Diagnosis Of Glaucoma Research Articles

Optimizing Glaucoma Diagnosis with Deep Learning-Based Segmentation and Classification of Retinal Images

Glaucoma, a leading cause of permanent blindness worldwide, necessitates early detection to prevent vision loss, a task that is challenging and time-consuming when performed manually. This study proposes an automatic glaucoma detection method on enhanced retinal images using deep learning. The system analyzes retinal images, generating masks for the optic disc and optic cup, and providing a classification for glaucoma diagnosis. We employ a U-Net architecture with a pretrained residual neural network (ResNet34) for segmentation and an EfficientNetB0 for classification. The proposed framework is tested on publicly available datasets, including ORIGA, REFUGE, RIM-ONE DL, and HRF. Our work evaluated the U-Net model with five pretrained backbones (ResNet34, ResNet50, VGG19, DenseNet121, and EfficientNetB0) and examined preprocessing effects. We optimized model training with limited data using transfer learning and data augmentation techniques. The segmentation model achieves a mean intersection over union (mIoU) value of 0.98. The classification model shows remarkable performance with 99.9% training and 100% testing accuracy on ORIGA, 99.9% training and 99% testing accuracy on RIM-ONE DL, and 98% training and 100% testing accuracy on HRF. The proposed model outperforms related works and demonstrates potential for accurate glaucoma classification and detection tasks.

Optical and Electronic Expert System for Diagnosing Eye Pathology in Glaucoma

For the first time, mathematical models for evaluating biomedical images were obtained using fuzzy set methods on the basis of expert knowledge bases, thus making it possible to carry out complex qualitative diagnostics and increase the reliability and efficiency of diagnosis. A methodology for analyzing biomedical images was formed based on the fuzzy set apparatus, which allowed a fuller assessment of the level of disease for glaucoma patients. Aspects of the practical implementation of the optical–electronic system for biomedical information processing were considered. An algorithm and an optical–electronic system for biomedical image analysis are proposed, and they can be used to increase the informativeness and reliability in the diagnosis of eye pathologies and glaucoma in particular.

Impact of acquisition area on deep-learning-based glaucoma detection in different plexuses in OCTA

Glaucoma is a group of neurodegenerative diseases that can lead to irreversible blindness. Yet, the progression can be slowed down if diagnosed and treated early enough. Optical coherence tomography angiography (OCTA) can non-invasively provide valuable information about the retinal microcirculation that has shown to be correlated with the onset of the disease. The vessel density (VD) is the most commonly used biomarker to quantify this vascular information. However, different studies showed that there is a great impact of the acquisition area on the performance of the VD to distinguish between glaucoma patients and a healthy control group. It also seems that the separate capillary plexuses are differently affected by the disease and therefore also influence the results. So in this study we investigate the impact of the acquisition area (3 ×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes $$\\end{document} 3 mm\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ extrm{mm}$$\\end{document} macular scan, 6.44 ×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes $$\\end{document} 6.4 mm\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ extrm{mm}$$\\end{document} macular scan, 6 ×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes $$\\end{document} 6 mm\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ extrm{mm}$$\\end{document} optic nerve head (ONH) scan) and the different plexuses on the machine-learning-based distinction between glaucoma patients and healthy controls. The results yielded that the 6 ×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes $$\\end{document} 6 mm\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ extrm{mm}$$\\end{document} ONH show the best performance over all plexuses. Moreover the deep learning-based approach outperforms the VD as a biomarker on every acquisition area and plexus. In addition to that, it also performs better than traditional biomarkers obtained from the OCT scans that are used in the clinical routine for diagnosis and progression tracking of glaucoma. Consequently, OCTA scans of the ONH might be a useful addition to OCT when studying glaucoma.

Multi-label deep learning for comprehensive optic nerve head segmentation through data of fundus images

Early diagnosis and continuous monitoring of patients with eye diseases are critical in computer-aided detection (CAD) techniques. Semantic segmentation, a key component in computer vision, enables pixel-level classification and provides detailed information about objects within images. In this study, we present three U-Net models designed for multi-class semantic segmentation, leveraging the U-Net architecture with transfer learning. To generate ground truth for the HRF dataset, we combine two U-Net models, namely MSU-Net and BU-Net, to predict probability maps for the optic disc and cup regions. Binary masks are then derived from these probability maps to extract the optic disc and cup regions from retinal images. The dataset used in this study includes pre-existing blood vessels and manually annotated peripapillary atrophy zones (alpha and beta) provided by expert ophthalmologists. This comprehensive dataset, integrating existing blood vessels and expert-marked peripapillary atrophy zones, fulfills the study's objectives. The effectiveness of the proposed approach is validated by training nine pre-trained models on the HRF dataset comprising 45 retinal images, successfully segmenting the optic disc, cup, blood vessels, and peripapillary atrophy zones (alpha and beta). The results demonstrate 87.7 % pixel accuracy, 87 % Intersection over Union (IoU), 86.9 % F1 Score, 85 % mean IoU (mIoU), and 15 % model loss, significantly contributing to the early diagnosis and monitoring of glaucoma and optic nerve disorders.

Quality of Life and Primary Open-Angle Glaucoma in the Ocular Hypertension Treatment Study

If preperimetric glaucoma reduces patient-reported vision-related quality of life (VRQoL), clinicians might consider earlier and more aggressive treatment of some patients with ocular hypertension and early glaucoma. To determine the impact of preperimetric glaucoma and early glaucomatous visual field (VF) loss on participants' VRQoL compared with participants who did not develop glaucoma in the Ocular Hypertension Treatment Study (OHTS). This cross-sectional study used data from participants enrolled in the OHTS from 1994 to 1996 who completed 20-year examination follow-up and VRQoL surveys from January 7, 2016, to November 19, 2019. Diagnosis of primary open-angle glaucoma (POAG) required reproducible changes in VFs or optic discs as determined by reading centers and attributed to glaucoma by a masked end point committee. Data analysis was performed from June 27, 2023 to March 7, 2024. Ocular hypertension and glaucoma. Cross-sectional analysis of Rasch-calibrated total scores of the National Eye Institute Visual Function Questionnaire (VFQ) and the Glaucoma Quality of Life (GQL) survey was performed. Total scores were standardized from 0 (poor) to 100 (good). The main outcomes were differences in total VRQoL scores between participants who did not develop POAG (control) and 4 mutually exclusive POAG groups: unilateral or bilateral disc POAG with no glaucomatous VF loss in either eye and unilateral or bilateral VF POAG with or without disc changes. Differences in total VRQoL scores were analyzed using univariate and multivariate linear regression models. Of 1636 participants originally enrolled in the OHTS, 679 (42%) completed the 20-year examination and VRQoL surveys. Of those participants completing 20-year follow-up, mean (SD) participant age at follow-up was 73.8 (7.7) years, and 412 of 679 participants (60.7%) self-reported as female. The mean (SD) Rasch-calibrated total VFQ scores were 72.5 (13.4) in the no POAG group (control) vs 72.7 (13.8) in the unilateral disc POAG group (difference, 0.17; 95% CI, -3.17 to 3.41; P = .92), 73.4 (14.0) in the bilateral disc POAG group (difference, 0.92; 95% CI, -2.93 to 4.77; P = .64), 69.2 (14.5) in the unilateral VF POAG group (difference, 3.33; 95% CI, -6.38 to -0.27; P = .03), and 58.5 (16.9) in the bilateral VF POAG group (difference, -13.96; 95% CI, -17.73 to -10.19; P<.001). Similar results were found for the GQL questionnaire. In this cross-sectional study, among the surviving participants of OHTS who completed the 20-year follow-up examination, those participants who developed preperimetric POAG but no glaucomatous VF loss did not report lower VFQoL compared with participants who did not develop POAG. This finding should allow clinicians and patients the time to determine the frequency of examinations and whether the initiation of treatment is appropriate.

Awareness and knowledge of glaucoma among the patients attending a tertiary eye hospital with and without glaucoma diagnosis

Background: Glaucoma, a leading cause of irreversible blindness, remains under-recognized in many regions, including Bangladesh. This study aimed to assess the awareness and knowledge of glaucoma among the patients attending a tertiary eye hospital with and without glaucoma diagnosis. Methods: This cross-sectional study was conducted on 300 individuals attending deep eye care foundation, Rangpur, from April 2023 to September 2023. Informed consent was obtained from eligible participants over 18 years. The questionnaire, available in both English and Bengali, collected demographic data and included questions on glaucoma awareness and knowledge. Data were analysed using SPSS 25, and the chi-square test was applied to determine statistical significance. Results: Among the participants, 34.7% had heard of glaucoma, with doctors/hospitals being the primary source of information. Awareness varied significantly based on age, residency, education, occupation, and income levels. Among those aware of glaucoma, 59.6% had poor knowledge, 33.7% had average knowledge, and only 6.7% had good knowledge. No significant association was found between glaucoma patients and non-glaucoma patients regarding knowledge level. Conclusions: This study revealed a substantial gap in glaucoma awareness and knowledge in Bangladesh. While a notable portion of the population had heard of glaucoma, their understanding of the condition was limited, emphasizing the need for targeted awareness campaigns and improved access to eye care services. Addressing these gaps is crucial for early diagnosis, treatment, and preventing irreversible blindness while reducing the economic burden associated with glaucoma-related healthcare costs.

INTEGRATING DUAL FUNDUS IMAGE DEEP FEATURE POOLING BASED ON CUP AND DISC SEGMENTATION FOR EFFICIENT GLAUCOMA DETECTION FRAMEWORK INDULGING HEURISTIC CONCEPT

The permanent damage occurring to the optical nerve, which transmits the visualized images to the brain leading to permanent vision loss, is called glaucoma. The detection and diagnosis of glaucoma at the beginning stage are essential to prevent permanent damage caused to vision as there are no initial symptoms to detect the onset of the damage, and there is no cure while the damage progresses to its extreme stage. Many models utilizing deep learning technology have been executed to identify the presence of glaucoma using digital Fundus Images (FI). However, these methods need specialized hardware and are computationally complicated as there is not much-labeled data available, leading to generalization issues in these models. Therefore, the development of a deep learning-oriented model for Glaucoma Detection (GD) using the dual feature pooling of cup and disc segmentation features with the aid of the FI is the main motive behind this work. At first, the digital FI is congregated from standardized online data sources. Then the gathered images are considered for the image segmentation procedure. The disc is segmented from the input image with the aid of the Transformer based Adaptive ResUNet++ (TA-ResUNet++) framework. The segmented disc image is now provided to hybrid convolution networks (HCN) for extracting the disc-oriented features. At the same time, the cup is segmented from the gathered input image using the executed TA-ResUnet++. Following this, the cup features are extracted using the same HCN model. The obtained features regarding the disc and the cup are concatenated in order to generate a single pool of glaucoma features. Then these features are inputted into the implemented bidirectional long short-term memory with multi-head attention (Bi-LSTM-MHA) mechanism to detect the presence of glaucoma in people. The segmentation and detection outcomes are made better by optimizing the parameters in the TA-ResUNet++ and Bi-LSTM-MHA models with the aid of hybrid sewing training with the Chameleon swarm optimization algorithm (HST-CSA). The experimental analysis is done to analyze the effective performance of the developed GD model. Jaccard analysis performed for the developed HST-CSOA-TA-ResUNet++-based disc segmentation gained better performance as 18.29% than MobileNet, 14.11% efficient than ResNet, 12.79% superior to Bi-LSTM and 5.43% higher than Bi-LSTM-MHA while considering best as the statistical measure.

Glaucoma classification through SSVEP derived ON- and OFF-pathway features.

Recent evidence from small animal models and human electrophysiology suggests that the OFF-pathway is more vulnerable to glaucomatous insult than the ON-pathway. Thus, OFF-pathway based measurements of visual function may be useful in the diagnosis of Glaucoma. The steady-state visually evoked potential (SSVEP) can be used to non-invasively make such functional measurements. Here, we examine whether OFF- and ON-pathway biasing SSVEP measurements differently predict glaucoma diagnosis using a large cohort of 98 glaucoma patients and 71 controls. Using both a logistic regression with k-fold cross-validation and a random forest classifier, we show that OFF-pathway biasing features produce a small improvement in predictive accuracy over ON-pathway biasing features. However, despite our inclusion of many more response features and the retention of both participants' eyes, our classifier did not perform as well as previous reports that used the isolated-check VEP. This is likely a result of the relatively small amount of data we collected for each participant, but may also be explained by the absence of any train-test splitting in preexisting work. Nevertheless, our results support further exploration of the diagnostic potential of OFF-pathway biasing functional biomarkers for glaucoma.

Relationship between Neighborhood-Level Social Risk Factor Measures and Presenting Glaucoma Severity Utilizing Multilevel Modeling

PurposeThe neighborhood and built environment social determinant of health domain has several social risk factors (SRF) that are modifiable through policy efforts. We investigated the impact of neighborhood-level SRFs on presenting glaucoma severity at a tertiary eye care center. DesignA cross-sectional study from August 2012 to May 2022 in the University of Michigan (UM) electronic health record (EHR). ParticipantsPatients with a diagnosis of any open angle glaucoma with ≥1 eye care visit at the UM Kellogg Eye Center and ≥1 reliable visual field. MethodsParticipants who met inclusion criteria were identified by ICD9/10 codes (365.x/H40.x). Data extracted from the EHR included patient demographics, address, presenting mean deviation (MD), and visual field reliability. Addresses were mapped to SRF measures at the census tract, block group, and county levels. Multilevel linear regression models were used to estimate the fixed effects of each SRF on MD, after adjusting for patient-level demographic factors and a random effect for neighborhood. Interactions between each SRF measure with patient-level race and Medicaid status were tested for an additive effect on MD. Main Outcome MeasuresThe main outcome measure was the effect of SRF on presenting MD. ResultsIn total, 4428 patients were included in the analysis who were, on average, 70.3 years old (standard deviation=11.9), 52.6% self-identified as female, 75.8% self-identified as White, and 8.9% had Medicaid. The median value of presenting MD was -4.94 dB (interquartile range=-11.45 to -2.07 dB). Neighborhood differences accounted for 4.4% of the variability in presenting MD. Neighborhood-level measures, including worse area deprivation (estimate, β=-0.31 per 1-unit increase; p<0.001), increased segregation (β=-0.92 per 0.1-unit increase in Theil’s H index; p<0.001), and increased neighborhood Medicaid (β=-0.68; p<0.001) were associated with worse presenting MD. Significant interaction effects with race and Medicaid status were found in several neighborhood-level SRF measures. ConclusionsAlthough patients’ neighborhood SRF measures accounted for a minority of the variability in presenting MD, most neighborhood-level SRFs are modifiable and were associated with clinically meaningful differences in presenting MD. Policies that aim to reduce neighborhood inequities to address allocation of resources could have lasting impacts on vision outcomes.

Glaucoma diagnosis from fundus images using modified Gauss-Kuzmin-distribution-based Gabor features in 2D-FAWT

PurposeGlaucoma is an eye disease that can result in perpetual eye vision loss if not perceived and treated in time. Therefore, an accurate and efficient automated method has been proposed for diagnosing Glaucoma. This method enables mass screening for such conditions and reduces the task of healthcare professionals. MethodologyThis proposed method involves splitting the fundus images into red, green, and blue channel components, where the green channel component is selected for further processing. The processed green channel of the images has been decomposed using Flexible analytical wavelet transform (FAWT) in sub-bands. Furthermore, the features are mined from decomposed green channel sub-band images using the modified Gauss-Kuzmin-distribution-based Gabor (GKDG) filter (eight scales and five orientations) and NCA by employing them to lessen the dimensionality of the silent features. Then, the selected features are graded using the student t-value, and the graded features are fed to the kernels like linear, gradient descent, Morlet, and Mexican-hat-based LS-SVM classifier to classify the Glaucoma. Results and ConclusionThe results of this research suggest that the newly proposed glaucoma classification model demonstrates superior performance compared to contemporary techniques. The model's evaluation was conducted using tenfold cross-validation, revealing an enhanced accuracy of 95.84 %, a specificity of 97.17 %, and a sensitivity of 94.55 %.

A multi-scale convolutional neural network with adaptive weight fusion strategy for assisting glaucoma screening

The diagnosis of glaucoma primarily relies on the accurate segmentation of the optic disc (OD) and optic cup (OC). However, OC segmentation remains challenging due to significant individual differences. This study proposes a threshold-based OD extraction method and multi-scale residual U-Net with context attention mechanism and adaptive weight fusion strategy (MRCAAU-Net) to segment OC and OD jointly. Firstly, based on the intensity difference between the OD and the background, an improved thresholding criterion combined with template matching technique is used to effectively detect the OD region, providing accurate input images for network training. Secondly, considering the semantic gap issue during the encoder-decoder feature fusion in the segmentation network, this paper develops an adaptive weight fusion module to guide the effective connections of encoder-decoder features. Additionally, the 1D convolution-based attention mechanism has stronger local perceptiveness. This paper integrate it into various modules, combining multi-scale methods to enhance the segmentation performance of OC by incorporating both global and local features. Finally, the network is guided to learn image segmentation through a hybrid loss function that ignores the background. We conducted extensive experiments on three public datasets, and obtained more accurate segmentation outputs compared to other state-of-the-art methods, particularly in the OC segmentation, where the segmentation accuracy is very close to that of the OD. The proposed joint segmentation network effectively improves and balances the segmentation performance of two objectives, which can greatly assist in large-scale screening for glaucoma.

Evaluating the risk of new-onset glaucoma in chronic kidney disease patients: a nationwide cohort study

BackgroundA better understanding of the association between chronic kidney disease (CKD) and glaucoma is required to optimize clinical outcomes. Therefore, this study aimed to investigate the association of chronic kidney disease (CKD) with new diagnoses of glaucoma over time from January 2009 to December 2019.MethodThis retrospective propensity-matched cohort study utilizing Taiwanese electronic health records examined the incidence of newly diagnosed glaucoma in patients with and without chronic kidney disease (CKD). The exposure variable was the diagnosis of CKD, identified through diagnostic codes. The primary outcome was the incidence of new-onset glaucoma. Subgroup analyses on glaucoma risk included age, gender, comorbidities, glaucoma subtypes, and dialysis status. Statistical analyses included Kaplan–Meier analysis, Cox proportional hazards models, and Poisson regression models, with the associated hazard ratios and confidence intervals reported.ResultsSeven hundred twenty-three thousand two hundred sixteen patients with CKD (42.3% female; mean [SD] age at index, 66.3 [15.6] years) and 723,216 patients without CKD (42.3% female; mean [SD] age at index, 66.3 [15.7]) were recruited. We showed a significantly increased risk of glaucoma irrespective of subtypes in CKD patients compared to those without CKD (HR: 1.29 [CI: 1.26–1.32], p < 0.001). Kaplan–Meier curves revealed a significantly increased glaucoma risk in both the dialytic subtype and non-dialytic CKD patients when compared to their non-CKD counterparts (p < 0.001). We also showed that all genders (aHR 1.17 [CI: 1.13–1.21] for females vs. aHR 1.39 [CI:1.35–1.43] for males), all ages (< = 49: aHR 1.49 [CI: 1.37–1.62]; 50–59: aHR 1.48 [CI: 1.40–1.56]; 60–69: aHR 1.30 [CI: 1.25–1.6]; 70–79: aHR 1.21 [CI: 1.17–1.26]; > 80: aHR 1.29 [CI: 1.21–1.37]); all income brackets and all urbanization status were associated with significantly increased risk of glaucoma from among the CKD cohort when compared to their respective non-CKD cohort (p < 0.001).ConclusionsOur cohort study spanning 12 years showed an elevated glaucoma risk following a CKD diagnosis compared to a frequency-matched non-CKD cohort. Our findings have relevance for the clinical practice of at-risk CKD patients.Trial registrationDue to the retrospective nature of the study, no registration was necessary.

Assessment of Missing Data on Glaucoma Severity among Participants in the NIH All of Us Research Program of the United States.

There were statistically significant differences across multiple socioeconomic characteristics and self-reported barriers to care among primary glaucoma patients with severity staging data versus those missing this data in the NIH All of Us database. To characterize missing data among glaucoma patients within All of Us. We used diagnosis codes to define cohorts of primary glaucoma patients with and without severity staging specified. Descriptive analyses were conducted by presence of disease severity stage. Analysis of missing data was conducted using a set intersection plot and Little's Test of Missing Completely at Random. T-tests were performed to evaluate differences. Of 2982 participants, 1714 (57%) did not have glaucoma severity stage specified, and 11 of 23 analyzed variables had missing data. Little's Test indicated data was not missing completely at random (P<0.001). Significant differences existed between the two cohorts with respect to age, age of first glaucoma diagnosis, gender, ethnicity, education, income, insurance, history of glaucoma surgery and medication use, and answers regarding ability to afford eyeglasses and having seen an eye care provider in the last 12 months (all P values≤0.01). There were significant differences between glaucoma participants with glaucoma severity stage specified versus those with unstaged disease across multiple socioeconomic characteristics and self-reported barriers to care. Glaucoma severity staging data was not missing completely at random. The unstaged cohort included higher rates of multiple underrepresented communities, which may potentially contribute to bias in ophthalmology research as participants from vulnerable populations may be disproportionately excluded from electronic health records or claims data studies where diagnosis codes with severity/staging levels are used to examine risk factors for disease, progression, and treatment efficacy.

Frequency of Elevated Intraocular Pressure in Patients with Acute and Chronic Anterior Uveitis

Background: Elevated intraocular pressure (IOP) is a frequent and serious complication in patients with uveitis, potentially leading to secondary glaucoma and permanent vision loss. Understanding the frequency and associated risk factors of elevated IOP in patients with acute and chronic anterior uveitis is essential for effective management and prevention of visual morbidity. Objective: This study aimed to determine the frequency of elevated IOP in patients with acute and chronic anterior uveitis and to identify the associated demographic and clinical factors. Methods: This This descriptive, cross-sectional study was conducted over six months at the Outpatient Department of Al-Shifa Trust Eye Hospital, Rawalpindi, involving 160 patients aged 20 to 60 years diagnosed with anterior uveitis. Patients were excluded if they were on anti-glaucoma medications, had specific ocular conditions, or had a pre-existing diagnosis of glaucoma or elevated IOP. Intraocular pressure was measured using Goldmann Applanation Tonometry, with elevated IOP defined as &gt;21 mmHg. Demographic data and clinical history, including the duration and grade of uveitis, were recorded. Data were analyzed using SPSS version 25, with qualitative variables presented as frequencies and percentages, and statistical significance assessed using chi-square tests (p ≤ 0.05). Results: The mean age of the study participants was 33.19 years (SD ± 7.26). Elevated IOP was observed in 38.75% of the patients. A significantly higher frequency of elevated IOP was found in females (61.7% vs. 25% in males, p = 0.000), patients over 30 years of age (46.4% vs. 30.3%, p = 0.026), and those with hypertension (69.8% vs. 23.4% in non-hypertensive patients, p = 0.000). Grade I uveitis had the highest frequency of elevated IOP (100%), followed by grade III (42.9%), grade IV (4.1%), and grade II (0%) (p = 0.000). No significant association was found between elevated IOP and diabetes mellitus or the duration of uveitis. Conclusion: The study found a substantial frequency of elevated IOP in patients with anterior uveitis, particularly among females, older patients, and those with hypertension. These findings highlight the need for regular IOP monitoring and tailored management strategies in high-risk patients to prevent the development of secondary glaucoma and associated vision loss.

Transformer-Based Deep Learning Prediction of 10-Degree Humphrey Visual Field Tests From 24-Degree Data.

To predict 10-2 Humphrey visual fields (VFs) from 24-2 VFs and associated non-total deviation features using deep learning. We included 5189 reliable 24-2 and 10-2 VF pairs from 2236 patients, and 28,409 reliable pairs of macular OCT scans and 24-2 VF from 19,527 eyes of 11,560 patients. We developed a transformer-based deep learning model using 52 total deviation values and nine VF test features to predict 68 10-2 total deviation values. The mean absolute error, root mean square error, and the R2 were evaluation metrics. We further evaluated whether the predicted 10-2 VFs can improve the structure-function relationship between macular thinning and paracentral VF loss in glaucoma. The average mean absolute error and R2 for 68 10-2 VF test points were 3.30 ± 0.52dB and 0.70 ± 0.11, respectively. The accuracy was lower in the inferior temporal region. The model placed greater emphasis on 24-2 VF points near the central fixation point when predicting the 10-2 VFs. The inclusion of nine VF test features improved the mean absolute error and R2 up to 0.17 ± 0.06dB and 0.01 ± 0.01, respectively. Age was the most important 24-2 VF test parameter for 10-2 VF prediction. The predicted 10-2 VFs achieved an improved structure-function relationship between macular thinning and paracentral VF loss, with the R2 at the central 4, 12, and 16 locations of 24-2 VFs increased by 0.04, 0.05 and 0.05, respectively (P < 0.001). The 10-2 VFs may be predicted from 24-2 data. The predicted 10-2 VF has the potential to improve glaucoma diagnosis.

Multi-step framework for glaucoma diagnosis in retinal fundus images using deep learning.

Glaucoma is one of the most common causes of blindness in the world. Screening glaucoma from retinal fundus images based on deep learning is a common method at present. In the diagnosis of glaucoma based on deep learning, the blood vessels within the optic disc interfere with the diagnosis, and there is also some pathological information outside the optic disc in fundus images. Therefore, integrating the original fundus image with the vessel-removed optic disc image can improve diagnostic efficiency. In this paper, we propose a novel multi-step framework named MSGC-CNN that can better diagnose glaucoma. In the framework, (1) we combine glaucoma pathological knowledge with deep learning model, fuse the features of original fundus image and optic disc region in which the interference of blood vessel is specifically removed by U-Net, and make glaucoma diagnosis based on the fused features. (2) Aiming at the characteristics of glaucoma fundus images, such as small amount of data, high resolution, and rich feature information, we design a new feature extraction network RA-ResNet and combined it with transfer learning. In order to verify our method, we conduct binary classification experiments on three public datasets, Drishti-GS, RIM-ONE-R3, and ACRIMA, with accuracy of 92.01%, 93.75%, and 97.87%. The results demonstrate a significant improvement over earlier results.

Evaluating machine learning techniques for enhanced glaucoma screening through Pupillary Light Reflex analysis

Glaucoma is a leading cause of irreversible visual field degradation, significantly impacting ocular health. Timely identification and diagnosis of this condition are critical to prevent vision loss. A range of diagnostic techniques is employed to achieve this, from traditional methods reliant on expert interpretation to modern, fully computerized diagnostic approaches. The integration of computerized systems designed for the early detection and classification of clinical indicators of glaucoma holds immense potential to enhance the accuracy of disease diagnosis. Pupillary Light Reflex (PLR) analysis emerges as a promising avenue for glaucoma screening, mainly due to its cost-effectiveness compared to exams such as Optical Coherence Tomography (OCT), Humphrey Field Analyzer (HFA), and fundoscopic examinations. The noninvasive nature of PLR testing obviates the need for disposable components and agents for pupil dilation. This facilitates multiple successive administrations of the test and enables the possibility of remote execution. This study aimed to improve the automated diagnosis of glaucoma using PLR data, conducting an extensive comparative analysis incorporating neural networks and machine learning techniques. It also compared the performance of different data processing methods, including filtering techniques, feature extraction, data balancing, feature selection, and their effects on classification. The findings offer insights and guidelines for future methodologies in glaucoma screening utilizing pupillary light response signals.

Association of Age of Menopause and Glaucoma Diagnosis in Female Veterans.

Age of menopause has been associated with the risk of developing glaucoma; however, it is unclear if the onset of menopause is directly associated with the development of glaucoma. Our objective was to determine if there is an association between the age at diagnosis of menopause and glaucoma. This retrospective, case-only analysis was performed using the Veterans Affairs (VA) Corporate Data Warehouse of female veterans from 2000 to 2019. Women with both menopause and glaucoma diagnoses were matched based on covariates. The two matched cohorts were early menopause-early comparative (EM-EC; n = 1075) and late menopause-late comparative (LM-LC; n = 1050) women. We used a Pearson correlation to examine the linear relationship between age at diagnosis of menopause and glaucoma. Afterward, we used a multivariate linear regression model with age at diagnosis of glaucoma serving as the outcome variable to account for the covariates. We found that EM women developed glaucoma 6.0 years (interquartile range [IQR], 5.1-6.5) earlier than the EC group (P < 0.001), and LM women developed glaucoma an average of 5.2 years (IQR, 4.8-5.7) later than the LC group (P < 0.001). There was a modest linear relationship between the age of menopause and glaucoma diagnoses in the EM-EC (r = 0.40) and LM-LC (r = 0.46) cohorts. In our multivariate analysis, age at diagnosis of menopause was the largest factor related to age at diagnosis of glaucoma while accounting for our covariates. Our models predicted a 0.67-year delay in age at diagnosis of glaucoma with each additional premenopausal year. This case-only analysis elucidates a temporal association between menopause and glaucoma, highlighting the need to characterize the role of menopause in the onset of glaucoma for women.

Female-Specific Association between the Apolipoprotein E E4 Allele and Age at Diagnosis of Glaucoma in UK Biobank

ObjectiveTo explore the impact of the apolipoprotein E (APOE) E4 allele in the gender-specific aging process in glaucoma by illustrating the interaction between risk factors, including the APOE E4 allele, gender and intraocular pressure (IOP), for age at diagnosis (AAD) of glaucoma. DesignA cross-sectional study included UK Biobank participants with complete data (2006-2010) for analysis. Data were analyzed in December 2023. Participants2,236 glaucoma patients and 103,232 controls. MethodsWe evaluated multivariable-adjusted associations of AAD of glaucoma, APOE E4 allele (0: absence; 1: presence), and IOP using linear mixed model (LMM) analyses across groups stratified by AAD of mean age of menopause (50 years) and gender. Main Outcomes MeasuresAAD of glaucoma, APOE E4 allele and IOP. ResultsGlaucoma patients were older and had a higher percentage of males and a higher mean IOP compared to controls (all P < 0.001). Further stratifying the glaucoma patients by AAD of 50 and gender, lower IOP (Model 1 adjusted by age, βIOP=-0.096±0.041, P=0.019) and positive APOE E4 allele (Model 2 adjusted by age and IOP, βe4=1.093±0.488, P=0.026) were associated with an older AAD in females with an AAD < 50 years under univariate LMM. In multivariate LMM adjusted by age (Model 3), the effect size of both factors increased in the multivariate model as the beta-value increased. (βIOP=-0.111±0.040, P=0.007; βe4=1.235±0.485, P=0.012) (Model 1 vs Model 3: P=0.011). In females with an AAD ≥50 years, only positive APOE E4 allele (adjusted by age and IOP, βe4=-1.121±0.412, P=0.007) was associated with a younger AAD. In males, only higher IOP was associated with an older AAD in those with an AAD ≥50 years (βIOP=0.088±0.032, P=0.006). ConclusionsAPOE E4 allele may initially delay and later accelerate the development of glaucoma in females around the transition period of 50 years, which is the mean age of menopause, and importantly, this is independent of IOP. Understanding the specific transition states and modifiable factors within each age phase is crucial for developing interventions or strategies that promote healthy aging.

Postmenopausal Hormone Therapy Was Associated With Later Age of Onset Among Glaucoma Cases.

Hormonal therapy (HT) has been suggested to lower the risk of developing glaucoma. Our goal was to investigate the association between HT use and the onset of glaucoma diagnosis in postmenopausal women. This retrospective case-only study included female veterans with open-angle glaucoma from VA records between 2000 to 2019. Propensity score matching was used to match HT (n = 1926) users to untreated (n = 1026) women on multiple covariates (e.g., age of menopause, BMI, blood pressure, antihypertensive medications, and a co-morbidity index). A simple linear regression was used to evaluate the impact of HT duration on the age of glaucoma diagnosis, and multivariate linear regression analysis was used to determine which factors contributed to the age at diagnosis of glaucoma. We found a linear relationship between the age at diagnosis of glaucoma and menopause in women with (r = 0.54) and without HT (r = 0.57) use. HT users tended to have a later diagnosis of glaucoma. Our multivariate analysis found that 0-2 years, 2-5 years, and >5 years of HT use were associated with a 2.20 [confidence interval (CI), 1.64, 2.76], 3.74 [CI, 3.02, 4.46], and 4.51 [CI, 3.84, 5.18] years later diagnosis of glaucoma. An interaction (-0.009 [-0.015, -0.003]) was observed between HT duration and age of menopause diagnosis, with the impact of HT decreasing for later menopause ages. Longer duration of HT use was associated with a later diagnosis of glaucoma in postmenopausal women in this case-only analysis. The impact of HT may be modulated by menopausal age, although further study is needed. The findings support a protective role of estrogen in glaucoma pathogenesis.