches, applications, and directions. IEEE Commun. Surv. Tutorials. 26 (1), 571\u2013618 (2023).","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"48421_CR24","doi-asserted-by":"crossref","unstructured":"Ravikumar, M., Rachana, P. G., Shivaprasad, B. J. & Guru, D. S. Enhancement of mammogram images using CLAHE and bilateral filter approaches. In Cybernetics, Cognition and Machine Learning Applications: Proceedings of ICCCMLA 2020, pp. 261\u2013271. Springer Singapore, (2021).","DOI":"10.1007\/978-981-33-6691-6_29"},{"issue":"1","key":"48421_CR25","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.infrared.2005.04.006","volume":"48","author":"M Zeng","year":"2006","unstructured":"Zeng, M., Li, J. & Zhang, P. The design of top-hat morphological filter and application to infrared target detection. Infrared Phys. Technol. 48 (1), 67\u201376 (2006).","journal-title":"Infrared Phys. Technol."},{"key":"48421_CR26","doi-asserted-by":"crossref","unstructured":"Kwon, J., Choi, J. A. & Kim, J. & La, T. Y. Ganglion cell-inner plexiform layer, peripapillary retinal nerve fiber layer, and macular thickness in eyes with myopic \u03b2\u2010zone parapapillary atrophy. J. Ophthalmol. 3746791 (2016).","DOI":"10.1155\/2016\/3746791"},{"key":"48421_CR27","doi-asserted-by":"publisher","unstructured":"Samiksha, P. et al. Retinal Fundus Multi-disease Image Dataset (RFMiD), IEEE Dataport, https:\/\/doi.org\/10.21227\/s3g7-st65.","DOI":"10.21227\/s3g7-st65"},{"key":"48421_CR28","doi-asserted-by":"publisher","unstructured":"Li, M., Yuan, S. & Chen, Q. OCTA-500. IEEE Dataport. December 23 https:\/\/doi.org\/10.1016\/j.media.2024.103092 (2019).","DOI":"10.1016\/j.media.2024.103092"},{"key":"48421_CR29","doi-asserted-by":"crossref","unstructured":"Li, M., Liu, Q., & Chen, Q. OCTA-500: A Retinal dataset for optical coherence tomography angiography study. Med. Image. Anal. 103092 (2024).","DOI":"10.1016\/j.media.2024.103092"},{"issue":"11","key":"48421_CR30","doi-asserted-by":"publisher","first-page":"3343","DOI":"10.1109\/TMI.2020.2992244","volume":"39","author":"M Li","year":"2020","unstructured":"Li, M. et al. Image projection network: 3D to 2D image segmentation in OCTA images. IEEE Trans. Med. Imaging. 39 (11), 3343\u20133354 (2020).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"48421_CR31","doi-asserted-by":"publisher","unstructured":"iMED, ROSE: Retinal OCT-Angiography segmentation dataset. IEEE Trans. Med. Imaging. Zenodo https:\/\/doi.org\/10.5281\/zenodo.12775880 (2021).","DOI":"10.5281\/zenodo.12775880"},{"key":"48421_CR32","doi-asserted-by":"crossref","unstructured":"Ding, L. et al. A novel deep learning pipeline for retinal vessel detection in fluorescein angiography. IEEE Trans. Image Proc. 29(1), 6561\u20136573 (2020).","DOI":"10.1109\/TIP.2020.2991530"},{"key":"48421_CR33","doi-asserted-by":"publisher","unstructured":"Li, D. et al. RECOVERY-FA19: Ultra-widefield fluorescein angiography vessel detection dataset. IEEE Dataport. https:\/\/doi.org\/10.21227\/m9yw-xs04 (2019).","DOI":"10.21227\/m9yw-xs04"},{"key":"48421_CR34","doi-asserted-by":"crossref","unstructured":"Ji, C. et al. Predicting cerebral small vessel disease through retinal scans and demographic data with Bayesian feature selection. In Medical Imaging 2024: Computer-Aided Diagnosis, vol. 12927, 830\u2013837. SPIE, (2024).","DOI":"10.1117\/12.3006453"},{"issue":"10","key":"48421_CR35","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1016\/S1474-4422(25)00270-4","volume":"24","author":"X Montalban","year":"2025","unstructured":"Montalban, X. et al. Diagnosis of multiple sclerosis: 2024 revisions of the McDonald criteria. Lancet Neurol. 24 (10), 850\u2013865 (2025).","journal-title":"Lancet Neurol."},{"issue":"10","key":"48421_CR36","doi-asserted-by":"publisher","first-page":"2390","DOI":"10.3390\/biomedicines10102390","volume":"10","author":"G Cennamo","year":"2022","unstructured":"Cennamo, G. et al. Correlation between retinal vascularization and disease aggressiveness in amyotrophic lateral sclerosis. Biomedicines 10(10), 2390 (2022).","journal-title":"Biomedicines"},{"issue":"1","key":"48421_CR37","first-page":"193","volume":"28","author":"KM Raghunath","year":"2025","unstructured":"Raghunath, K. M., Karthick, B., Unhelkar, S., Siva Shankar & Chakrabarti, P. Statistical Assessment of an Interpretable AI Framework for Improved Disease Diagnosis through Medical Images. J. Stat. Manage. Syst. 28 (1), 193\u2013204 (2025).","journal-title":"J. Stat. Manage. Syst."},{"key":"48421_CR38","doi-asserted-by":"publisher","first-page":"34435","DOI":"10.1109\/access.2025.3543577","volume":"13","author":"V Vinoth Kumar","year":"2025","unstructured":"Vinoth Kumar, V., Karthick Raghunath, K. M., Perumal, I. & Manikandan, K. Leveraging personalized customer experiences in mobile edge computing through split learning using smart data-driven modeling. IEEE Access. 13, 34435\u201334448. https:\/\/doi.org\/10.1109\/access.2025.3543577 (2025).","journal-title":"IEEE Access."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-48421-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-48421-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-48421-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T22:07:52Z","timestamp":1781647672000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-48421-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,15]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["48421"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-48421-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,15]]},"assertion":[{"value":"26 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 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":"17579"}}