Search Results (91)

Glaucoma is a leading cause of irreversible vision loss, and its early diagnosis remains critically important yet challenging. Traditional assessment based on the cup-to-disc ratio is often insufficient at early stages, whereas the retinal vascular network can provide additional quantitative biomarkers. This study develops and validates a binary classification method for distinguishing healthy from glaucomatous fundus images by combining deep-learning-based vessel segmentation, fractal and multifractal analysis, and textural features. The public ORIGA dataset is utilized. Images are converted to grayscale using three alternative approaches, followed by Gray-Level Co-occurrence Matrix texture analysis and fractal analysis based on the differential box-counting method. Vessel segmentation is implemented via a U-Net neural network trained on a combination of public datasets, after which multifractal analysis is performed on the resulting binary masks. The extracted features are used to train and compare several machine learning models with hyperparameter optimization. The best-performing model among ONH-based features (Random Forest) achieves 75.00%; however, a logistic regression model using multifractal parameters and CDR reaches 86.17%, substantially outperforming the CDR-only baseline (66.15%). Notably, while classical fractal dimension shows only marginal differences (1–2% relative change) between groups, multifractal parameters reveal distinct changes: the multifractal spectrum width $\Delta \alpha$ increases markedly and the minimum singularity exponent ${\alpha }_{\min }$ decreases in glaucomatous eyes, indicating increased heterogeneity of the vascular network. These findings suggest that multifractal characteristics of the vascular network can serve as reliable and sensitive biomarkers for automated glaucoma screening, offering clear advantages over classical fractal analysis. Full article

Background and Objectives: Non-invasive biomarkers reflecting neurodegeneration are increasingly important in multiple sclerosis (MS). Optical coherence tomography (OCT) provides quantitative measures of retinal structure, most commonly peripapillary retinal nerve fiber layer (pRNFL) thickness. However, the potential clinical relevance of optic nerve head morphology, including cup-to-disc ratio (CDR), remains insufficiently explored. We investigated associations between OCT-derived parameters, subjective visual vertical (SVV), and disability in MS. Materials and Methods: In this retrospective study, 100 patients with MS were included. OCT parameters (pRNFL thickness and area-based CDR) were analyzed at baseline and follow-up. Clinical disability was assessed using the Expanded Disability Status Scale (EDSS). Detailed optic neuritis history was not consistently available in the retrospective clinical records and therefore could not be systematically accounted for in the analyses. SVV was evaluated in 37 patients using a virtual reality–based protocol. Associations were assessed using Spearman correlation and linear regression analyses. Multivariable regression models were adjusted for age, sex, and follow-up duration. Results: pRNFL thickness was not associated with baseline EDSS (rho = −0.06, p = 0.55) or annualized EDSS change. Baseline CDR correlated with both baseline EDSS (rho = 0.30, p = 0.0065) and follow-up EDSS (rho = 0.46, p < 0.0001). In univariable regression analysis, baseline CDR was associated with follow-up EDSS (B = 3.33, R² = 0.23, p < 0.0001), remaining significant after adjustment for age, sex, and follow-up duration (B = 2.59, 95% CI 1.26–3.92, p = 0.0002). No significant associations were observed between OCT parameters and SVV measures. Conclusions: Higher CDR values, but not pRNFL thickness, were associated with disability measures in this exploratory MS cohort. However, these findings should be interpreted cautiously because optic neuritis history could not be systematically accounted for and physiological optic disc variability may substantially influence CDR measurements. Full article

Glaucoma affects a significant proportion of people worldwide, and if it progresses to a severe stage, it can lead to blindness. Furthermore, screening and accurately diagnosing glaucoma present a challenge for ophthalmologists. Early detection of glaucoma is crucial because it allows for timely treatment, potentially preventing severe complications that could lead to blindness. Typically, ophthalmologists diagnose glaucoma by analyzing eye fundus photographs to assess the ratio of the optic cup and optic disc (CDR). Machine learning algorithms can assist in glaucoma detection by classifying fundus images. This study introduces image preprocessing techniques for optic disc localization, combined with an integrating multi-view network for accurate glaucoma classification. The dataset used in this research was obtained from Naresuan University Hospital. The study found that EfficientNet underwent training using the Adam optimizer at a fixed learning rate of 0.0001. The multi-view network achieved Accuracy 90.48%, AUC 95.14%, Precision 81.95%, Recall 75.90%, and F1-score 78.72%. This study presents an effective approach to assist ophthalmologists in detecting early-stage glaucoma and glaucoma, thereby improving diagnostic efficiency. Full article

Eye diseases, such as glaucoma, diabetic retinopathy, and age-related macular degeneration, drive the growing need for reliable and scalable analyses of fundus and optical coherence tomography (OCT) images. Deep learning performs strongly in ocular structure segmentation. However, it typically relies on dense pixel-wise annotations, which are costly and difficult to obtain at scale. Weakly supervised learning (WSL) can reduce this burden by leveraging coarse labels, limited strong annotations, and unlabeled data. This systematic umbrella review synthesizes survey and review articles on weakly supervised deep learning for image segmentation, with a focus on ocular imaging (fundus and OCT/OCTA). After analyzing twenty-one secondary studies, the main finding reveals an “empty intersection”: WSL-focused segmentation surveys are often modality-agnostic. Conversely, ocular reviews are predominantly fully supervised and seldom offer quantitative evidence on annotation-effort savings or direct comparisons between weak and fully supervised methods on identical datasets. Across the included reviews, label-efficient strategies cluster around CAM/MIL formulations, sparse supervision (points/scribbles/boxes), pseudo-labelling/self-training, and semi-/self-supervised learning, implemented mainly with U-Net/DeepLab families and increasingly Transformer or hybrid backbones. These results provide a structured map of available WSL mechanisms and, critically, identify reproducible reporting gaps that currently prevent fair benchmarking in ocular segmentation. Therefore, this review supports the development of ocular-specific benchmarks and minimum reporting practices that link segmentation performance to annotation effort. Full article

Background/Objectives: Reversibility of glaucomatous optic-disc cupping, following intraocular pressure (IOP) reduction, represents a fascinating structural response observed in both pediatric and adult patients. This review summarizes evidence on its mechanisms, diagnostic evaluation, and clinical significance. Methods: A comprehensive review of experimental, clinical, and imaging-based studies investigating optic-disc cupping reversibility was conducted. Findings were categorized by patient population, imaging technique, and follow-up duration. Results: Experimental models established a strong correlation between IOP reduction and optic-disc structural recovery. Pediatric glaucoma demonstrated the greatest reversibility due to enhanced ocular tissue elasticity, whereas adult cases showed limited yet measurable structural changes after sustained IOP lowering. Imaging modalities, including confocal scanning laser ophthalmoscopy and spectral-domain optical coherence tomography (SD-OCT), consistently confirmed quantitative disc-shape changes correlated with pressure reduction. Conclusions: Although optic-disc cupping reversal reflects biomechanical and glial remodeling rather than true neuronal recovery, it remains an important biomarker of successful IOP control. Advanced imaging provides valuable insights into optic-nerve-head (ONH) biomechanics and may improve glaucoma management. Full article

Purpose: This study investigates the association between obstructive sleep apnea (OSA), dry eye disease (DED), and glaucoma, focusing on the impact of positive airway pressure (PAP) usage and air leakage. Methods: This retrospective cross-sectional study included 57 adults with polysomnography-confirmed OSA between 2010 and 2023. Participants were grouped into PAP users (PAP+, n = 40) and non-users (PAP−, n = 17). Ocular assessments included tear film break-up time, Schirmer’s test, Oxford staining, meibomian gland evaluation, intraocular pressure, cup-to-disc (C/D) ratio, and retinal nerve fiber layer thickness. PAP device data (usage duration and air leak rate) and OSA severity metrics were recorded. Group comparisons used chi-square and Student’s t-test, and regression analyses identified associations between PAP leakage and ocular parameters. Results: Among the 57 OSA patients, PAP users showed a trend toward a higher risk of glaucoma (OR = 0.83) and DED (OR = 0.69) compared to non-users, but neither trend was statistically significant. PAP users had significantly more severe OSA, including longer N1 sleep stage (p = 0.0005), higher apnea-hypopnea index (AHI, p = 0.0001), and poorer oxygenation. PAP leakage: 95% (mean = 25.84 L/min) exceeded the 24 L/min threshold specified in ResMed’s clinical guidelines, suggesting suboptimal therapy. Higher PAP leak was significantly associated with a lower Schirmer’s test value (p = 0.031) and a higher C/D ratio (p = 0.040) on regression analysis. However, no significant differences were found in ophthalmic parameters between PAP+ and PAP− groups. Conclusions: Suboptimal PAP therapy as mask leakage or nocturnal hemodynamic changes may worsen evaporative dry eye and affect intraocular pressure. Our findings highlight the association between PAP mask leakage and reduced tear production, and suggest that OSA-related optic nerve stress may persist unless both hypoxia and nocturnal IOP fluctuations are properly managed. However, due to the relatively small sample size and retrospective cross-sectional design, future prospective studies with larger cohorts are needed to confirm these associations. Full article

Background: Trabeculectomy remains gold-standard surgical approach for intraocular pressure (IOP) control in glaucoma, yet its impact on optic nerve head (ONH) morphology and retinal microvasculature has not been fully clarified. This study aimed to investigate structural and vascular changes of the ONH and macula after trabeculectomy using spectral-domain optical coherence tomography (SD-OCT) and OCT angiography (OCTA). Methods: In this retrospective study, data from 22 patients with primary open-angle glaucoma who underwent uncomplicated trabeculectomy were reviewed. The fellow eye served as control. Structural parameters, including Bruch’s membrane opening (BMO), maximum cup depth (MCD), and cup area, were measured with SD-OCT. Vessel density (VD) of the optic disc, peripapillary retina, and macular superficial (SCP) and deep (DCP) capillary plexuses were analyzed with OCTA. Preoperative and two-month postoperative data were compared using paired statistical tests. Results: Mean IOP decreased from 23.1 ± 3.9 mmHg to 13.2 ± 3.2 mmHg (p < 0.001). Significant postoperative reductions were observed in BMO (−5 ± 6%, p = 0.004), MCD (−31 ± 8%, p < 0.001), and cup area (−44 ± 18%, p < 0.001). RNFL thickness and ONH vascular parameters remained stable. In contrast, DCP vessel density increased in the foveal (p = 0.002) and parafoveal (p = 0.023) regions, while SCP density showed no significant change. Conclusions: Trabeculectomy was associated with measurable reversal of optic disc cupping, indicating partial structural recovery of the ONH following IOP reduction. The selective improvement in deep retinal vessel density suggests a layer-specific microvascular response. These findings provide further insight into the interplay between mechanical and vascular mechanisms in glaucoma and may inform postoperative monitoring strategies. Full article

Multiple ocular diseases frequently coexist in fundus images, while image quality is highly susceptible to imaging conditions and patient cooperation, often manifesting as blurring, underexposure, and indistinct lesion regions. These challenges significantly hinder robust multi-disease joint classification. To address this, we propose a novel framework, BiNeXt-SMSMVL (Bilateral ConvNeXt-based Structure-aware Multi-scale Multi-view Learning Network), that integrates structural medical biomarkers with deep semantic image features for robust multi-class fundus disease recognition. Specifically, we first employ automatic segmentation to extract the optic disc/cup and vascular structures, calculating medical biomarkers such as vertical/horizontal cup-to-disc ratio (CDR), vessel density, and fractal dimension as structural priors for classification. Simultaneously, a ConvNeXt-Tiny backbone extracts multi-scale visual features from raw fundus images, enhanced by SENet channel attention mechanisms to improve feature representation. Architecturally, the model performs independent predictions on left-eye, right-eye, and fused binocular images, leveraging multi-view ensembling to enhance decision stability. Structural priors and image features are then fused for joint classification modeling. Experiments on public datasets demonstrate that our model maintains stable performance under variable image quality and significant lesion heterogeneity, outperforming existing multi-label classification methods in key metrics including F1-score and AUC. Also, our approach exhibits strong robustness, interpretability, and clinical applicability. Full article

Background: Optical coherence tomography (OCT) is the main diagnostic technology used to detect damage to the retinal ganglion cells (RGCs) in glaucoma. However, it remains unclear which OCT parameter demonstrates the best diagnostic performance for eyes with early, especially preperimetric glaucoma (PPG). We determined the diagnostic performance of ganglion cell–inner plexiform layer (GCIPL) parameters using spectral-domain OCT (SD-OCT) in primary open-angle preperimetric and early perimetric glaucoma and compared them with optic nerve head (ONH) and peripapillary retinal nerve fiber layer (pRNFL) parameters. Methods: We analyzed 101 eyes: 36 normal eyes, 33 with PPG, and 32 with early perimetric glaucoma. All patients underwent Topcon SD–OCT imaging using the Optic Disc and Macular Vertical protocols. The diagnostic abilities of the GCIPL, rim area, vertical cup-to-disc ratio (CDR), and pRNFL were assessed using the area under the receiver operating characteristic curve (AUC). Results: For PPG, the AUCs ranged from 0.60 to 0.63 (GCIPL), 0.82 to 0.86 (ONH), and 0.49 to 0.75 (pRNFL). For early perimetric glaucoma, the AUCs for GCIPL and pRNFL ranged from 0.81 to 0.88 and 0.57 to 0.91, respectively, whereas both ONH parameters demonstrated an AUC of 0.89. The GCIPL parameters were significantly lower than both ONH parameters in detecting preperimetric glaucoma (p < 0.05). For early perimetric glaucoma, comparisons between the AUCs of the best-performing mGCIPL parameters and those of the best-performing pRNFL and ONH parameters revealed no significant differences in their diagnostic abilities (p > 0.05). Conclusions: GCIPL parameters exhibited a diagnostic performance comparable to that of ONH and pRNFL parameters for early perimetric glaucoma. However, their ability to detect preperimetric glaucoma was significantly lower than the ONH parameters. Full article

Glaucoma is an eye disease caused by increased intraocular pressure (IOP) that affects the optic nerve head (ONH), leading to vision problems and irreversible blindness. Background/Objectives: Glaucoma is the second leading cause of blindness worldwide, and the number of people affected is increasing each year, with the number expected to reach 111.8 million by 2040. This escalating trend is alarming due to the lack of ophthalmology specialists relative to the population. This study proposes an explainable end-to-end pipeline for automated glaucoma diagnosis from fundus images. It also evaluates the performance of Vision Transformers (ViTs) relative to traditional CNN-based models. Methods: The proposed system uses three datasets: REFUGE, ORIGA, and G1020. It begins with YOLOv11 for object detection of the optic disc. Then, the optic disc (OD) and optic cup (OC) are segmented using U-Net with ResNet50, VGG16, and MobileNetV2 backbones, as well as MaskFormer with a Swin-Base backbone. Glaucoma is classified based on the vertical cup-to-disc ratio (vCDR). Results: MaskFormer outperforms all models in segmentation in all aspects, including IoU OD, IoU OC, DSC OD, and DSC OC, with scores of 88.29%, 91.09%, 93.83%, and 93.71%. For classification, it achieved accuracy and F1-scores of 84.03% and 84.56%. Conclusions: By relying on the interpretable features of the vCDR, the proposed framework enhances transparency and aligns well with the principles of explainable AI, thus offering a trustworthy solution for glaucoma screening. Our findings show that Vision Transformers offer a promising approach for achieving high segmentation performance with explainable, biomarker-driven diagnosis. Full article

Multiple sclerosis (MS), a chronic disease of the central nervous system, is known to cause structural and vascular changes in the retina. Although optical coherence tomography (OCT) and fundus photography can detect retinal thinning and circulatory abnormalities, these findings are not specific to MS. This study explores the potential of Infrared Scanning-Laser-Ophthalmoscopy (IR-SLO) imaging to uncover vascular morphological features that may serve as MS-specific biomarkers. Using an age-matched, subject-wise stratified k-fold cross-validation approach, a deep learning model originally designed for color fundus images was adapted to segment optic disc, optic cup, and retinal vessels in IR-SLO images, achieving Dice coefficients of 91%, 94.5%, and 97%, respectively. This process included tailored pre- and post-processing steps to optimize segmentation accuracy. Subsequently, clinically relevant features were extracted. Statistical analyses followed by SHapley Additive exPlanations (SHAP) identified vessel fractal dimension, vessel density in zones B and C (circular regions extending 0.5–1 and 0.5–2 optic disc diameters from the optic disc margin, respectively), along with vessel intensity and width, as key differentiators between MS patients and healthy controls. These findings suggest that IR-SLO can non-invasively detect retinal vascular biomarkers that may serve as additional or alternative diagnostic markers for MS diagnosis, complementing current invasive procedures. Full article

Background: This case–control study evaluated the concentrations of zinc (Zn), iron (Fe), and copper (Cu) in the aqueous humor (AH) of patients with primary glaucoma, and their relationships with clinical factors. Methods: This study enrolled 100 patients with primary glaucoma and categorized them into subtypes: acute angle-closure crisis (AACC), primary angle-closure glaucoma (PACG), and primary open-angle glaucoma (POAG). A total of 67 patients with senile cataract were enrolled as controls. Their AH samples and clinical information were obtained. Results: In primary glaucoma, Zn, Fe, and Cu concentrations increased, especially in AACC group; Zn, Fe, and Cu were positively correlated mutually; and decreased Zn/Fe and increased Fe/Cu were observed. The number of quadrants with closed anterior chamber angle on gonioscopy was positively associated with Fe and Cu levels in AACC and with Zn and Cu levels in PACG. In POAG, we found negative associations between Zn and the number of quadrants with retinal nerve fiber layer thinning on optical coherence tomography, Fe and age, and Cu and the cup-to-disc ratio. Trace metals showed high efficiency in discriminating primary glaucoma from controls. Conclusions: Zn, Fe, and Cu concentrations in patients with primary glaucoma increased and were associated with clinical factors, acting as potential biomarkers. Full article

Segmentation of the Optic Disc (OD) and Optic Cup (OC) boundaries in fundus images is a critical step for early glaucoma diagnosis, but accurate segmentation is challenging due to low boundary contrast and significant anatomical variability. To address these challenges, this study proposes a novel segmentation framework that integrates structure-preserving data augmentation, Boundary-aware Transformer Attention (BAT), and Geometry-aware Loss. We enhance data diversity while preserving vascular and tissue structures through truncated Gaussian-based sampling and colormap transformations. BAT strengthens boundary recognition by globally learning the inclusion relationship between the OD and OC within the skip connection paths of U-Net. Additionally, Geometry-aware Loss, which combines the normalized Hausdorff Distance with the Dice Loss, reduces fine-grained boundary errors and improves boundary precision. The proposed model outperforms existing state-of-the-art models across five public datasets—DRIONS-DB, Drishti-GS, REFUGE, G1020, and ORIGA—and achieves Dice scores of 0.9127 on Drishti-GS and 0.9014 on REFUGE for OC segmentation. For joint segmentation of the OD and OC, it attains high Dice scores of 0.9892 on REFUGE, 0.9782 on G1020, and 0.9879 on ORIGA. Ablation studies validate the independent contributions of each component and demonstrate their synergistic effect when combined. Furthermore, the proposed model more accurately captures the relative size and spatial alignment of the OD and OC and produces smooth and consistent boundary predictions in clinically significant regions such as the region of interest (ROI). These results support the clinical applicability of the proposed method in medical image analysis tasks requiring precise, boundary-focused segmentation. Full article

Accurate glaucoma diagnosis relies on precise segmentation of the optic disc (OD) and optic cup (OC) in retinal images. However, despite the development of numerous automatic segmentation models, the lack of annotations in the target domain and domain shift among datasets continue to limit their segmentation performance. To address these issues, we propose a Causal Self-Supervised Network (CSSN) that leverages self-supervised learning to enhance model performance. First, we construct a Structural Causal Model (SCM) and employ backdoor adjustment to convert the conventional conditional distribution into an interventional distribution, effectively severing the influence of style information on feature extraction and pseudo-label generation. Subsequently, the low-frequency components of source and target domain images are exchanged via Fourier transform to simulate cross-domain style transfer. The original target images and their style-transferred counterparts are then processed by a dual-path segmentation network to extract their respective features, and a confidence-based pseudo-label fusion strategy is employed to generate more reliable pseudo-labels for self-supervised learning. In addition, we employ adversarial training and cross-domain contrastive learning to further reduce style discrepancies between domains. The former aligns feature distributions across domains using a feature discriminator, effectively mitigating the adverse effects of style inconsistency, while the latter minimizes the feature distance between original and style-transferred images, thereby ensuring structural consistency. Experimental results demonstrate that our method achieves more accurate OD and OC segmentation in the target domain during testing, thereby confirming its efficacy in cross-domain adaptation tasks. Full article

Glaucoma is a visual disease that affects millions of people, and early diagnosis can prevent total blindness. One way to diagnose the disease is through fundus image examination, which analyzes the optic disc and cup structures. However, screening programs in primary care are costly and unfeasible. Neural network models have been used to segment optic nerve structures, assisting physicians in this task and reducing fatigue. This work presents a methodology to enhance morphological biomarkers of the optic disc and cup in images obtained by a smartphone coupled to an ophthalmoscope through a deep neural network, which combines two backbones and a dual decoder approach to improve the segmentation of these structures, as well as a new way to combine the loss weights in the training process. The models obtained were numerically evaluated through Dice and IoU measures. The dice values obtained in the experiments reached a Dice of 95.92% and 85.30% for the optical disc and cup and an IoU of 92.22% and 75.68% for the optical disc and cup, respectively, in the BrG dataset. These findings indicate promising architectures in the fundus image segmentation task. Full article