Translational Vision Science & Technology最新文献

{"title":"Retinalysis-Vascx: An Explainable Software Toolbox for the Extraction of Retinal Vascular Biomarkers From Color Fundus Images.","authors":"Jose D Vargas Quiros, Michael J Beyeler, Sofía Ortín-Vela, Sven Bergmann, Caroline C W Klaver, Bart Liefers","doi":"10.1167/tvst.15.9.11","DOIUrl":"10.1167/tvst.15.9.11","url":null,"abstract":"<p><strong>Purpose: </strong>Automatic extraction of retinal vascular biomarkers from color fundus images (CFIs) is crucial for large-scale studies of the retinal vasculature. We present VascX, an open-source software toolbox that extracts biomarkers from CFI artery-vein segmentations.</p><p><strong>Methods: </strong>From a color fundus image, VascX computes artery and vein segmentation masks, extracts their centerlines, builds undirected and directed vessel graphs, and resolves vessel segments into longer vessels. A comprehensive set of biomarkers is derived, including vascular density, central retinal equivalents (CREs), and tortuosity. Spatially localized biomarkers may be calculated over grids placed relative to the fovea and optic disc.</p><p><strong>Results: </strong>Our test-retest reproducibility analysis on repeat imaging of the same eye by different devices shows that most VascX biomarkers have moderate to excellent agreement (intraclass correlation coefficient > 0.5), with important differences in the level of robustness of different biomarkers. Our analyses of biomarker sensitivity to image perturbations and heuristic parameter values support these differences and further characterize VascX biomarkers.</p><p><strong>Conclusions: </strong>VascX provides an explainable and flexible biomarker extraction toolbox that complements segmentation to produce reliable retinal vascular biomarkers. Our graph-based biomarker computation stages support reproducible, region-aware measurements suited for large-scale clinical and epidemiological research.</p><p><strong>Translational relevance: </strong>VascX supports oculomics research by enabling easy extraction of existing biomarkers and rapid experimentation with new biomarkers. Its robustness and computational efficiency facilitate scalable deployment in large databases. VascX is released via GitHub and PyPI with comprehensive documentation and examples to facilitate adoption by ophthalmic researchers and clinicians.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 9","pages":"11"},"PeriodicalIF":2.7,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13614130/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149012779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Influence of Refraction on Widefield Retinal and Choroidal Vascular Metrics in Optical Coherence Tomography Angiography in a Caucasian Population.","authors":"Charlotte Egbring, Sarah Kleemann, Moritz Fabian Danzer, Nicole Eter, Jens Julian Storp","doi":"10.1167/tvst.15.9.20","DOIUrl":"10.1167/tvst.15.9.20","url":null,"abstract":"<p><strong>Purpose: </strong>Refraction-related differences in retinal and choroidal vascular metrics have been reported using optical coherence tomography angiography (OCTA), primarily within the central fundus. This study aimed to establish normative vascular reference values for the retina and choroid using widefield swept-source OCTA (WF-SS-OCTA), stratified by spherical equivalent (SE), to characterize associations between refractive status and OCTA-derived vascular measurements extending beyond the central fundus.</p><p><strong>Methods: </strong>In this prospective single-center study, healthy volunteers underwent WF-SS-OCTA at the University Hospital Münster, Germany. Vascular metrics of the superficial capillary plexus (SCP) and the choroid were quantified using AngioTool software. Associations between SE and vascular metrics were analyzed using linear quantile mixed models accounting for inter-eye dependency and sex-specific effects.</p><p><strong>Results: </strong>A total of 414 eyes from 216 participants were analyzed. Exploratory analyses suggested an inverse relationship between SE and vascular endpoints in the SCP. In sex-stratified analyses, higher SE tended to be associated with increased flow density, vessel length, and junction counts in men, whereas junction counts tended to decrease in women. In the choroid, no clear associations were observed in the overall cohort; however, exploratory sex-specific analyses indicated potential associations between increasing SE and reduced junction density and total vessel length in women. Significant sex-related differences were observed for baseline junction counts and SE-related total vessel length trends.</p><p><strong>Conclusions: </strong>Refractive status may influence WF retinal and choroidal vascular metrics, with several parameters showing potential sex-specific patterns.</p><p><strong>Translational relevance: </strong>The resulting refraction- and sex-stratified normative dataset may serve as a practical reference framework for the interpretation of WF-SS-OCTA measurements, whereas future studies incorporating axial length (AL) measurements are needed to refine anatomic interpretation.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 9","pages":"20"},"PeriodicalIF":2.7,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13641213/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149040544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Vortex Vein Morphology and Choroidal Thickness as Predictors of Refractive Status: Model Construction and Mediation Analysis.","authors":"Huyong Zou, Junming Wang, Zhiping Liu, Juan Peng, Qun Lu, Xi Yin, Binhe Xu","doi":"10.1167/tvst.15.9.7","DOIUrl":"10.1167/tvst.15.9.7","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study was to investigate how vortex vein geometry and choroidal structure relate to refractive status and to develop an internally validated prediction framework based on these posterior segment features.</p><p><strong>Methods: </strong>A cross-sectional study was conducted on 147 participants, including 49 with myopic eyes, 49 with emmetropic eyes, and 49 with hyperopic eyes. Participants were young adults aged approximately 18 years, and axial length (AL) ranged from 23.19 ± 0.09 mm in hyperopic eyes to 24.92 ± 0.30 mm in myopic eyes. All participants underwent multimodal imaging, including ultra-widefield fundus photography, enhanced-depth imaging optical coherence tomography (EDI-OCT), and optical coherence tomography angiography (OCTA). Temporal-superior (TS) vortex vein distances, subfoveal choroidal thickness (SFCT), AL, and spherical equivalent (SE) were analyzed using least absolute shrinkage and selection operator (LASSO) regression, restricted cubic splines (RCS), multinomial logistic modeling, and mediation analysis.</p><p><strong>Results: </strong>Compared with hyperopic eyes, myopic eyes showed significantly longer AL and thinner SFCT (both P < 0.001). LASSO regression retained TS together with established refractive parameters including SFCT and AL in the final predictive model. RCS analysis demonstrated significant nonlinear associations of AL and SFCT with myopia probability (both P < 0.001). The internally validated nomograms achieved AUCs of approximately 0.99 for myopia and 0.97 for hyperopia classification. Mediation analysis showed that SFCT accounted for approximately 64.7% of the association between TS and SE.</p><p><strong>Conclusions: </strong>Combining vortex vein morphology with choroidal metrics offers a comprehensive structural framework for refractive assessment and suggests potential utility for refractive risk stratification, pending external validation.</p><p><strong>Translational relevance: </strong>These findings translate posterior segment imaging biomarkers into proof-of-concept prediction nomograms for refractive risk stratification, with potential future clinical relevance pending external validation.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 9","pages":"7"},"PeriodicalIF":2.7,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13589397/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148971512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Normative Values of Retinal and Choroidal Thickness in a Healthy Pediatric Population Using DRI Triton SS-OCT.","authors":"Ana Isabel Diaz Cortes, Genis Cardona, Enric Puigventos Rosanas, Juan Carlos Ondategui-Parra, Carlos Fresno Cañada","doi":"10.1167/tvst.15.9.21","DOIUrl":"10.1167/tvst.15.9.21","url":null,"abstract":"<p><strong>Purpose: </strong>Clinical interpretation of optical coherence tomography (OCT) in pediatric populations requires specific normative values, because the reference databases incorporated in most devices are based on adults. The aim of this study was to establish reference ranges for macular retinal and choroidal thickness in healthy children using the swept source DRI Triton OCT (Topcon).</p><p><strong>Methods: </strong>A cross-sectional observational study was conducted on 192 healthy children (347 eyes) aged between 4 and 16 years. Measurements were obtained for total retinal thickness, thickness of macular retinal nerve fiber layer (mRNFL) and ganglion cell layers (GCL+ and GCL++), as well as choroidal thickness, using macular OCT. Participants were classified by age, sex, and spherical equivalent of refraction (SER). Differences between groups were analyzed using tests, analysis of variance, and the Pearson coefficient of correlation was used to explore associations between parameters (P < 0.05).</p><p><strong>Results: </strong>The pattern of retinal thickness distribution matched that described in previous pediatric studies in the inner circle and NSIT in the outer circle). Differences between sexes were observed in some retinal quadrants and inner layers, though effect sizes were small. Age showed limited influence on retinal and ganglion cell layer thickness, with weak correlations. In contrast, SER showed a more consistent effect: children with higher myopia presented significant variations in mRNFL, GCL+, and GCL++, as well as generalized choroidal thinning. Age and SER displayed only a weak correlation with each other.</p><p><strong>Conclusions: </strong>This study provides a detailed normative database for retinal and choroidal thickness in a Spanish pediatric population obtained with the DRI Triton SS-OCT device. The data confirm that SER is a relevant factor influencing structural measurements, whereas age has a more limited impact. These references are essential for improving diagnostic accuracy and early detection of macular and choroidal alterations in children.</p><p><strong>Translational relevance: </strong>By providing pediatric-specific OCT normative values, this study directly translates structural imaging research into clinically useful benchmarks that enhance early detection, diagnosis, and monitoring of retinal and choroidal disorders in children.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 9","pages":"21"},"PeriodicalIF":2.7,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13641207/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149070176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association and Age Heterogeneity of Systemic Metabolomic Signatures With Age-Related Cataract: A Mendelian Randomization and Heterogeneity Analysis.","authors":"Zhangluxi Liu, Ao Lu, Siyuan He, Yiying Wang, Guannan Su, Peizeng Yang","doi":"10.1167/tvst.15.9.2","DOIUrl":"10.1167/tvst.15.9.2","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate systemic metabolomic signatures associated with age-related cataract and prioritize signals with age-stable or age-heterogeneous patterns.</p><p><strong>Methods: </strong>We performed two-sample Mendelian randomization (MR) analyses of 249 Nightingale Health metabolomic traits against age-related cataract in FinnGen 12. Higher-confidence MR candidates were defined by inverse-variance weighted (IVW) false discovery rate (FDR) < 0.05, complete directional concordance across seven complementary MR and sensitivity analyses, and nominal support in at least five analyses. MR-prioritized candidates were then triangulated against UK Biobank incident cataract associations. Age-stratum heterogeneity was assessed using tertile-specific UK Biobank estimates and Cochran Q statistics.</p><p><strong>Results: </strong>Among 249 metabolites, 71 met the IVW FDR threshold, and 22 remained after higher-confidence MR filtering. Of these, 13 showed MR-concordant associations with incident cataract in the UK Biobank 500,000 summary layer. Age-stratum assessment prioritized eight metabolites, comprised of five age-stable fatty-acid/lipoprotein-related signals and three age-heterogeneous signals involving glycoprotein acetyls, phenylalanine, and total fatty acids.</p><p><strong>Conclusions: </strong>Using an MR-guided triangulation framework, we prioritized eight systemic metabolomic signals associated with age-related cataract. These signals were comprised of an age-stable fatty-acid/lipoprotein axis and age-heterogeneous inflammatory, amino-acid, and fatty-acid traits, highlighting distinct systemic metabolic patterns that may inform future cataract biomarker and mechanistic studies.</p><p><strong>Translational relevance: </strong>This study provides a focused set of systemic metabolic candidates for future cataract biomarker validation and prospective risk-stratification research. The integration of MR prioritization, UK Biobank triangulation, and age-stratum heterogeneity assessment offers a transferable framework for studying metabolic signatures in age-related ocular disease.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 9","pages":"2"},"PeriodicalIF":2.7,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13549411/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148866806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving Generalization of Deep Learning for Glaucoma Classification Under Real-World Domain Shift via Unsupervised Domain Adaptation.","authors":"Homa Rashidisabet, R V Paul Chan, Thasarat Sutabutr Vajaranant, Darvin Yi","doi":"10.1167/tvst.15.9.3","DOIUrl":"10.1167/tvst.15.9.3","url":null,"abstract":"<p><strong>Purpose: </strong>To develop and evaluate an unsupervised domain adaptation (UDA) framework for glaucoma classification from fundus images that improves the generalizability of deep learning (DL) models across heterogeneous imaging characteristics and clinical settings.</p><p><strong>Methods: </strong>We developed an adversarial UDA framework that adapts a labeled source domain to an unlabeled target domain by jointly optimizing glaucoma classification and domain discrimination. A total of 6906 fundus images were included: 1422 images (full-view and optic nerve head-cropped) derived from 711 fundus photographs of 520 patients from the University of Illinois Chicago and 5484 images from three public datasets (RIMONE-DL, n = 371; REFUGE, n = 259; LAG, n = 4854). Performance was evaluated across multiple source-target domain pairs. Saliency map analysis compared feature utilization between UDA and standard DL models.</p><p><strong>Results: </strong>Across diverse source-target dataset pairs, the proposed UDA framework improved standard DL classification accuracy by up to 40.0% and area under the curve (AUC) by up to 59.8% in extreme domain shift experiments. UDA also reduced the performance gap to the ideal target-trained model by up to 82.6% for accuracy and 38.1% for AUC. When applied to unseen domains, UDA improved classification accuracy by up to 14.7% relative to standard DL.</p><p><strong>Conclusions: </strong>The proposed UDA framework improves cross-domain generalizability of DL-based glaucoma classification from fundus images. Compared with standard DL models, UDA exhibits feature utilization patterns more aligned with an ideal baseline, reducing overreliance on optic nerve head-specific cues and supporting more robust decision-making under domain shift.</p><p><strong>Translational relevance: </strong>By enabling glaucoma classification without requiring labeled data from new clinical sites, this UDA framework addresses a key barrier to deploying artificial intelligence-based screening tools across diverse real-world ophthalmic settings.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 9","pages":"3"},"PeriodicalIF":2.7,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13549403/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148881897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simulating Partial Conduction Delays in VEPs Via Asynchronous and Contrast-Modulated Stimulation.","authors":"Leon A Pfeiffer, Julia Haldina, Sven P Heinrich","doi":"10.1167/tvst.15.9.5","DOIUrl":"10.1167/tvst.15.9.5","url":null,"abstract":"<p><strong>Purpose: </strong>To investigate the origin of P100 double peaks occasionally observed in patients with optic neuritis by experimentally inducing timing asynchronies between visual field locations and modulating stimulus strength via contrast reduction in transient and steady-state VEPs (trVEP and ssVEP).</p><p><strong>Methods: </strong>The trVEPs and ssVEPs were recorded using a checkerboard stimulus vertically split into nasal and temporal half-fields. Timing asynchrony was induced by delaying the temporal half-field by 24, 35, or 47 ms; stimulus strength was modulated by reducing the temporal half-field contrast to 20% or 8%. Full-field and half-field responses were quantitatively analyzed and qualitatively compared to characterize the superposition effects induced by these stimulus changes.</p><p><strong>Results: </strong>In trVEPs, contrast reduction produced smaller, broader P100 responses with modest peak-time delays and only sporadic double-peak formation. Conversely, induced temporal half-field delays robustly generated P100 double peaks (incidence: 50% at 24 ms, 85% at 35 ms, and 100% at 47 ms). Quantitative and qualitative analyses demonstrated that the P100 peaks of the half-field responses aligned temporally with the two peaks of the full-field double peak. In ssVEPs, increasing delays reduced the absolute harmonic magnitude and altered the second-to-first harmonic ratio (decreased at 24 and 35 ms; increased at 47 ms).</p><p><strong>Conclusions: </strong>Spatially localized timing asynchronies reliably reproduce double-peaked P100 morphologies, supporting differential conduction speeds within the optic nerve as a plausible mechanism in patients with optic neuritis.</p><p><strong>Translational relevance: </strong>Linking experimentally induced conduction-delay effects to VEP morphology enhances the clinical interpretation of atypical VEP waveforms in suspected optic neuritis.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 9","pages":"5"},"PeriodicalIF":2.7,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13574218/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148907304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative Utility of Tear Film and Ocular Surface Parameters in Differentiating Sjögren's Disease Dry Eye From Non-Sjögren's Dry Eye.","authors":"Meron Haile, Michael X Lin, Julia Zeng, Gavin Li, David Cui, Michelle Hessen, Michela Montecchi-Palmer, Esen K Akpek","doi":"10.1167/tvst.15.9.17","DOIUrl":"10.1167/tvst.15.9.17","url":null,"abstract":"<p><strong>Purpose: </strong>Tear production and ocular surface damage are equally weighted in the 2016 classification criteria for Sjögren's disease (SjD). We compared Schirmer testing versus ocular surface staining to distinguish SjD from non-SjD dry eye.</p><p><strong>Methods: </strong>Patients with SjD dry eye (n = 20), non-SjD dry eye (n = 47), and controls (n = 29) were evaluated in this cross-sectional study. Schirmer testing assessed tear production; ocular surface staining was graded using the Sjögren's International Collaborative Clinical Alliance (SICCA) and National Eye Institute (NEI) systems. Analyses included age-stratified comparisons, receiver operating characteristic (ROC) analyses, and multivariable regression.</p><p><strong>Results: </strong>Overall, mean Schirmer values did not differ between SjD and non-SjD dry eye but were lower in SjD among participants <60 years (8.78 ± 6.24 vs. 18.00 ± 10.04 mm, P = 0.018), not ≥60 years (15.27 ± 11.01 vs. 14.00 ± 8.28 mm, P = 0.699). Schirmer ≤5 mm threshold differentiated SjD only in the younger group (<60 years: 55.6% vs. 5.0%, P = 0.014; ≥60 years: 18.2% vs. 25.9%, P = 0.145), and Schirmer testing showed poor overall discrimination, particularly among older participants (area under the curve [AUC] = 0.602; <60 years 0.772; ≥60 years 0.453). By contrast, SICCA corneal staining demonstrated consistently stronger discrimination (overall AUC 0.803; <60 years 0.872; ≥60 years 0.754). In multivariable models, NEI conjunctival staining (odds ratio [OR] = 1.23, P = 0.008) and SICCA corneal staining (OR = 1.83, P = 0.046), but not Schirmer testing (OR = 1.01, P = 0.888), were associated with SjD.</p><p><strong>Conclusions: </strong>Ocular surface staining was more strongly associated with classified SjD status in this cohort, whereas Schirmer testing showed age-dependent performance.</p><p><strong>Translational relevance: </strong>Ocular surface staining may be a more reliable marker of Sjögren's dry eye than Schirmer testing, with implications for clinical evaluation.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 9","pages":"17"},"PeriodicalIF":2.7,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13641203/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149040640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High-Resolution Optical Coherence Tomography Visualizes Posterior Vitreous Lamellar Architecture in Eyes With Chronic Central Serous Chorioretinopathy.","authors":"Yoko Miura, Dinh Nho Vu, Joyce Tohme, Ophir Reinhardt, Giorgio Bozzini, Svenja Rebecca Sonntag, Salvatore Grisanti","doi":"10.1167/tvst.15.9.14","DOIUrl":"10.1167/tvst.15.9.14","url":null,"abstract":"<p><strong>Purpose: </strong>High-resolution optical coherence tomography (HighRes-OCT) enables in vivo visualization of microstructural features that are not accessible with conventional clinical OCT systems. Using this capability, we investigated posterior vitreous microarchitecture in eyes with chronic central serous chorioretinopathy (CSC) and healthy individuals.</p><p><strong>Methods: </strong>HighRes-OCT imaging (axial resolution approximately 3 µm) was performed in 20 patients with chronic CSC and 20 age-matched healthy subjects. Posterior vitreous structures were qualitatively assessed for the presence of discrete lamellar patterns and compared with conventional spectral-domain OCT (SD-OCT) acquired at the same visits. Lamellar visibility was evaluated across scan orientations, and reproducibility was assessed in all CSC eyes with follow-up imaging.</p><p><strong>Results: </strong>Distinct hyper-reflective lamellar structures within the posterior vitreous were clearly identified in 9 of 20 CSC eyes, whereas no comparable lamellar organization was observed in healthy eyes. In CSC eyes, lamellae appeared as parallel, layered bands located immediately anterior to the internal limiting membrane and were reproducible across scan orientations. These structures were not readily discernible on conventional OCT. Healthy eyes showed relatively homogeneous vitreous reflectivity, although faint linear structures were occasionally observed.</p><p><strong>Conclusions: </strong>HighRes-OCT enables in vivo visualization of posterior vitreous lamellar microstructures that are not readily discernible with conventional clinical OCT. The preferential detection of these structures in eyes with chronic CSC suggests disease-associated alterations in vitreous matrix organization and highlights a previously underexplored dimension of vitreous imaging.</p><p><strong>Translational relevance: </strong>Visualization of vitreous microarchitecture using HighRes-OCT may provide a new translational imaging window to study disease-related vitreous remodeling and its relationship to retinal pathology.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 9","pages":"14"},"PeriodicalIF":2.7,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13615552/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149018099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Stereo-Vision-Inspired Spectral Disparity Learning for Choroidal Tumor Thickness Prediction.","authors":"Albert K Dadzie, Sanjay Ganesh, Behrouz Ebrahimi, Masrur Sadhin, Reem Alahmadi, Taeyoon Son, Michael J Heiferman, Xincheng Yao","doi":"10.1167/tvst.15.9.18","DOIUrl":"10.1167/tvst.15.9.18","url":null,"abstract":"<p><strong>Purpose: </strong>To investigate whether choroidal tumor thickness can be estimated from fundus photographs using a stereo-vision-inspired deep learning approach.</p><p><strong>Methods: </strong>A deep learning framework was developed to independently extract features from red and green color channels of ultra-widefield fundus photographs and integrate them using a spectral disparity module (SDM). The SDM explicitly captures inter-channel correspondence and disparity, mimicking the principles of human binocular depth perception. The model was trained and evaluated on 337 patients with choroidal tumors, using ultrasound-measured thickness as ground truth. Performance was assessed using regression metrics and risk classification based on the Collaborative Ocular Melanoma Study criteria.</p><p><strong>Results: </strong>The proposed stereo-fusion model achieved strong agreement with the ground-truth ultrasound measurements (root mean squared error = 1.07 mm, mean absolute error = 0.74 mm, R² = 0.85), outperforming single-channel and conventional color image models. Thickness-based risk stratification yielded an accuracy of 90.5%, a sensitivity of 87.7%, and a specificity of 92.9%.</p><p><strong>Conclusion: </strong>Choroidal tumor thickness can be accurately estimated from fundus photographs by leveraging wavelength-dependent spectral disparities. This approach enables noncontact thickness estimation and supports scalable screening and triage of choroidal tumors.</p><p><strong>Translational relevance: </strong>By leveraging wavelength-dependent spectral disparities with deep learning, this work translates fundus photography into a noncontact tool for estimating choroidal tumor thickness.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 9","pages":"18"},"PeriodicalIF":2.7,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13641199/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149040606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}