{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T06:11:17Z","timestamp":1790143877758,"version":"4.0.1"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cell Dev. Biol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Retinal microvascular alterations observed in optical coherence tomography angiography (OCTA) have emerged as promising biomarkers for cerebral small vessel disease (CSVD). However, accurate quantification of OCTA-derived vascular biomarkers remains challenging due to imaging noise, projection artifacts, low contrast, and structural discontinuities, which often lead to unreliable vessel segmentation and distorted vascular topology.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To address these challenges, we propose SemTopNet, a semantic\u2010topology joint modeling framework for OCTA vessel segmentation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The proposed framework integrates vision\u2010language semantic guidance, centerline-guided topology refinement, and uncertainty-aware adaptive supervision within a unified architecture. Specifically, semantic embeddings are incorporated to enhance global structural representation, while a centerline-guided topology refinement module explicitly improves vascular continuity and suppresses fragmented predictions. In addition, Monte Carlo dropout\u2010based uncertainty estimation is employed to improve robustness in ambiguous and low signal\u2010to\u2010noise regions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Extensive experiments on a CSVD OCTA dataset demonstrate that SemTopNet consistently outperforms existing convolutional and Transformer\u2010based segmentation methods, achieving the best performance in Dice similarity coefficient (0.8931), clDice (0.9027), Recall (0.9293), and AUC (0.9567). Ablation studies further verify the effectiveness of semantic modeling, topology\u2010aware refinement, and uncertainty\u2010aware supervision. Based on the obtained segmentation results, quantitative retinal vascular biomarkers were further analyzed, revealing significant layer-dependent microvascular alterations in CSVD patients, particularly in the deep vascular complex (DVC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>These findings demonstrate that topology-consistent OCTA vessel segmentation is essential for reliable retinal microvascular quantification. The proposed SemTopNet provides a robust framework for OCTA biomarker extraction and retinal\u2010cerebral vascular association analysis in CSVD\u2010related studies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcell.2026.1940436","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T05:50:29Z","timestamp":1790142629000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Vision\u2013language semantic guidance and topology refinement for robust retinal vessel segmentation and biomarker analysis in cerebral small vessel disease"],"prefix":"10.3389","volume":"14","author":[{"given":"Shanshan","family":"Hua","sequence":"first","affiliation":[{"name":"The First Affiliated Hospital of Ningbo University","place":["Ningbo, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, Nanjing University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuwei","family":"Mi","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital of Ningbo University","place":["Ningbo, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Shen","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital of Ningbo University","place":["Ningbo, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yisha","family":"Li","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital of Ningbo University","place":["Ningbo, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, Nanjing University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxin","family":"Ji","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital of Ningbo University","place":["Ningbo, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,23]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/978-3-030-32239-7_11","article-title":"A deep learning design for improving topology coherence in blood vessel segmentation","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"Ara\u00fajo","year":"2019"},{"key":"B2","first-page":"15016","article-title":"Learning to exploit temporal structure for biomedical vision-language processing","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Bannur","year":"2023"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-025-01945-x","article-title":"Retinal microvascular alterations reflect cerebral small vessel disease burden in frontotemporal dementia: a multimodal octa\u2013mri study","volume":"18","author":"Chen","year":"2025","journal-title":"Alzheimer\u2019s Res. & Ther"},{"key":"B4","doi-asserted-by":"publisher","first-page":"113558","DOI":"10.1016\/j.patcog.2026.113558","article-title":"Mtr-dnet: manifold topology and re-learning driven dual-branch network for semi-supervised octa vessel segmentation","volume":"179","author":"Chen","year":"2026","journal-title":"Pattern Recognit."},{"key":"B5","doi-asserted-by":"publisher","first-page":"8766","DOI":"10.1109\/TPAMI.2020.3013679","article-title":"A topological loss function for deep-learning based image segmentation using persistent homology","volume":"44","author":"Clough","year":"2020","journal-title":"IEEE Transactions Pattern Analysis Machine Intelligence"},{"key":"B6","doi-asserted-by":"crossref","first-page":"4194","DOI":"10.1109\/WACV61041.2025.00412","article-title":"Image-level regression for uncertainty-aware retinal image segmentation","volume-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","author":"Dang","year":"2025"},{"key":"B7","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1016\/S0161-6420(87)33527-4","article-title":"Treatment techniques and clinical guidelines for photocoagulation of diabetic macular edema: early treatment diabetic retinopathy study report number 2","volume":"94","year":"1987","journal-title":"Ophthalmology"},{"key":"B8","doi-asserted-by":"publisher","first-page":"207","DOI":"10.3390\/biomimetics10040207","article-title":"Frnet v2: a lightweight full-resolution convolutional neural network for octa vessel segmentation","volume":"10","author":"Gao","year":"2025","journal-title":"Biomimetics"},{"key":"B9","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1001\/jamaophthalmol.2019.4971","article-title":"Prevalence and severity of artifacts in optical coherence tomographic angiograms","volume":"138","author":"Holmen","year":"2020","journal-title":"JAMA Ophthalmology"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1111\/dom.15492","article-title":"Retinal vascular density as a potential biomarker of diabetic cerebral small vessel disease","volume":"26","author":"Huang","year":"2024","journal-title":"Diabetes, Obes. Metabolism"},{"key":"B11","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnu-net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"B12","article-title":"What uncertainties do we need in bayesian deep learning for computer vision?","volume":"30","author":"Kendall","year":"2017","journal-title":"Adv. Neural Information Processing Systems"},{"key":"B13","first-page":"1425","volume-title":"Residual u-net for Retinal Vessel Segmentation","author":"Li","year":"2019"},{"key":"B14","first-page":"3656","article-title":"Iternet: retinal image segmentation utilizing structural redundancy in vessel networks","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Li","year":"2020"},{"key":"B15","doi-asserted-by":"publisher","first-page":"774","DOI":"10.3390\/s24030774","article-title":"Segmentation of low-light optical coherence tomography angiography images under the constraints of vascular network topology","volume":"24","author":"Li","year":"2024","journal-title":"Sensors"},{"key":"B16","doi-asserted-by":"publisher","first-page":"16248","DOI":"10.1109\/TNNLS.2023.3293274","article-title":"Gesenet: a general semantic-guided network with couple mask ensemble for medical image fusion","volume":"35","author":"Li J.","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"B17","doi-asserted-by":"publisher","first-page":"133547","DOI":"10.1016\/j.neucom.2026.133547","article-title":"Sgba-net: semantic-guided bleeding-aware segmentation network for spinal endoscopy","volume":"683","author":"Li","year":"2026","journal-title":"Neurocomputing"},{"key":"B18","doi-asserted-by":"crossref","first-page":"5923","DOI":"10.1109\/EMBC.2019.8857785","article-title":"Epistemic uncertainty modeling for vessel segmentation","volume-title":"2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","author":"Martin","year":"2019"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1955","DOI":"10.1109\/TBME.2022.3232730","article-title":"Estimating uncertainty in neural networks for cardiac mri segmentation: a benchmark study","volume":"70","author":"Ng","year":"2022","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B20","doi-asserted-by":"publisher","first-page":"102547","DOI":"10.1016\/j.compmedimag.2025.102547","article-title":"Uncertainty-aware segmentation quality prediction via deep learning bayesian modeling: comprehensive evaluation and interpretation on skin cancer and liver segmentation","volume":"123","author":"Ok","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"B21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"B22","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-3965900\/v1","volume-title":"Retinal Vasculature and Faz Segmentation in Octa with efficientnet-enhanced u-net","author":"Raja","year":"2024"},{"key":"B23","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","volume-title":"International Conference on Medical Image Computing and computer-assisted Intervention","author":"Ronneberger","year":"2015"},{"key":"B24","first-page":"16560","article-title":"cldice-a novel topology-preserving loss function for tubular structure segmentation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Shit","year":"2021"},{"key":"B25","first-page":"229","article-title":"Semantic-aware graph reasoning and guidance for surgical scene understanding","volume-title":"2024 5th International Conference on Artificial Intelligence and Electromechanical Automation","author":"Song","year":"2024"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2024.3411133","article-title":"A hierarchical full-resolution fusion network and topology-aware connectivity booster for retinal vessel segmentation","volume":"73","author":"Su","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"B27","doi-asserted-by":"publisher","first-page":"107454","DOI":"10.1016\/j.cmpb.2023.107454","article-title":"Oct2former: a retinal oct-angiography vessel segmentation transformer","volume":"233","author":"Tan","year":"2023","journal-title":"Comput. Methods Programs Biomed."},{"key":"B28","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s40662-018-0104-3","article-title":"Emerging applications of optical coherence tomography angiography (octa) in neurological research","volume":"5","author":"Wang","year":"2018","journal-title":"Eye Vis."},{"key":"B29","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.neucom.2019.01.103","article-title":"Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks","volume":"338","author":"Wang","year":"2019","journal-title":"Neurocomputing"},{"key":"B30","doi-asserted-by":"crossref","first-page":"3876","DOI":"10.18653\/v1\/2022.emnlp-main.256","article-title":"Medclip: contrastive learning from unpaired medical images and text","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Wang","year":"2022"},{"key":"B31","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1109\/lsp.2023.3348664","article-title":"Blood vessel segmentation via topology interaction and contrast","volume":"31","author":"Wang","year":"2024","journal-title":"IEEE Signal Process. Lett."},{"key":"B32","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1109\/tmm.2023.3273924","article-title":"Msgfusion: medical semantic guided two-branch network for multimodal brain image fusion","volume":"26","author":"Wen","year":"2024","journal-title":"IEEE Trans. Multimedia"},{"key":"B33","doi-asserted-by":"publisher","first-page":"3990","DOI":"10.1109\/TMI.2024.3405982","article-title":"Deep closing: enhancing topological connectivity in medical tubular segmentation","volume":"43","author":"Wu","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B34","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1177\/1535370219899893","article-title":"Quantitative optical coherence tomography angiography: a review","volume":"245","author":"Yao","year":"2020","journal-title":"Exp. Biology Medicine"},{"key":"B35","doi-asserted-by":"publisher","first-page":"3155","DOI":"10.1109\/TMI.2023.3240825","article-title":"Tag-net: topology-aware graph network for centerline-based vessel labeling","volume":"42","author":"Yao","year":"2023","journal-title":"IEEE Transactions Medical Imaging"},{"key":"B36","doi-asserted-by":"publisher","first-page":"4551","DOI":"10.1109\/JBHI.2022.3182471","article-title":"Mfi-net: multiscale feature interaction network for retinal vessel segmentation","volume":"26","author":"Ye","year":"2022","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B37","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1109\/JBHI.2021.3089201","article-title":"Multi-level attention network for retinal vessel segmentation","volume":"26","author":"Yuan","year":"2022","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B38","first-page":"2967","article-title":"Ifseg: image-free semantic segmentation via vision-language model","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yun","year":"2023"},{"key":"B39","first-page":"15","article-title":"Smf-net: semantic-guided multimodal fusion network for precise pancreatic tumor segmentation in medical ct image","author":"Zhou","year":"2025","journal-title":"Front. Oncol."}],"container-title":["Frontiers in Cell and Developmental Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2026.1940436\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T05:50:32Z","timestamp":1790142632000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2026.1940436\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,23]]},"references-count":39,"alternative-id":["10.3389\/fcell.2026.1940436"],"URL":"https:\/\/doi.org\/10.3389\/fcell.2026.1940436","relation":{},"ISSN":["2296-634X"],"issn-type":[{"value":"2296-634X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,23]]},"article-number":"1940436"}}