Translational Vision Science & Technology最新文献

{"title":"Generation of a New Immunodeficient Rat Model of Retinal Degeneration With LSL TdTomato Reporter and TdTomato-Pcp2 Expression.","authors":"Magdalene J Seiler, Helios Nguyen, Devan Endejan, Bin Lin, Guojun Zhao, Lauren Klaskala","doi":"10.1167/tvst.15.8.24","DOIUrl":"10.1167/tvst.15.8.24","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study was to develop a fluorescently labeled immunodeficient retinal degenerate (RD) rat model for studying photoreceptor degeneration and transplant-host connectivity using the Cre-lox system.</p><p><strong>Methods: </strong>We developed gene constructs for CAG-LSL-TdTomato (expressing floxed TdTomato) and Pcp2-Cre (marker for ON-bipolar cells) that were injected into rat embryos. The LSL TdTomato reporter strain, created on immunodeficient RhoS334ter-3 rats (RRRC #539), was bred to homozygosity (strain SD-Foxn1rnuTg((Rho-S334X)3,CAG-TdTomato)1010Mjsuc, RRRC #1055, \"RNT\"). The gene construct Pcp2-Cre was injected into Long-Evans (LE) rat embryos, resulting in two Pcp2-cre founders (strain PCP2 Cre-1105 RKI, \"Pcp2\"), with targeted and targeted/random insertion of the transgene. F1 offspring were bred to homozygosity and immunodeficiency. To test whether TdTomato expression can be induced in \"RNT\" rats expressing floxed TdTomato, retinal explants of P9 \"RNT\" rats were exposed to AAV-PHP.eB-hSyn-myc-Cre (AAV-Syn-Cre) virus. Homozygous rats of both strains (\"RNT\" and Pcp2-Cre) were crossbred to generate RD TdTomato-Pcp2 (\"RTP\") rats. Retinas were stained for various retinal markers. GFP-expressing rat retinas were transplanted to 6-week-old \"RTP\" rats and analyzed after 37 and 77 days.</p><p><strong>Results: </strong>AAV-Syn-Cre induced TdTomato expression in \"RNT\" retinas. TdTomato-Pcp2 RD rats developed RD similar to the original Rho S334ter-3 rats. Retinas with targeted Pcp2-Cre insertion showed TdTomato in retinal interneurons, overlapping with Pcp2-staining ON bipolar cells, and cones. Retinas with random Pcp2-Cre insertion exhibited additional TdTomato in many other cells. Pcp2-TdTomato expression defined transplant-host boundaries.</p><p><strong>Conclusions: </strong>We created a unique RD rat model for studying retinal transplant connectivity which can also be used to generate RD rats with other cell-specific labels.</p><p><strong>Translational relevance: </strong>This newly created rat is useful for cell therapy and retinal degeneration studies.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 8","pages":"24"},"PeriodicalIF":2.7,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13545737/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148814215","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":"Explicit Inclusion of Diabetes Mellitus Without Retinopathy Within Diabetic Retinopathy Prediction.","authors":"Homa Rashidisabet, Jennifer I Lim, Andrius Kazlauskas, Darvin Yi","doi":"10.1167/tvst.15.7.3","DOIUrl":"10.1167/tvst.15.7.3","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study was to evaluate whether explicitly modeling diabetes mellitus (DM) without diabetic retinopathy (DR) as its own stage enables deep learning (DL) to detect early retinal changes for early risk identification of DR severity spectrum.</p><p><strong>Methods: </strong>We developed 3 DL classification models that explicitly incorporated DM without DR as a distinct stage using 3-class, 4-class, and 6-class staging granularity using 6069 color fundus images from the University of Illinois Chicago Hospital, including 1996 no-DM cases, 1852 DM without DR cases, and 2221 DR cases (516 mild, 220 moderate, 103 severe, and 1382 proliferative DR [PDR]). We developed segmentation models for the optic nerve head (ONH) and retinal vessels to quantify the impact of these regions on classification performance through targeted perturbations. We also examined spatial changes in retinal features across DR stages by measuring the alignment between DL saliency maps and ONH location.</p><p><strong>Results: </strong>For the 3-class model, areas under the curve (AUCs) were 92.2% (no-DM), 80.3% (DM without DR), and 74.1% (mild DR). For the 4-class model, AUCs were 94.0% (no-DM), 71.9% (DM without DR), 61.5% (mild DR), and 80.3% (referable DR). For the 6-class model, AUCs were 94.0% (no-DM), 65.7% (DM without DR), 65.6% (mild DR), 58.9% (moderate DR), 58.6% (severe DR), and 76.1% (PDR). Vessel perturbations reduced performance by 16% to 31% across models, and greater DR severity was associated with increased saliency-to-ONH distances (Pearson r = 0.69-0.72, P < 0.001).</p><p><strong>Conclusions: </strong>Explicitly modeling diabetes without retinopathy improved early-stage discrimination and revealed feature-reliance shifts with DR severity. Vessel- and saliency-based analyses identified subtle retinal changes preceding clinical DR.</p><p><strong>Translational relevance: </strong>Treating diabetes without retinopathy as its own stage may enhance early DR risk identification and aid development of clinically useful artificial intelligence (AI) tools.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 7","pages":"3"},"PeriodicalIF":2.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13332532/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148369779","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":"Leakage-Aware Visit-Level Benchmarking Reveals Representational Overlap in Deep Learning for Bacterial Versus Fungal Keratitis Classification.","authors":"Wonjong Jeong, Jinho Jeong","doi":"10.1167/tvst.15.7.28","DOIUrl":"10.1167/tvst.15.7.28","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study was to benchmark deep learning for bacterial versus fungal keratitis classification from slit-lamp photographs under a leakage-aware, visit-level framework, and to characterize embedding-space geometry as a potential performance ceiling.</p><p><strong>Methods: </strong>This retrospective single-center study included white-light slit-lamp photographs from 101 patients with culture-confirmed bacterial or fungal keratitis (258 visits; 658 images), using strict patient-disjoint five-fold cross-validation with the clinical visit as the primary prediction unit. Image-level classifiers, multiple instance learning (MIL), and DINOv2-based retrieval were compared under three preprocessing strategies: full-frame, corneal region of interest (ROI), and lesion-centered MedSAM crops. Embedding geometry was analyzed using Uniform Manifold Approximation and Projection (UMAP). Pairwise visit-level model comparisons were performed using patient-cluster paired bootstrap on aligned out-of-fold (OOF) visit-level predictions, and probability calibration was assessed using expected calibration error (ECE) and Brier score.</p><p><strong>Results: </strong>At the image level, the highest area under the receiver operating characteristic curve (AUROC) was 0.691. At the visit level, convolutional neural network (CNN)-based MIL models achieved the highest AUROC (0.677), followed by retrieval-based approaches (0.661). However, MIL models showed larger generalization gaps, whereas DINOv2 lesion-crop retrieval remained stable (-0.014). Lesion-centered preprocessing was the dominant performance determinant within the retrieval paradigm. Embedding analysis revealed extensive class overlap, with 90.9% of fungal visits within the bacterial convex hull.</p><p><strong>Conclusions: </strong>Under leakage-aware, visit-level evaluation, all paradigms converged to modest discrimination, consistent with representational overlap within this single-center cohort. CNN-based MIL achieved higher AUROC but greater overfitting; retrieval-based models provided more stable generalization and superior probability calibration. Whether this ceiling is task-intrinsic or site-specific requires multicenter validation.</p><p><strong>Translational relevance: </strong>Leakage-aware visit-level benchmarking supports realistic evaluation and calibrated decision support.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 7","pages":"28"},"PeriodicalIF":2.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13426526/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148593269","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":"Binocular Non-Cycloplegic Ocular Parameters for Modeling Cycloplegic SER in Children.","authors":"Ranran Chen, Juan Zhang, Jinming Lei, Jinling Zhang, Xiaoyan Yu, Yanlong Bi, Yujie Liao","doi":"10.1167/tvst.15.7.15","DOIUrl":"10.1167/tvst.15.7.15","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study was to evaluate an interpretable binocular modeling approach for predicting cycloplegic spherical equivalent refraction (SER) in children while accounting for inter-eye correlation.</p><p><strong>Methods: </strong>Clinical data from children aged 4 to 17 years were collected at 2 centers. Participants were stratified into three age groups. The binocular approach constructed inter-eye features, including means, differences, and error-related metrics. A linear mixed-effects model (LMM) with subject-specific random intercepts was applied. Model performance was evaluated using R², mean absolute error (MAE), mean square error (MSE), and root mean square error RMSE. SHapley Additive exPlanations (SHAP) were used to quantify feature contributions.</p><p><strong>Results: </strong>In internal validation, the optimal binocular models achieved R² values of 0.882, 0.957, and 0.969, with MAE values of 0.399 diopter (D), 0.285 D, and 0.232 D in the 4 to 5, 6 to 12, and 13 to 17 years age groups, respectively. In external validation, the best binocular models achieved R² values of 0.834, 0.947, and 0.969, with MAE values of 0.488 D, 0.287 D, and 0.354 D in the 3 age groups. SHAP analysis revealed axial length/corneal curvature radius (AL/CR) and AL predominated in children aged 4 to 5 years; non-cycloplegic SER was the determinant in those aged 6 to 12 years; non-cycloplegic SER and its mean became dominant in adolescents aged 13 to 17 years.</p><p><strong>Conclusions: </strong>The binocular modeling approach shows potential for improving accuracy of refractive status prediction in children, and the integration of interpretability methods further supports its utility as an auxiliary tool in large-scale vision screening programs.</p><p><strong>Translational relevance: </strong>This study translates ocular biometric modeling into clinical practice by providing an interpretable binocular approach to support risk assessment and preliminary screening in pediatric myopia management.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 7","pages":"15"},"PeriodicalIF":2.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13372062/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148424407","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":"Identification and Mapping of a Posterior Ocular Lymphatic Outflow (POLO) Pathway Through Choroidal Lymphatics.","authors":"Babishaa Sauntharrajan, Neeru Gupta, Xun Zhou, Ekim Gümeler, Greg Stanisz, Wilfred W Lam, Margaret Koletar, Yeni H Yücel","doi":"10.1167/tvst.15.7.23","DOIUrl":"10.1167/tvst.15.7.23","url":null,"abstract":"<p><strong>Purpose: </strong>To identify, map, and characterize a posterior ocular lymphatic outflow (POLO) pathway from the suprachoroidal space and assess its drainage dynamics and cervical nodal uptake using time-resolved imaging.</p><p><strong>Methods: </strong>Albumin-based tracers (galbumin and CF770/BSA) were delivered into the suprachoroidal space of adult mice under general anesthesia. In vivo imaging included magnetic resonance imaging (MRI) and near-infrared fluorescence imaging using confocal scanning laser ophthalmoscopy (cSLO) of the ocular surface and orbital soft tissues. Ex vivo assessments included in situ head and neck fluorescence imaging 20 minutes after tracer injection and hyperspectral microscopy of ocular and orbital sections. Lymphatic identity was assessed by immunofluorescence staining (podoplanin and vascular endothelial growth factor receptor-3 [VEGFR-3]) in Prox1-tdTomato reporter mice.</p><p><strong>Results: </strong>Following suprachoroidal tracer injection, in vivo MRI and cSLO fluorescence imaging showed preferential drainage toward the nasal orbit. Hyperspectral microscopy showed higher tracer signal in the ipsilateral sclera and orbit than contralateral tissues, and in situ fluorescence imaging detected near-infrared tracer in the ipsilateral cervical lymph node at 20 minutes. Confocal microscopy of the choroid showed co-localization of podoplanin with VEGFR-3 and Prox1 and demonstrated tracer within podoplanin-positive choroidal lymphatic vessels, consistent with a posterior drainage route from the suprachoroidal space to cervical lymph nodes.</p><p><strong>Conclusions: </strong>This study identifies a previously unrecognized POLO pathway and expands ocular drainage physiology beyond the anterior segment to include a posterior lymphatic route through choroidal lymphatic vessels.</p><p><strong>Translational relevance: </strong>Identification of a POLO pathway reveals a measurable route for fluid clearance, intraocular pressure regulation, and drug delivery, offering new strategies to preserve vision in retinal and posterior segment diseases characterized by fluid accumulation, impaired clearance, or inflammation.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 7","pages":"23"},"PeriodicalIF":2.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13390728/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148473132","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":"Therapeutic Potential of Mesenchymal Stem Cell-Derived Exosomes in Ocular Surface Disorders.","authors":"Kaiyao Chi, Kai Jia, Tong Guo, Daoxi Lei, Huili Li","doi":"10.1167/tvst.15.7.19","DOIUrl":"10.1167/tvst.15.7.19","url":null,"abstract":"<p><p>The global burden of ocular surface disorders (OSDs), manifesting as progressive visual impairment and chronic discomfort, has driven urgent exploration of regenerative therapeutic strategies. Mesenchymal stem cell-derived exosomes (MSC-Exos) have emerged as promising candidates for OSD treatment, as they exhibit multifaceted therapeutic properties including immunomodulation, antifibrotic activity, and pro-regenerative capacity. This systematic review consolidates current understanding of MSC-Exo-mediated ocular surface repair mechanisms, with particular emphasis on the molecular dialog established through delivery of bioactive cargo that modulate pivotal signaling pathways. We critically analyze preclinical evidence demonstrating therapeutic efficacy across diverse OSD pathologies, including dry eye disease, corneal epithelial defects, and limbal stem cell deficiency. Notwithstanding these advances, critical barriers to clinical translation persist: (1) methodological heterogeneity arising from variable cell sourcing, culture protocols, and exosome isolation/characterization standards; (2) discordance between animal models and human OSD pathophysiology; and (3) technological limitations in scalable, clinically compatible delivery systems. Addressing these challenges requires interdisciplinary collaboration to standardize exosome production pipelines and establish robust preclinical validation frameworks, thereby accelerating the transition of MSC-Exo therapies from bench to bedside.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 7","pages":"19"},"PeriodicalIF":2.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13374847/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148430752","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":"In Vivo Confocal Microscopy Revealed Alteration of Limbal Stem Cells and Sub-Basal Nerve Plexus in Allergic and Dry Eye-Related Ocular Surface Diseases.","authors":"Xiaojie Wan, Kaiye Zhang, Yu Zhang, Yujie Mou, Xiaodan Huang","doi":"10.1167/tvst.15.7.7","DOIUrl":"10.1167/tvst.15.7.7","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate alterations of the palisades of Vogt (POV), basal epithelial cell density (BECD), and the corneal sub-basal nerve plexus (SBNP) in patients with vernal keratoconjunctivitis (VKC), blepharokeratoconjunctivitis (BKC), and allergic conjunctivitis (AC) using in vivo confocal microscopy (IVCM).</p><p><strong>Methods: </strong>IVCM imaging of the limbus, central basal epithelial layer, and SBNP was performed in 122 participants (39 VKC, 26 BKC, 42 AC, and 14 normal controls). POV was graded semiquantitatively. To account for intereye correlation, generalized estimating equations were applied, and ordinal logistic regression was used to identify factors associated with POV visibility. Spearman correlation analysis was performed to evaluate relationships between SBNP parameters, BECD, and POV scores.</p><p><strong>Results: </strong>POV visibility was significantly associated with age, disease group, disease duration, and limbal quadrant. Compared with controls, patients with VKC, BKC, and AC showed significantly lower POV scores, accompanied by decreased BECD and SBNP parameters. Older age and longer disease duration were associated with lower POV scores; a more pronounced POV morphology was observed in the superior and inferior quadrants. Significant correlations were observed among BECD, SBNP parameters, and POV scores.</p><p><strong>Conclusions: </strong>Chronic ocular surface inflammation may be associated with disruption of the limbal stem cell niche, reflected by alterations in POV, cellular, and neural parameters, supporting the potential role of IVCM-derived metrics in the early detection of limbal stem cell dysfunction.</p><p><strong>Translational relevance: </strong>Vivo confocal microscopy may provide noninvasive in vivo biomarkers of limbal niche and corneal nerve alterations in inflammatory ocular surface diseases, with potential value for earlier identification of limbal stem cell deficiency-related changes.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 7","pages":"7"},"PeriodicalIF":2.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13355388/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148405940","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":"A Polycaprolactone-Based Drug Carrier Loaded With Methotrexate to Attenuate Proliferative Vitreoretinopathy In Vitro.","authors":"Anna Hillenmayer, Vincent Bilal, Christina Hilterhaus, Melih Parlak, Armin Wolf, Christian Maximilian Wertheimer","doi":"10.1167/tvst.15.7.26","DOIUrl":"10.1167/tvst.15.7.26","url":null,"abstract":"<p><strong>Purpose: </strong>Proliferative vitreoretinopathy (PVR) leads to poor outcomes through recurrent detachment. Early clinical evidence suggests that repeated intravitreal injections of methotrexate (MTX) may offer protective benefits. In this study, we developed a polycaprolactone (PCL)-based drug carrier loaded with MTX and examined its in vitro pharmacodynamics and biological effects in vitro.</p><p><strong>Methods: </strong>PCL was melted and combined with MTX to form a solidified carrier, which was then characterized by electron microscopy. Drug release kinetics were assessed using an ocular pharmacokinetic model. Human retinal pigment epithelium (hRPE) cells and Müller glial cells (MIO-M1) were exposed to the MTX-loaded carrier for 48 hours, and proliferation, metabolism, migration, protein expression, and toxicity were evaluated.</p><p><strong>Results: </strong>Ultrastructural analysis confirmed the typical morphology of the PCL-based matrix. The pharmacokinetic model revealed an initial burst release of MTX followed by a sustained release over approximately 6 months. Exposure to the drug carrier significantly reduced viability and proliferation of both hRPE and MIO-M1 cells, while toxicity was not detected. The drug carrier led to downregulation of fibroblastic protein expression in hRPE, but did not affect MIO-M1. Several other proteins exhibited significant regulation in the proteomics assay.</p><p><strong>Conclusions: </strong>The MTX-loaded PCL carrier maintained a prolonged release profile and demonstrated potential protective effects against PVR in vitro. Further studies are warranted to explore the clinical applicability of this drug delivery system.</p><p><strong>Translational relevance: </strong>This in vitro study introduces a new PCL-based sustained-release MTX drug carrier that may help address major limitations of current PVR treatments.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 7","pages":"26"},"PeriodicalIF":2.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13421831/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148580239","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":"3D Imaging and Measurement of Optic Nerve Sheath Diameter.","authors":"Ronald H Silverman, Cédric Venuat, Lionel Letoffet, Jeffrey A Ketterling","doi":"10.1167/tvst.15.7.11","DOIUrl":"10.1167/tvst.15.7.11","url":null,"abstract":"<p><strong>Purpose: </strong>The subarachnoid space between the dura and the pia mater is filled with cerebrospinal fluid, and, with elevated intracranial pressure, optic nerve sheath diameter (ONSD) will consequently increase. ONSD measurement thus serves as a non-invasive means for detecting intracranial hypertension. B-scans, however, only measure ONSD in a plane, and axial symmetry is assumed. In this study, we evaluated a novel ultrasound system for three-dimensional (3D) imaging and measurement of ONSD.</p><p><strong>Methods: </strong>We imaged both eyes of 18 subjects using 15-MHz B-scans and a prototype 3D system. In this system, a focused single-element transducer was moved in a spiral pattern to sweep out a volume in approximately 5 seconds. We compared transverse B-scan ONSD measurements with values derived from cross-sections of 3D scans.</p><p><strong>Results: </strong>Mean ONSD was 5.32 ± 0.79 mm by B-scan and 5.57 ± 0.61 mm by 3D. The larger measurement by 3D was borderline statistically significant (P = 0.05). The within-eye variability between repeated measurements was comparable. Bland-Altman analysis showed no trend associated with increasing or decreasing ONSD. Eccentricity of 3D ONSD best-fit ellipses to nerve coronal sections averaged 0.51 ± 0.098.</p><p><strong>Conclusions: </strong>The 3D prototype 5-second acquisition was faster than prior mechanical systems based on single element probes but still somewhat vulnerable to motion artifacts. The ability to assess the ONSD in three dimensions rather than as a transverse cross-section offers an avenue toward improved assessment of nerve anatomy and detection of intracranial hypertension.</p><p><strong>Translational relevance: </strong>3D imaging of the optic nerve offers improved assessment of changes associated with elevated intracranial pressure.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 7","pages":"11"},"PeriodicalIF":2.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13367202/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148412974","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":"AI for Anterior Segment Disease Using Transfer Learning: Adapting Slit-Lamp-Trained Model for Analysis of Smartphone Corneal Images.","authors":"Hiroki Maehara, Yuta Ueno, Masahiro Oda, Yoshikazu Ito, Yoshiyuki Kitaguchi, Dai Miyazaki, Ryohei Nejima, Takenori Inomata, Naoko Kato, Tai-Ichiro Chikama, Jun Ominato, Tatsuya Yunoki, Kinya Tsubota, Manabu Suzutani, Kensaku Mori, Takefumi Yamaguchi, Tetsuro Oshika","doi":"10.1167/tvst.15.7.24","DOIUrl":"10.1167/tvst.15.7.24","url":null,"abstract":"<p><strong>Purpose: </strong>The automated classification artificial intelligence (AI) for anterior segment corneal diseases that we developed is capable of classifying images into nine categories, including vision-threatening corneal diseases, such as infectious keratitis; however, it has been trained exclusively on slit-lamp images. We aimed to develop an AI model adaptable to smartphone images by applying transfer learning using smartphone images to the existing AI model. AI trained with transfer learning on smartphone images will be referred to as \"Phone-tuned AI.\"</p><p><strong>Methods: </strong>This study included 2530 images captured using smartphones, collected from multiple collaborating facilities between October 2021 and March 2024. Transfer learning was applied to two existing AI models (You Only Look Once version 5 [YOLOv5] and YOLOX) using these smartphone images, and the accuracy of the Phone-tuned AI was evaluated.</p><p><strong>Results: </strong>The average accuracy for each classification using smartphone images was 93.5% for Phone-tuned AI (YOLOv5) and 67.0% for Original AI (YOLOv5), showing a statistically significant improvement (P = 0.0033). Similarly, the accuracy was 84.2% for Phone-tuned AI (YOLOX) and 78.4% for Original AI (YOLOX), with no significant difference (P = 0.36). When diseases were categorized by urgency, the Phone-tuned AI (YOLOv5) achieved 94.8% for urgent, 89.7% for semi-urgent, 89.4% for routine, and 98.7% for observation-level cases.</p><p><strong>Conclusions: </strong>Phone-tuned AI has the potential to assist in diagnosis and triage in regions with a shortage of ophthalmologists, such as rural areas.</p><p><strong>Translational relevance: </strong>Transfer learning using smartphone images showed a particularly good fit with YOLOv5, resulting in high diagnostic accuracy and demonstrating strong potential for clinical application.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 7","pages":"24"},"PeriodicalIF":2.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13390727/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148473121","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}