Cup-to-disc Ratio Research Articles

An automatic recognition of glaucoma in fundus images using deep learning and random forest classifier

Glaucoma is perpetual damage of optic nerves which causes fractional or complete visual misfortune. The fundamental reason for this illness is the increment of the intra-ocular pressure inside the eye which harms the optic nerve. Retinal images give indispensable data about an eye’s wellbeing. Based on progressions in retinal images technology, it is conceivable to create frameworks that can investigate these retinal imageries for better determination. This work presents a glaucoma recognition technique by estimating CDR (Cup to Disc Ratio) from fundus images. The size of the optic disc and optic cup is utilized to distinguish the presence of glaucoma. Therefore, the segmentation of the optic disc and optic cup is the primary step in glaucoma recognition. Decreasing the number of features and reducing the error are the two clashing destinations. The proposed glaucoma recognition technique comprises image acquisition, feature extraction, and glaucoma evaluation stages. The contrast enhancement operation is performed in image acquisition. While boundaries of OD (Optic Disc) and OC (optic cup) are segmented in the feature extraction stage and it is performed by utilizing Au-Net. Then CDR ratio of an abused image is computed to assess glaucoma in the images. Thereafter, a random forest classifier has been used to classify the glaucomatous images based on the CDR values. The performance of the proposed method has been evaluated with different techniques such as Deformable U-Net, Full-Deformable U-Net, and Original U-Net. From the outcomes, it can be noticed that the proposed method gives better performance in terms of classification accuracy of 99% and 14% of segmentation accuracy has been compared when compared with Original U-Net.

Phase quantized polar transformative with cellular automaton for early glaucoma detection

Glaucoma is the leading cause of blindness worldwide. Glaucoma being a chronic eye disease results in irreversible loss of vision. Everyone is at danger for glaucoma. But, certain groups are greater risk. Hence, accurate Classification of normal and glaucoma images is significant one. In the screening and early detection of glaucoma, Cup to Disc Ratio (CDR) method plays a significant role. The automatic segmentation for early detection from Optimal Coherence Tomography (OCT) images is a fundamental task. Several research works based on OCT were contributed for early detection of glacuoma. However, inherent feature extraction and over fitting issues while performing early glaucoma detection have been researched by the research community for long time. In this paper, we propose Artificial Intelligence architecture, called Phase Quantized Polar Transformed Cellular Automaton (PQPT-CA) method that use the displacement gradients and distance gradients for early glaucoma detection. The proposed PQPT-CA method comprises of inherent feature extraction, robust feature segmentation and early glaucoma detection based on OCT. To start with, First Order Phase Quantization model is applied to the raw input image for extracting inherent features. Next, with the extracted features, Differential Polar Transformation is applied to generate robust segmentation map. Finally, glaucoma detection is performed for three different state employing Cellular Automaton model. The experiments show that our PQPT-CA method achieves state-of-the-art early detection on ACRIMA database. Simultaneously, the proposed method also obtains the satisfactory glaucoma screening performances with calculated diagnosis accuracy on ACRIMA database. The PQPT-CA method increases the Diagnosis Accuracy by 24% and minimizes computational time and false positive rate by 21% and 54% respectively.

Incidence of non-glaucomatous ocular disease in patients with asymmetric optic disc cupping.

To evaluate the incidence of non-glaucomatous ocular disease in patients with asymmetric optic disc cupping. A retrospective case series, including consecutive patients with cup-to-disc ratio (CDR) asymmetry greater than 0.2. All patients underwent a complete neuro-ophthalmological examination, automated perimetry with the Humphrey 24-2 visual fields program. Retinal nerve fibre layer thickness was measured by optical coherence tomography (OCT). The results of neuroimaging, macular OCT and blood tests were recorded as well. Patients were assigned a diagnosis of glaucomatous optic neuropathy (GON) or non-glaucomatous disease (NGD). The main outcome measure was the rate of non-glaucomatous ocular disease. A total of 120 (67 males) patients with a mean age of 71.1 ± 12.5years met the inclusion criteria and were included in this study. The mean asymmetry in CDR between the eyes was 0.3 ± 0.13 (range, 0.2-0.9). Twenty patients (16.6%) had a visual field defect not typical for glaucoma and positive relative afferent pupillary defect was found in 24 patients (20%). Six patients were found to have newly diagnosed non-glaucomatous ocular disease: maculopathy in three patients, retinopathy in one patient and traumatic optic neuropathy in two patients. Patients with NGD were significantly younger than the patients with GON (59.8 ± 23.3 vs. 71.3 ± 11.5years, P = 0.001). Optic disc pallor was found in 4/93 patients with glaucoma compared to 3/6 with newly diagnosed non-glaucomatous disease (4.7% vs. 50.0%, P = 0.03). Asymmetric optic disc cupping can be associated with non-glaucomatous disease and may warrant neuro-ophthalmological evaluation, especially in younger patients or those with optic disc pallor.

Agreement of findings of glaucoma screening between trained vision center technicians and glaucoma specialists at a tertiary hospital in South India.

Purpose:To study the agreement of findings of glaucoma screening between trained vision center (VC) technicians and glaucoma specialists in patients referred from VC to the glaucoma services of a tertiary eye care hospital in south India.Methods:This was a retrospective study comparing the findings of the VC technicians and the specialists of the glaucoma services in the base hospital, in patients referred from 13 VCs between January and June 2019. Medical records of 277 referred patients (out of 533 referrals) who attended the glaucoma clinic were analyzed.Results:Of the 277 patients, 111 (40%) were confirmed having glaucoma, 133 (48%) were suspects, 29 (10.4%) were normal, and four (1.4%) had other pathology. The mean age of the patients was 59.7 ± 13 years and 60.6% were females. There was no statistically significant difference between the mean intraocular pressure (IOP) measured (17 ± 7.2 mmHg at the VC and 18 ± 8.7 mmHg at the clinic, p = 0.16) and the cup-to-disc ratio (CDR) (0.7 ± 0.13 at the VC and 0.6 ± 0.18 at the clinic, p = 0.57). Bland–Altman plots with 95% limits of agreement supported that mean differences were close to zero, and the intraclass correlation coefficient at 95% CI showed good consistency between the measurement of IOP (0.78 [0.74 to 0.81]) and CDR (0.90 [0.88 to 0.92]) at the base hospital and vision center.Conclusion:There is good agreement between the findings of VC technicians and glaucoma specialists. VC technicians can help in detecting glaucoma in the community.

Surgical Outcomes of Primary Congenital Glaucoma in Children Under One Year from the Nile Delta.

PurposeTo present outcomes of surgical management of primary congenital glaucoma (PCG) in children less than one year of age in a population based at the Nile Delta.MethodsA retrospective review of medical records of patients with PCG less than one year of age at presentation who underwent surgical intervention in a tertiary care facility based at the Nile Delta. All patients underwent measurement of intraocular pressure (IOP), horizontal corneal diameter (HCD), cup-to-disc ratio (CDR) before and after surgery and a minimum of 6 months follow up was required. Surgical success was defined as IOP less than 22mmHg without medications and without progression of main disease parameters.ResultsThe review revealed 44 eyes of 26 consecutive patients who underwent surgical treatment for PCG. Average age at surgery was 5.2 months and mean follow up was 18.5 months. Preoperative IOP was 28.5±4 mmHg, HCD was 13.7±0.7mm, and CDR (when visible) was 0.65±0.18. A total of 69 surgical procedures were performed with an average of 1.56 procedures per eye. Postoperative IOP was 13.3±4.8 mmHg, HCD was 12.8±0.9mm, and CDR was 0.3±0.2 (P<0.0001). Surgical success was achieved in 32 eyes (72.7%) while sight-threatening postoperative complications were reported in 3 eyes.ConclusionSurgical management of PCG younger than one year of age achieved good success rate in the region of the Nile Delta with low rate of visually significant postoperative complications. However, larger studies with longer follow up are needed to fully reveal the overall characteristics of PCG in the region.

A novel optic disc and optic cup segmentation technique to diagnose glaucoma using deep learning convolutional neural network over retinal fundus images

Glaucoma is currently leading retinal disease, which damages the eye because of the Intraocular pressure (IOP) on the eye. If glaucoma is left untreated it will lead to vision loss by damaging the Optic Nerve Head (ONH). The progression of glaucoma is examined on the retinal part of the eye by an experienced ophthalmologist. This approach is very tedious, and it consumes more time to do it manually. Hence this issue is right problem that can be solved by automatically diagnosing glaucoma with the help of the deep learning approaches. Convolutional Neural Networks (CNN's) are appropriate to find the solution for this type of issue as they can extract various levels of data from the input image, and which encourages to differentiate among non-glaucomic and glaucomic images. This proposed paper introduces an efficient glaucoma master framework to segment the optic cup and optic disc to find the Cup-to-Disc-Ratio (CDR). Here the diagnosis of glaucoma is achieved by using deep learning with novel CNN. The proposed system uses two individual CNN architecture to segment the Optic Cup (OC) and Optic Disc (OD) to get more accurate result. This model is trained and tested on DRISHTI – GS database, which is publicly available and an accuracy of 98% for optic disc and 97% for optic cup segmentation is achieved.

A multi-scale convolutional neural network with context for joint segmentation of optic disc and cup

Glaucoma is the leading cause of irreversible blindness. For glaucoma screening, the cup to disc ratio (CDR) is a significant indicator, whose calculation relies on the segmentation of optic disc(OD) and optic cup(OC) in color fundus images. This study proposes a residual multi-scale convolutional neural network with a context semantic extraction module to jointly segment the OD and OC. The proposed method uses a W-shaped backbone network, including image pyramid multi-scale input with the side output layer as an early classifier to generate local prediction output. The proposed method includes a context extraction module that extracts contextual semantic information from multiple level receptive field sizes and adaptively recalibrates channel-wise feature responses. It can effectively extract global information and reduce the semantic gaps in the fusion of deep and shallow semantic information. We validated the proposed method on four datasets, including DRISHTI-GS1, REFUGE, RIM-ONE r3, and a private dataset. The overlap errors are 0.0540, 0.0684, 0.0492, 0.0511 in OC segmentation and 0.2332, 0.1777, 0.2372, 0.2547 in OD segmentation, respectively. Experimental results indicate that the proposed method can estimate the CDR for a large-scale glaucoma screening.

Demographic and Clinical Characteristics Associated with Minimally Invasive Glaucoma Surgery Use: An Intelligent Research in Sight (IRIS®) Registry Retrospective Cohort Analysis

Minimally invasive glaucoma surgery (MIGS) is increasingly performed at the time of cataract extraction. Understanding the demographic and clinical characteristics of patients undergoing MIGS procedures may provide insight into patient selection. This study evaluates racial-ethnic and other differences in the utilization of MIGS in persons with cataract and open-angle glaucoma (OAG). Retrospective cohort study using IRIS® (Intelligent Research in Sight) Registry data. U.S. patients aged ≥40 years with a diagnosis of OAG and no history of MIGS or cataract surgery who were undergoing cataract extraction, with or without MIGS, during 2013-2017. Multivariable logistic regression models were used to calculate odds ratios (ORs) and 95% confidence intervals (CIs). Variables assessed include age, sex, race-ethnicity, disease severity, insurance type, census region, comorbidity, and cup-to-disc ratio (CDR). The odds of MIGS utilization was greater among patients who were >60 years (OR, 1.10 [95% CI, 1.05-1.16]); African American (OR, 1.11 [CI, 1.07-1.15]), compared with white; a Medicare recipient (OR, 1.12 [CI, 1.10-1.15]), , versus privately insured; or in the Midwest (OR, 1.32 [CI, 1.28-1.36]) or Northeast (OR, 1.26 [CI, 1.22-1.30]), compared with the South. Having moderate, rather than mild, glaucoma (OR, 1.07 [CI, 1.04-1.11]) and a higher CDR (OR for 0.5 to 0.8, vs. <0.5, 1.24 [CI, 1.21-1.26]; OR for >0.8 to 1.0, vs. <0.5, 1.27 [CI, 1.23-1.32]) were also each associated with increased odds of MIGS utilization. MIGS was less likely in females (OR, 0.96 [CI, 0.94-0.98]); patients taking 5 to 7 glaucoma medications (OR, 0.94 [CI, 0.90-0.99]), compared with 1 to 2 medications; and patients with severe, compared with mild, glaucoma (OR, 0.64 [CI, 0.61-0.67]). To our knowledge, the IRIS Registry contains the largest cohort of U.S. patients with MIGS procedures reported to date. This analysis highlights the importance of capturing race-ethnicity data and other pertinent patient characteristics in electronic health records to provide insight into practice patterns. Such data can be used to assess the long-term performance of MIGS and other procedures in various patient populations.

Underdiagnosis of glaucoma in patients with exudative age-related macular degeneration.

To compare the rate of glaucoma-related diagnoses in patients with exudative or non-exudative age-related macular degeneration (AMD). Patients above the age of 55 with a diagnosis of AMD were identified from billing records from 2015 to 2018. Out of the 3991 patients with AMD, two cohorts with 990 patients in each were formed by randomly age-matching patients with exudative AMD with those with non-exudative AMD; patients within each group were further classified by subtype and severity of glaucoma. Charts of AMD patients without glaucoma-related diagnoses were reviewed to determine potential underdiagnosis. We applied a set of broad clinical criteria that comprised an intraocular pressure ≥22 mmHg, a cup-to-disc ratio (CDR) ≥ 0.6, and/or CDR difference between eyes of ≥0.2. The rate of diagnosed, open-angle glaucoma was significantly lower in patients with exudative AMD (6.06%) compared to patients with non-exudative AMD (8.99%, P = 0.04). Similarly, the rate of suspected glaucoma was significantly lower in the first group compared to the second (12.12% versus 18.48%, respectively, P < 0.001). A greater number of patients with exudative AMD (13.94%, n = 138) met clinical risk criteria compared with those having non-exudative AMD (6.97%, n = 69, P < 0.001). When these at-risk patients were added to their respective groups, the rate of glaucoma, or its suspicion, became similar (χ2 = 1.24, P = 0.539). A significantly lower rate of diagnosed glaucoma, or its suspicion, was identified in patients with exudative compared to non-exudative AMD. This apparent underdiagnosis was resolved by the retrospective application of clinical criteria that may represent a risk of glaucoma.

Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network

BackgroundGlaucoma is an eye disease that causes vision loss and even blindness. The cup to disc ratio (CDR) is an important indicator for glaucoma screening and diagnosis. Accurate segmentation for the optic disc and cup helps obtain CDR. Although many deep learning-based methods have been proposed to segment the disc and cup for fundus image, achieving highly accurate segmentation performance is still a great challenge due to the heavy overlap between the optic disc and cup.MethodsIn this paper, we propose a two-stage method where the optic disc is firstly located and then the optic disc and cup are segmented jointly according to the interesting areas. Also, we consider the joint optic disc and cup segmentation task as a multi-category semantic segmentation task for which a deep learning-based model named DDSC-Net (densely connected depthwise separable convolution network) is proposed. Specifically, we employ depthwise separable convolutional layer and image pyramid input to form a deeper and wider network to improve segmentation performance. Finally, we evaluate our method on two publicly available datasets, Drishti-GS and REFUGE dataset.ResultsThe experiment results show that the proposed method outperforms state-of-the-art methods, such as pOSAL, GL-Net, M-Net and Stack-U-Net in terms of disc coefficients, with the scores of 0.9780 (optic disc) and 0.9123 (optic cup) on the DRISHTI-GS dataset, and the scores of 0.9601 (optic disc) and 0.8903 (optic cup) on the REFUGE dataset. Particularly, in the more challenging optic cup segmentation task, our method outperforms GL-Net by 0.7% in terms of disc coefficients on the Drishti-GS dataset and outperforms pOSAL by 0.79% on the REFUGE dataset, respectively.ConclusionsThe promising segmentation performances reveal that our method has the potential in assisting the screening and diagnosis of glaucoma.

Automated Glaucoma Diagnosis System Based on Fundus Images Features

Glaucoma is a disease that can damage the eye’s optic nerve and cause permanent vision loss or even total blindness if not detected in early stage and thus, it is important diagnose early to prevent blindness. Image processing techniques has been used to detect early glaucoma using the fundus images. In this paper, a computer aided glaucoma diagnosis system is proposed based on fundus image features. The optic disc and optic cup features are extracted from funds images and two parameters are calculated, namely: Cup to Disc Ratio (CDR) which indicates the enlargement of cup and the Inferior Superior to Nasal Temporal (ISNT) which determine the ratio of the thickness of the rim. Support Vector Machine (SVM) and k-Nearest Neighbor (KNN) classifiers are used to classify images into "Normal" or "Abnormal". The quality of both classifiers is evaluated and compared in terms of three performance metrics, namely: sensitivity, specificity and accuracy and satisfactory results have been achieved where the system accuracy is 95%. Moreover; Patient data such as age, family history of the disease, eye pressure and the last eye examination record were taken in account. The proposed system can categorize images into five categories: "no risk", "low risk", "moderate risk", "high risk" and "very high risk".

Ability of Optical Coherence Tomography in Early Detection of Primary Open Angle Glaucoma

Introduction: As glaucoma is one of the leading causes of blindness, its early diagnosis is crucial. Standard Visual Field (VF) examinations are used in the diagnosis and follow-up of glaucoma, but the major drawback is that the abnormalities do not appear until 20-40% of ganglion cells are lost. Defects in the Retinal Nerve Fiber Layer (RNFL), measured by Optical Coherence Tomography (OCT), is an excellent objective and quantitative method in the diagnosis and management of glaucoma at earlier stages. Aim: To assess the ability of OCT in diagnosing early glaucomatous changes using RNFL, Optic Nerve Head (ONH) and macular thickness parameters. Materials and Methods: A hospital-based case control study was done for 18 months at Department of Ophthalmology, Sawai Man Singh (SMS) Hospital and Medical College, Jaipur, Rajasthan, India. Fifty patients meeting the inclusion criteria were evaluated in the study as case group. To compare the results with those of a normal population 50 age and sex matched subjects were included. Each subject underwent detailed ocular examination and RNFL, ONH and macular thickness parameters were measured using Spectral Domain (SD) OCT. The unpaired t-test was used to compare continuous variables and Chi-square test was used to compare categorical variables. The Area Under the Curve (AUC) with its 95% Confidence Interval (CI) was calculated. The p-value &lt;0.05 was considered significant. Results: A total of 50 glaucoma or glaucoma suspect cases and 50 controls partcipated in the present study, i.e., 100 eyes in each group were studied. Mean RNFL thickness, superior thickness, inferior thickness and temporal thickness were significantly (p&lt;0.05) lower among cases than controls. Cup area, cup/disc (C/D) area ratio, horizontal and vertical cup to disc ratio (CDR) were significantly (p=0.0001) higher among cases than controls. Vertically Integrated Rim Area (VIRA) was significantly (p&lt;0.05) lower among cases (0.19±0.13) than controls (0.28±0.05). There was no significant (p&gt;0.05) difference in disc area between cases and controls. All the macular thickness parameters were significantly (p&lt;0.05) lower among cases than controls except fovea. Overall, ONH and macular thickness parameters had high sensitivity and specificity than RNFL parameters in glaucoma patients. Conclusion: The present study found that a combination of RNFL, ONH and macular thickness parameters improved the diagnostic accuracy of OCT in early detection of Primary Open Angle Glaucoma (POAG).

A Comparative Study of Deep Learning Models for Diagnosing Glaucoma From Fundus Images

Glaucoma is an eye disease that damages the optic nerve head (ONH) causing loss of vision. Therefore, early diagnosis and treatment are important in preventing possible blindness caused by glaucoma. Its current identification is based on the manual segmentation of the optic cup and disc to examine the cup-to-disc ratio (CDR). However, experts' annotation of these regions is a rather difficult and tedious task. Employing a convolutional neural network (CNN) for diagnosing glaucoma could be an alternative solution. However, its performance depends on the availability of a large number of labeled samples for the training phase. This paper presents an automatic glaucoma diagnosing framework based on three convolutional neural network (CNN) models with different learning methods, and compares the performance of these models with ophthalmologists. We use transfer and semi-supervised learning methods based on both labeled and unlabeled data. First, the transfer learning model starts with a pre-trained CNN model that was trained with non-medical data and fine-tunes it with our labeled data. Secondly, a semi-supervised framework is developed and trained using both labeled and unlabeled data based on two different unsupervised methods. The experimental results using two datasets, RIM-ONE and RIGA, demonstrate the efficacy of deep learning models when applied to glaucoma, which is a promising step towards automated screening for identifying individuals with early-stage glaucoma. Compared with annotations by two ophthalmologists, all the presented models achieve better performances, demonstrating the capability of artificial intelligence in diagnosing glaucoma with a high level of reliability.

Enhanced CNN-RNN deep learning-based framework for the detection of glaucoma

Glaucoma is the currently leading retinal disease, which damages the eye due to the intraocular pressure on the eye. If the disease is not diagnosed in the early stage, then there is a chance to lose the vision. Mainly the progression of glaucoma will be examined on the retinal part of the eye by an experienced ophthalmologist. The manual detection of glaucoma is very tedious, and also it consumes more time. Hence this problem can be solved by automatically detecting glaucoma by applying deep learning techniques. In this paper, deep learning-based enhanced image segmentation, and classification approaches are used to get more accurate results. The modified convolutional neural network (CNN) architecture is applied to segment the fundus images of the optic cup (OC) and the optic disk (OD) part to calculate the cup-to-disc ratio (CDR) of the optic nerve head (ONH). The trained segmented images of the CNN model are applied for the enhanced RNN-LSTM model to classify the images from glaucoma and non-glaucoma images. DRISHTI_GS public database is used to test and train the model.

A significant progress of computer aided diagnosis system using automated glaucoma screening

The automatic retinal image examination will be developing and significant screening device for initial recognition of eye diseases. This research proposes a computer aided diagnosis framework for initial recognition of glaucoma through Cup to Disc Ratio (CDR) measurement utilizing 2D fundus images. The system uses computer based analytical methods to procedure the patient data. The Glaucoma is chronic &amp; progressive eye disease which damages optic nerve (ON) caused by improved intraocular pressure (IOP) of eye. The Glaucoma mostly affects on optic disc (OD) by enhancing cup size. It might lead to blindness whether not recognized initially. The glaucoma detection through “Heidelberg Retinal Tomography (HRT) optical Coherence Tomography (OCT)” have been more costly. This system proposes an efficient technique to recognize glaucoma utilizing 2D fundus image. The physical analysis of OD is a normal process utilized for identifying glaucoma. In this manuscript, we suggest automatic OD parameterization method is based on segmented OD and optic cup (OC) region attained from fundus retinal images. To automatically extract OD and optic cup, we used K-means clustering technique, SLIC (Simple linear iterative clustering) method, Gabor filter and thresholding. To reshape the attained disc and cup boundary ellipse fitting (EF) is applied to obtained image. We also propose a novel method which automatically calculates CDR from non-stereographic fundus camera images. The CDR is initial clinical indicator for glaucoma assessment. Also, we have calculated OD and cup area. These features are validated by classifying image either normal or glaucomatous for given patient.

Retinal Nerve Fiber Layer Thickness in Healthy Eyes of Black, Chinese, and Latino Americans: A Population-Based Multiethnic Study

To compare peripapillary retinal nerve fiber layer (RNFL) thickness among healthy adults by race and ethnicity and to identify determinants of RNFL thickness. Population-based cross-sectional study. Data from 6133 individuals (11 585 eyes) from 3 population-based studies in Los Angeles County, California, 50 years of age or older and of self-described African, Chinese, or Latin American ancestry. We measured RNFL thickness and optic nerve head parameters using the Cirrus HD-OCT 4000. Multivariate linear mixed regression was used to evaluate factors associated with RNFL thickness among participants without ocular diseases. Determinants and modifiers of RNFL thickness. The mean age of the participants was 60.1 years (standard deviation, 7.4 years). Black Americans showed the lowest RNFL thickness and smallest cup-to-disc ratio (CDR), and Chinese Americans showed the largest CDR and disc area after adjusting for age and gender (all P < 0.05). Per each 10-year older age group, the average RNFL thickness was 2.5 μm (95% confidence interval [CI], 1.8-3.1 μm), 2.8 μm (95% CI, 2.3-3.3 μm), and 3.5 μm (95% CI, 2.9-4.1 μm) thinner for Black, Chinese, and Latino Americans, respectively (age trend P < 0.05 and interaction P= 0.041). Black Americans compared with Chinese Americans, older age, male gender, hypertension, diabetes, greater axial length (AL), bigger disc area, and lower scan signal strength were associated with thinner average RNFL. Race, age, AL, disc area, and scan signal strength consistently were associated with RNFL thickness in all quadrants, whereas gender, hypertension, and diabetes were associated with RNFL thickness in select quadrants. Age and race explained the greatest proportion of variance of RNFL thickness. Clinically important differences in RNFL thickness are present in healthy adults 50 years of age or older from different racial and ethnic groups of the same age, with the thinnest measures observed in Black Americans. This difference remains after accounting for disc size and AL. Furthermore, age-related RNFL thinning differs by race and ethnicity. Longitudinal studies are needed to verify our findings and to assess the influence of race and ethnicity in the clinical application of RNFL thickness.

Atlas-based score for automatic glaucoma risk stratification

Glaucoma is a disease that affects the optic nerve and can lead to blindness. The cup-to-disc ratio (CDR) measurement is one of the key clinical indicators for glaucoma assessment. However, the CDR only evaluates the relative sizes of the cup and optic disc (OD) via their diameters, and does not characterize local morphological changes that can inform clinicians on early signs of glaucoma. In this work, we propose a novel glaucoma score based on a statistical atlas framework that automatically quantifies the deformations of the OD region induced by glaucoma. A deep-learning approach is first used to segment the optic cup with a dedicated atlas-based data augmentation strategy. The segmented OD region (disc, cup and vessels) is then registered to the statistical OD atlas and the deformation is projected onto the atlas eigenvectors. The atlas glaucoma score (AGS) is then obtained by a linear combination of the principal modes of deformation of the atlas with linear discriminant analysis. The AGS performs better than the CDR on the three datasets used for evaluation, including RIM-ONE and ORIGA650. Compared to the CDR measurement, which yields an area under the ROC curve (AUC) of 91.4% using the expert segmentations, the AGS achieves an AUC of 98.2%. Our novel glaucoma score captures more complex deformations within the optic disc region than the CDR can. Such morphological changes are the first cue of glaucoma onset, before the visual field is affected. The proposed approach can thus significantly improve early detection of glaucoma.

Two-Year Multicenter Outcomes of iStent inject Trabecular Micro-Bypass Stents Combined with Phacoemulsification in Various Types of Glaucoma and Ocular Hypertension.

PurposeThis multicenter study evaluated 2-year effectiveness and safety following implantation of two second-generation trabecular micro-bypass stents (iStent inject®) with phacoemulsification.Materials and MethodsThis was a retrospective study of iStent inject implantation with phacoemulsification by nine surgeons across Australia. Eyes had mild to advanced glaucoma (predominantly primary open-angle/POAG, appositional angle-closure/ACG, or normal-tension/NTG) or ocular hypertension (OHT), and cataract. Evaluations included intraocular pressure (IOP); medications; proportions of eyes with 0 or ≥2 medications, reduced/stable medications versus preoperative, and IOP ≤15 mmHg; visual acuity; cup-to-disc ratio (CDR); visual fields (VF); adverse events; and secondary surgery.ResultsA total of 340 eyes underwent surgery and had 24-month follow-up data. At 24 months, mean IOP decreased by 16% from 16.4±4.7 mmHg preoperatively to 13.7±3.1 mmHg (p<0.001), and 77% of eyes achieved IOP of ≤15 mmHg versus 49% preoperatively (p<0.001). Mean number of medications decreased by 67% to 0.49±0.95 versus 1.49±1.20 preoperatively (p<0.001), with 74% of eyes medication-free versus 25% preoperatively (p<0.001), and 14% of eyes on ≥2 medications versus 46% preoperatively (p<0.001). Medication burden was reduced or stable in 98% of eyes versus preoperative. Stratified analyses showed significant IOP and medication reductions across glaucoma subtypes (POAG, ACG, NTG, OHT): 13–22% for IOP (p<0.01 for all) and 62–100% for medication (p<0.001 for all). Favorable safety included few adverse events; stable CDR, VF, and visual acuity; and filtering surgery in only 8 eyes (2.4%) over 2 years.ConclusionThis 340-eye multicenter dataset provides robust evidence of the safety and efficacy of iStent inject implantation with phacoemulsification, with significant and sustained IOP and medication reductions through 2 years. Results were similarly favorable across glaucoma subtypes (including POAG, ACG, NTG, OHT) and were attained across various glaucoma severities, clinical sites, and surgeons, highlighting the real-world versatility and utility of this treatment modality.

Automatic glaucoma screening using optic nerve head measurements and random forest classifier on fundus images.

Glaucoma is an optic neuropathy that gradually steals the patient's sight by damaging the optic nerve head (which is responsible for transferring images from the eye to the brain). Causing an estimated 12.3% of global blindness, glaucoma is considered as the first leading cause of irreversible blindness in the world. This paper presents a novel eye fundus image analysis algorithm for the automatic measurement of fundus related glaucoma indicators; Cup to Disc Ratio (CDR), verification of the ISNT rule, Disc Damage Likelihood Scale (DDLS), and the classification of the input fundus into glaucoma or non-glaucoma case using a random forest model. The proposed method is applied on the public image database 'HRF', and a local database containing both, normal and glaucoma cases, and resulted sensitivity, specificity, and accuracy of 1, 0.93 and 0.97 respectively. This technique presented the highest classification accuracy compared to previous works studied in the state of the art; hence, it can be used as a computer aided glaucoma diagnosis system by ophthalmologists to assist in their screening routine.

Enhanced CNN-RNN Deep Learning Based Framework for the Detection of Glaucoma

Glaucoma is the currently leading retinal disease, which damages the eye due to the intraocular pressure on the eye. If the disease is not diagnosed in the early stage, then there is a chance to lose the vision. Mainly the progression of glaucoma will be examined on the retinal part of the eye by an experienced ophthalmologist. The manual detection of glaucoma is very tedious, and also it consumes more time. Hence this problem can be solved by automatically detecting glaucoma by applying deep learning techniques. In this paper, deep learning-based enhanced image segmentation, and classification approaches are used to get more accurate results. The modified convolutional neural network (CNN) architecture is applied to segment the fundus images of the optic cup (OC) and the optic disk (OD) part to calculate the cup-to-disc ratio (CDR) of the optic nerve head (ONH). The trained segmented images of the CNN model are applied for the enhanced RNN-LSTM model to classify the images from glaucoma and non-glaucoma images. DRISHTI_GS public database is used to test and train the model.