Search Results (957)

Background/Objectives: Infectious keratitis remains a major cause of blindness worldwide, and many cases progress to therapeutic keratoplasty despite advances in antimicrobial therapy. This systematic review aims to evaluate the outcomes of therapeutic keratoplasty in microbial keratitis and examine factors influencing anatomical success, graft survival, and visual rehabilitation. Methods: A systematic review was conducted following PRISMA guidelines, including English-language studies, published between 2000 and 2025. Studies with ≥10 eyes and ≥6 months follow-up were included. Data on infection control, graft clarity, anatomical success, visual acuity, and complications were extracted. Results: Fourteen studies encompassing 1527 eyes were analyzed. TPK accounted for 89% of procedures; DALK was used selectively for anterior or mid-stromal infections. Overall infection control ranged from 69 to 100%, with globe preservation in 85–100% of cases. Bacterial keratitis had higher cure rates and graft clarity than fungal or Acanthamoeba keratitis. Larger grafts (>8 mm) and deep stromal involvement were associated with increased graft rejection and postoperative complications. DALK offered higher graft survival and lower immunologic risk when the endothelium was spared. Visual outcomes were generally limited, reflecting preoperative disease severity, timing of surgery, and postoperative immunomodulation constraints. Early surgical intervention improved anatomical outcomes in severe fungal keratitis. Conclusions: Therapeutic keratoplasty is an effective globe-preserving intervention in advanced microbial keratitis, but with limited functional outcomes. Further prospective studies are needed to refine surgical indications, postoperative management, and long-term functional results. Full article

Meibomian gland dysfunction (MGD) is a leading cause of dry eye disease, assessable through gland atrophy degree. While deep learning (DL) has advanced meibomian gland (MG) segmentation and MGD classification, existing methods treat these tasks independently and suffer from domain shift across multi-center imaging devices. We propose ADAM-Net, an attention-guided unsupervised domain adaptation multi-task framework that jointly models MG segmentation and MGD classification. Our model introduces structure-aware multi-task learning and anatomy-guided attention to enhance feature sharing, suppress background noise, and improve glandular region perception. For the cross-domain tasks MGD-1K→{K5M, CR-2, LV II}, this study systematically evaluates the overall performance of ADAM-Net from multiple perspectives. The experimental results show that ADAM-Net achieves classification accuracies of 77.93%, 74.86%, and 81.77% on the target domains, significantly outperforming current mainstream unsupervised domain adaptation (UDA) methods. The F1-score and the Matthews correlation coefficient (MCC-score) indicate that the model maintains robust discriminative capability even under class-imbalanced scenarios. t-SNE visualizations further validate its cross-domain feature alignment capability. These demonstrate that ADAM-Net exhibits strong robustness and interpretability in multi-center scenarios and provide an effective solution for automated MGD assessment. Full article

This study presents DeepVisionAnalytics, an integrated framework that combines eye tracking, OpenCV-based computer vision (CV), and machine learning (ML) to support objective analysis of consumer behaviour in visually driven tasks. Unlike conventional self-reported surveys, which are prone to cognitive bias, recall errors, and social desirability effects, the proposed approach relies on direct behavioural measurements of visual attention. The system captures gaze distribution and fixation dynamics during interaction with products or interfaces. It uses AOI-level eye tracking metrics as the sole behavioural signal to infer candidate choice under constrained experimental conditions. In parallel, OpenCV and ML perform facial analysis to estimate demographic attributes (age, gender, and ethnicity). These attributes are collected independently and linked post hoc to gaze-derived outcomes. Demographics are not used as predictive features for choice inference. Instead, they are used as contextual metadata to support stratified, segment-level interpretation. Empirical results show that gaze-based inference closely reproduces observed choice distributions in short-horizon, visually driven tasks. Demographic estimates enable meaningful post hoc segmentation without affecting the decision mechanism. Together, these results show that multimodal integration can move beyond descriptive heatmaps. The platform produces reproducible decision-support artefacts, including AOI rankings, heatmaps, and segment-level summaries, grounded in objective behavioural data. By separating the decision signal (gaze) from contextual descriptors (demographics), this work contributes a reusable end-to-end platform for marketing and UX research. It supports choice inference under constrained conditions and segment-level interpretation without demographic priors in the decision mechanism. Full article

This paper presents a novel hybrid multimodal deep learning model for robust and real-time eye gaze estimation. Accurate gaze tracking is essential for advancing human–computer interaction (HCI) and assistive technologies, but existing methods often struggle with environmental variations, require extensive calibration, and are computationally intensive. Our proposed model, GazeNet-HM, addresses these limitations by synergistically fusing features from RGB, depth, and infrared (IR) imaging modalities. This multimodal approach allows the model to leverage complementary information: RGB provides rich texture, depth offers invariance to lighting and aids pose estimation, and IR ensures robust pupil detection. Furthermore, we introduce a personalized adaptation module that dynamically fine-tunes the model to individual users with minimal calibration data. To ensure practical deployment, we employ advanced model compression techniques, enabling real-time inference on resource-constrained embedded systems. Extensive evaluations on public datasets (MPIIGaze, EYEDIAP, Gaze360) and our collected M-Gaze dataset demonstrate that GazeNet-HM achieves state-of-the-art performance, reducing the mean angular error by up to 27.1% compared to leading unimodal methods. After model compression, the system achieves a real-time inference speed of 32 FPS on an embedded Jetson Xavier NX platform. Ablation studies confirm the contribution of each modality and component, highlighting the effectiveness of our holistic design. Full article

Background/Objectives: Keratoconus, a condition in which the cornea becomes thinner and steeper, can cause visual problems, particularly when it is progressive. Early diagnosis is important for preserving visual acuity. Raw data, unlike preprocessed data, are unaffected by software modifications. They retain their native structure across versions, providing consistency for analytical purposes. The objective of this study was to design a deep learning-based graphical user interface for predicting the corneal ectasia score using raw optical coherence tomography data. Methods: The graphical user interface was developed using Tkinter, a Python library for building graphical user interfaces. The user is allowed to select raw data from the cornea/anterior segment optical coherence tomography Casia2, which is generated in the 3dv format, from the local system. To view the predicted corneal ectasia score, the user must determine whether the selected 3dv file corresponds to the left or right eye. Extracted optical coherence tomography images are cropped, resized to 224 × 224 pixels and processed by the modified EfficientNet-B0 convolutional neural network to predict the corneal ectasia score. The predicted corneal ectasia score value is displayed along with a diagnosis: ‘No detectable ectasia pattern’ or ‘Suspected ectasia’ or ‘Clinical ectasia’. Performance metric values were rounded to four decimal places, and the mean absolute error value was rounded to two decimal places. Results: The modified EfficientNet-B0 obtained a mean absolute error of 6.65 when evaluated on the test dataset. For the two-class classification, it achieved an accuracy of 87.96%, a sensitivity of 82.41%, a specificity of 96.69%, a PPV of 97.52% and an F1 score of 89.33%. For the three-class classification, it attained a weighted-average F1 score of 84.95% and an overall accuracy of 84.75%. Conclusions: The graphical user interface outputs numerical ectasia scores, which improves other categorical labels. The graphical user interface enables consistent diagnostics, regardless of software updates, by using raw data from the Casia2. The successful use of raw optical coherence tomography data indicates the potential for raw optical coherence tomography data to be used, rather than preprocessed optical coherence tomography data, for diagnosing keratoconus. Full article

The deployment of Advanced Driver-Assistance Systems (ADAS) in economically constrained markets frequently relies on hardware architectures that lack dedicated graphics processing units. Within such environments, the integration of deep neural networks faces significant hurdles, primarily stemming from strict limitations on energy consumption, the absolute necessity for deterministic real-time response, and the rigorous demands of safety certification protocols. Meanwhile, traditional geometry-based lane detection pipelines continue to exhibit limited robustness under adverse illumination conditions, including intense backlighting, low-contrast nighttime scenes, and heavy rainfall. Motivated by these constraints, this work re-examines geometry-based lane perception from a sensor-level viewpoint and introduces a Binary Line Segment Filter (BLSF) that leverages the inherent structural regularity of lane markings in bird’s-eye-view (BEV) imagery within a computationally lightweight framework. The proposed BLSF is integrated into a complete pipeline consisting of inverse perspective mapping, median local thresholding, line-segment detection, and a simplified Hough-style sliding-window fitting scheme combined with RANSAC. Experiments on a self-collected dataset of 297 challenging frames show that the inclusion of BLSF significantly improves robustness over an ablated baseline while sustaining real-time performance on a 2 GHz ARM CPU-only platform. Additional evaluations on the Dazzling Light and Night subsets of the CULane and LLAMAS benchmarks further confirm consistent gains of approximately 6–7% in F₁-score, together with corresponding improvements in IoU. These results demonstrate that interpretable, geometry-driven lane feature extraction remains a practical and complementary alternative to lightweight learning-based approaches for cost- and safety-critical ADAS applications. Full article

Background/Objectives: Hemodialysis (HD) is the commonest life sustaining form of kidney replacement therapy in the world; however, this method of treatment have many adverse effects, and even a single HD session affects many organs, including the eyes. The aim of this study was to assess the effect of a single HD session on the ophthalmologic findings in patients with End-stage Renal Disease (ESRD). The second aim of the study was to examine the correlation of these changes with each other and between changes in systemic stressors related to the HD session. Methods: This was a single-center cross-sectional observational study conducted on 32 patients undergoing HD. Selected parameters of the anterior and posterior segment of the eye as well as systemic parameters were assessed before and after a single HD session. Results: Best corrected visual acuity (BCVA) improved, and lens thickness (LT), axial length (AXL), average macular thickness (MT), central MT and total vessel density (VD) of the deep capillary plexus DCP increased significantly after a single HD session. The Schirmer test results, tear break up time (TBUT), anterior chamber depth (ACD), central and average choroidal thickness (CT) decreased significantly after HD. Body weight loss was the only significant systemic change. Decrease in TBUT correlated positively with Schirmer’s test results decrease. Increase in CCT correlated positively with AXL increase. Decrease in central and average CT correlated positively with IOP decrease. Increase in central MT correlated positively with increase in average MT. Decrease in central CT correlated positively with average CT decrease. Change in VD of the SCP correlated positively with change in VD of DCP. Apart from the positive correlation between SBP change and Schirmer’s test results change, there were no correlations between systemic and ophthalmic parameters changes. Conclusions: Our study showed that HD affected the parameters of the anterior and posterior segments of the eye. Numerous correlations between these changes suggest that they are interrelated and represent the complex response of the eye to the HD process. Full article

Background: To investigate baseline MNV characteristics in Optical Coherence Tomography Angiography (OCTA) and its impact on therapeutic needs and visual acuity after 5 years in initially therapy-naïve eyes. Methods: A retrospective study of 43 therapy-naïve eyes with neovascular AMD (nAMD). OCTA was performed at baseline and all eyes were observed for 5 years. MNV architecture was characterized by area, total vessel length, flow density and fractal dimension. These variables were tested for correlation with the number of administered intravitreal injections (IVIs) and best-corrected visual outcome (BCVA) after 5 years of treatment. Results: Mean follow-up time was 4.97 ± 0.21 years. Area and total vessel length of MNVs were significantly associated with a higher number of administered IVIs after 5 years (p < 0.05), flow density significantly correlated with fewer IVIs (p < 0.05). Fractal dimension showed a tendency to more IVIs (p = 0.056) after 5 years. Flow density at baseline correlated with a better BCVA (p < 0.05). In contrast, MNV area size, total vessel length and fractal dimension did not show any correlation to BCVA after 5 years (p > 0.05). Conclusions: Specific features of MNV architecture such as area, total vessel length and flow density can predict long-term treatment requirement and visual outcome. Further studies using deep learning algorithms are necessary to explore the usage of these findings in daily practice. Full article

Safety on construction sites is an essential yet challenging issue due to the inherently hazardous nature of these sites. Workers are expected to wear Personal Protective Equipment (PPE), such as helmets, vests, and safety glasses, to prevent or minimize their exposure to injuries. However, ensuring compliance remains difficult, particularly in large or complex sites, which require a time-consuming and usually error-prone manual inspection process. The research proposes an automated PPE detection system utilizing the deep learning model YOLO11, which is trained on the CHVG dataset, to identify in real-time whether workers are adequately equipped with the necessary gear. The proposed PPE-EYE method, using YOLO11x, achieved a mAP50 of 96.9% and an inference time of 7.3 ms, which is sufficient for real-time PPE detection systems, in contrast to previous approaches involving the same dataset, which required 170 ms. The model achieved these results by employing data augmentation and fine-tuning. The proposed solution provides continuous monitoring with reduced human oversight and ensures timely alerts if non-compliance is detected, allowing the site manager to act promptly. It further enhances the effectiveness and reliability of safety inspections, overall site safety, and reduces accidents, ensuring consistency in follow-through of safety procedures to create a safer and more productive working environment for all involved in construction activities. Full article

Vitamin D deficiency is increasingly recognized as a systemic factor influencing retinal health through inflammatory, neuroprotective, and vasculotropic pathways. Evidence regarding early retinal alterations in otherwise healthy adults remains limited. This cross-sectional study evaluated 120 eyes from 60 healthy adults stratified by serum 25(OH)D levels into <30 ng/mL (n = 60) and ≥30 ng/mL (n = 60). All subjects underwent optical coherence tomography (OCT), OCT angiography (OCTA), visual field testing, and contrast sensitivity assessment. Central macular thickness (CMT), ganglion cell complex (GCC) thickness, and perfusion density in the superficial and deep capillary plexuses (SCP, DCP) were compared between groups. Vitamin-D-insufficient eyes showed significantly reduced CMT (267.66 ± 13.31 µm vs. 274.69 ± 14.96 µm; p = 0.035). GCC thinning was significant only in the inner inferior nasal sector (70.7 ± 13.14 µm vs. 76.45 ± 12.12 µm; p = 0.030), whereas other GCC sectors were comparable between groups. Perfusion density was lower in the DCP across whole, inner, and outer regions (all p < 0.001) and in the SCP inner (p = 0.027) and outer (p = 0.009) regions, while whole SCP did not differ (p = 0.065). FAZ area was numerically larger in vitamin-D-insufficient eyes but was not statistically different (p = 0.168). Functionally, retinal sensitivity decline was greater in vitamin-D-insufficient eyes (−2.89 ± 1.29 dB vs. −2.16 ± 1.04 dB; p = 0.003), and mean central sensitivity was lower (p = 0.010), whereas contrast sensitivity did not differ between groups. Serum vitamin D levels < 30 ng/mL are associated with early, subclinical, structural and microvascular retinal alterations in healthy adults, supporting a potential role of hypovitaminosis D as a modifier of retinal integrity. Full article

Background/Objectives: Forensic DNA phenotyping (FDP) enables the prediction of externally visible characteristics (EVCs) such as eye, hair, and skin color, ancestry, and age from biological traces. However, low template DNA (LT-DNA), often derived from degraded or trace samples, poses significant challenges due to allelic dropout, contamination, and incomplete profiles. This review evaluates recent advances in FDP from LT-DNA, focusing on the integration of machine learning (ML) models to improve predictive accuracy and operational readiness, while addressing ethical and population-related considerations. Methods: A comprehensive literature review was conducted on FDP and ML applications in forensic genomics. Key areas examined include SNP-based trait modeling, genotype imputation, epigenetic age estimation, and probabilistic inference. Comparative performance of ML algorithms (Random Forests, Support Vector Machines, Gradient Boosting, and deep learning) was assessed using datasets such as the 1000 Genomes Project, UK Biobank, and forensic casework samples. Ethical frameworks and validation standards were also analyzed. Results: ML approaches significantly enhance phenotype prediction from LT-DNA, achieving AUC > 0.9 for eye color and improving SNP recovery by up to 15% through imputation. Tools like HIrisPlex-S and VISAGE panels remain robust for eye and hair color, with moderate accuracy for skin tone and emerging capabilities for age and facial morphology. Limitations persist in admixed populations and traits with polygenic complexity. Interpretability and bias mitigation remain critical for forensic admissibility. Conclusions: L integration strengthens FDP from LT-DNA, offering valuable investigative leads in challenging scenarios. Future directions include multi-omics integration, portable sequencing platforms, inclusive reference datasets, and explainable AI to ensure accuracy, transparency, and ethical compliance in forensic applications. Full article

Background/Objectives: Thyroid eye disease (TED) can lead to structural and microvascular changes in the orbit and retina. This study aimed to investigate the associations between Clinical Activity Score (CAS), orbital magnetic resonance imaging (MRI) measurements, and retinal microvascular changes in TED patients. Methods: This cross-sectional study included 38 patients (76 eyes) with TED. Each patient underwent a comprehensive ophthalmological evaluation, CAS assessment, and a detailed medical history. Optical coherence tomography angiography (OCTA) was performed to quantify vessel density (VD) in the superficial and deep capillary plexus (SCP and DCP). Exophthalmos, extraocular muscle thickness and orbital fat thickness were measured on MRI scans to evaluate structural changes. Laboratory analyses included thyroid hormone levels, thyrotropin receptor antibodies (TRAb), anti-thyroid peroxidase antibodies (anti-TPO), and lipid profile. Results: Active TED patients (CAS ≥ 3) had significantly higher TRAb levels (p < 0.001), while anti-TPO did not differ between groups. Active eyes showed significantly higher DCP VD in the whole image (p = 0.013), parafovea (p = 0.012), and perifovea (p = 0.009) across all quadrants, with no difference in SCP or the foveal avascular zone (FAZ). In linear mixed model regression analyses, after adjusting for previous glucocorticosteroid therapy, higher triglycerides, greater medial rectus thickness, and whole-image DCP VD independently predicted higher CAS values (R² = 42, p < 0.001). After adjusting for age and sex, CAS remained significantly positive predictor of DCP VD in the parafovea (R² = 0.22, p < 0.001). Conclusions: Changes in DCP VD reflect TED activity and structural orbital involvement. Full article

Background/Objectives: Alzheimer’s disease (AD) is the leading cause of dementia, which is an inevitable consequence of aging. Early detection of AD, or detection during the pre-AD stage, is beneficial, as it enables timely intervention to reduce modifiable risk factors, which may help prevent or delay the progression to dementia. On the one hand, plasma biomarkers have demonstrated great promise in predicting cognitive decline. On the other hand, in recent years, ocular imaging features, particularly the thickness of retinal layers measured by spectral-domain optical coherence tomography (SD-OCT), are emerging as possible non-invasive, non-contact surrogate markers for early detection and monitoring of neurodegeneration. This pilot study aims to identify retinal layer thickness changes across the entire retina linked to plasma AD biomarkers in cognitively healthy (CH) elderly individuals at risk for AD. Methods: Eleven CH individuals (20 eyes total) were classified in the pre-AD stage by plasma β-amyloid (Aβ)42/40 ratio < 0.10 and underwent SD-OCT. A deep-learning-derived automated algorithm was used to segment retinal layers on OCT (with manual correction when needed). Multiple layer thicknesses throughout the entire retina (including the inner retina, the outer retina, and the choroid) were measured in the inner ring (1–3 mm) and outer ring (3–6 mm) of the Early Treatment Diabetic Retinopathy Study (ETDRS). Relationships between retinal layers and plasma biomarkers were analyzed by ridge regression/bootstrapping. Results: Results showed that photoreceptor inner segment (PR-IS) thinning had the largest size effect with neurofilament light chain. Additional findings revealed thinning or thickening of the other retinal layers in association with increasing levels of glial fibrillary acidic protein and phosphorylated tau at threonine 181 and 217 (p-tau181 and p-tau217). Conclusions: This pilot study suggests that retinal layer-specific signatures exist, with PR-IS thinning as the largest effect, indicating neurodegeneration in pre-AD. Further research is needed to confirm the findings of this pilot study using larger longitudinal pre-AD cohorts and comparative analyses with healthy aging adults. Full article

Background: Optical coherence tomography (OCT) can quantify the morphology and dimensions of a macular hole for diagnosis and treatment planning. Objective: The aim of this study was to perform automatic segmentation of macular holes (MHs) and cysts from OCT macular volumes using a deep learning-based model and to quantitatively evaluate decision reliability using the model’s focus regions and GradientSHAP-based explainability. Methods: In this study, we automatically segmented MHs and cysts in OCT images from the open-access OIMHS dataset. The dataset comprises 125 eyes from 119 patients and 3859 OCT B-scans. OCT B-scan slices were input to a UNet-48-based model with a 2.5D stacking strategy. Performance was evaluated using Dice and intersection-over-union (IoU), boundary accuracy was evaluated using the 95th-percentile Hausdorff distance (HD95), and calibration was evaluated using the expected calibration error (ECE). Explainability was quantified from GradientSHAP maps using lesion coverage and spatial focus metrics: Attribution Precision in Lesion (APILτ), which is the proportion of attributions (SHAP contributions) falling inside the lesion; Attribution Recall in Lesion (ARILτ), which is the proportion of the true lesion covered by the attributions; and leakage (Leakτ = 1 − APILτ), which is the proportion of attributions falling outside the lesion. Spatial focus was monitored using the center-of-mass distance (COM-dist), which is the Euclidean distance between the attribution center and the segmentation center. All metrics were calculated using the top τ% of the pixels with the highest SHAP values. SHAP features were clustered using PCA and k-means. Explanations were calculated using the clinical mask in ground truth (GT) mode and the model segmentation in prediction (Pred) mode. Results: The Dice/IoU values for holes and cysts were 0.94/0.91 and 0.87/0.81, respectively. Across lesion classes, HD95 = 6 px and ECE = 0.008, indicating good boundary accuracy and calibration. In GT mode (τ = 20), three regimes were observed: (i) retina-dominant: high ARIL (hole: 0.659; cyst: 0.654), high Leak (hole: 0.983; cyst: 0.988), and low COM-dist (hole: 7.84 px; cyst: 6.91 px), with the focus lying within the retina and largely confined to the retinal tissue; (ii) peri-lesional: highest ARIL (hole: 0.684; cyst: 0.719), relatively lower Leak (hole: 0.917; cyst: 0.940), and medium/high COM-dist (hole: 16.22 px; cyst: 10.17 px), with the focus located around the lesion; (iii) narrow-coverage: primarily seen for cysts in GT mode (ARIL: 0.494; Leak: 1.000; COM-dist: 52.02 px), with markedly reduced coverage. In Pred mode, the ARIL20 for holes increased in the retina-dominant cluster (0.758) and COM-dist decreased (6.24 px), indicating better agreement with the model segmentation. Conclusions: The model exhibited high accuracy and good calibration for MH and cyst segmentation in OCT images. Quantitative characterization of SHAP validated the model results. In the clinic, peri-lesion and narrow-coverage conditions are the key situations that require careful interpretation. Full article

Iris recognition continues to pose challenges for deep learning models, despite its status as one of the most reliable biometric authentication techniques. These challenges become more pronounced when training data is limited, as subtle, high-dimensional patterns are easily missed. To address this issue and strengthen both feature extraction and recognition accuracy, this study introduces IRIS-QResNet, a customized ResNet-18 architecture augmented with a quanvolutional layer. The quanvolutional layer simulates quantum effects such as entanglement and superposition and incorporates sinusoidal feature encoding, enabling more discriminative multilayer representations. To evaluate the model, we conducted 14 experiments on the CASIA-Thousands, IITD, MMU, and UBIris datasets, comparing the performance of the proposed IRIS-QResNet with that of the IResNet baseline. While IResNet occasionally yielded subpar accuracy, ranging from 50.00% to 98.66%, and higher loss values ranging from 0.1060 to 2.0640, comparative analyses showed that IRIS-QResNet consistently outperformed it. IRIS-QResNet achieved lower loss (ranging from 0.0570 to 1.8130), higher accuracy (ranging from 66.67% to 99.55%), and demon-started improvement margins spanning from 0.1870% in the CASIA End-to-End subject recognition with eye-side to 16.67% in the MMU End-to-End subject recognition with eye-side. Loss reductions ranged from 0.0360 in the CASIA End-to-End subject recognition without eye-side to 1.0280 in the UBIris Non-End-to-End subject recognition. Overall, the model exhibited robust generalization across recognition tasks despite the absence of data augmentation. These findings indicate that quantum-inspired modifications provide a practical and scalable approach for enhancing the discriminative capacity of residual networks, offering a promising bridge between classical deep learning and emerging quantum machine learning paradigms. Full article