Automated diagnosis of Age-related Macular Degeneration using greyscale features from digital fundus images

Age-related Macular Degeneration (AMD) is one of the major causes of vision loss and blindness in ageing population. Currently, there is no cure for AMD, however early detection and subsequent treatment may prevent the severe vision loss or slow the progression of the disease. AMD can be classified into two types: dry and wet AMDs. The people with macular degeneration are mostly affected by dry AMD. Early symptoms of AMD are formation of drusen and yellow pigmentation. These lesions are identified by manual inspection of fundus images by the ophthalmologists. It is a time consuming, tiresome process, and hence an automated diagnosis of AMD screening tool can aid clinicians in their diagnosis significantly. This study proposes an automated dry AMD detection system using various entropies (Shannon, Kapur, Renyi and Yager), Higher Order Spectra (HOS) bispectra features, Fractional Dimension (FD), and Gabor wavelet features extracted from greyscale fundus images. The features are ranked using t-test, Kullback–Lieber Divergence (KLD), Chernoff Bound and Bhattacharyya Distance (CBBD), Receiver Operating Characteristics (ROC) curve-based and Wilcoxon ranking methods in order to select optimum features and classified into normal and AMD classes using Naive Bayes (NB), k-Nearest Neighbour (k-NN), Probabilistic Neural Network (PNN), Decision Tree (DT) and Support Vector Machine (SVM) classifiers. The performance of the proposed system is evaluated using private (Kasturba Medical Hospital, Manipal, India), Automated Retinal Image Analysis (ARIA) and STructured Analysis of the Retina (STARE) datasets. The proposed system yielded the highest average classification accuracies of 90.19%, 95.07% and 95% with 42, 54 and 38 optimal ranked features using SVM classifier for private, ARIA and STARE datasets respectively. This automated AMD detection system can be used for mass fundus image screening and aid clinicians by making better use of their expertise on selected images that require further examination.

Decision support system for age-related macular degeneration using discrete wavelet transform

Age-related macular degeneration (AMD) affects the central vision and subsequently may lead to visual loss in people over 60 years of age. There is no permanent cure for AMD, but early detection and successive treatment may improve the visual acuity. AMD is mainly classified into dry and wet type; however, dry AMD is more common in aging population. AMD is characterized by drusen, yellow pigmentation, and neovascularization. These lesions are examined through visual inspection of retinal fundus images by ophthalmologists. It is laborious, time-consuming, and resource-intensive. Hence, in this study, we have proposed an automated AMD detection system using discrete wavelet transform (DWT) and feature ranking strategies. The first four-order statistical moments (mean, variance, skewness, and kurtosis), energy, entropy, and Gini index-based features are extracted from DWT coefficients. We have used five (t test, Kullback–Lieber Divergence (KLD), Chernoff Bound and Bhattacharyya Distance, receiver operating characteristics curve-based, and Wilcoxon) feature ranking strategies to identify optimal feature set. A set of supervised classifiers namely support vector machine (SVM), decision tree, k -nearest neighbor ( k -NN), Naive Bayes, and probabilistic neural network were used to evaluate the highest performance measure using minimum number of features in classifying normal and dry AMD classes. The proposed framework obtained an average accuracy of 93.70 %, sensitivity of 91.11 %, and specificity of 96.30 % using KLD ranking and SVM classifier. We have also formulated an AMD Risk Index using selected features to classify the normal and dry AMD classes using one number. The proposed system can be used to assist the clinicians and also for mass AMD screening programs.

Prevalence and visual risk factors for falls in bilateral cataract patients in Ho Chi Minh City, Vietnam

Purpose To determine the prevalence of falls in the 12 months prior to cataract surgery and examine the associations between visual and other risk factors and falls among older bilateral cataract patients in Vietnam. Methods Data collected from 413 patients in the week before scheduled cataract surgery included a questionnaire and three objective visual tests. Results The outcome of interest was self-reported falls in the previous 12 months. A total of 13% (n = 53) of bilateral cataract patients reported 60 falls within the previous 12 months. After adjusting for age, sex, race, employment status, comorbidities, medication usage, refractive management, living status and the three objective visual tests in the worse eye, women (odds ratio, OR, 4.64, 95% confidence interval, CI, 1.85–11.66), and those who lived alone (OR 4.51, 95% CI 1.44–14.14) were at increased risk of a fall. Those who reported a comorbidity were at decreased risk of a fall (OR 0.43, 95% CI 0.19–0.95). Contrast sensitivity (OR 0.31, 95% CI 0.10–0.95) was the only significant visual test associated with a fall. These results were similar for the better eye, except the presence of a comorbidity was not significant (OR 0.45, 95% CI 0.20–1.02). Again, contrast sensitivity was the only significant visual factor associated with a fall (OR 0.15, 95% CI 0.04–0.53). Conclusion Bilateral cataract patients in Vietnam are potentially at high risk of falls and in need of falls prevention interventions. It may also be important for ophthalmologists and health professionals to consider contrast sensitivity measures when prioritizing cataract patients for surgery and assessing their risk of falls.

Development of appropriateness explicit criteria for cataract extraction by phacoemulsification

Background: Consensus development techniques were used in the late 1980s to create explicit criteria for the appropriateness of cataract extraction. We developed a new appropriateness of indications tool for cataract following the RAND method. We tested the validity of our panel results. Methods: Criteria were developed using a modified Delphi panel judgment process. A panel of 12 ophthalmologists was assembled. Ratings were analyzed regarding the level of agreement among panelists. We studied the influence of all variables on the final panel score using linear and logistic regression models. The explicit criteria developed were summarized by classification and regression tree analysis. Results: Of the 765 indications evaluated by the main panel in the second round, 32.9% were found appropriate, 30.1% uncertain, and 37% inappropriate. Agreement was found in 53% of the indications and disagreement in 0.9%. Seven variables were considered to create the indications and divided into three groups: simple cataract, with diabetic retinopathy, or with other ocular pathologies. The preoperative visual acuity in the cataractous eye and visual function were the variables that best explained the panel scoring. The panel results were synthesized and presented in three decision trees. Misclassification error in the decision trees, as compared with the panel original criteria, was 5.3%. Conclusion: The parameters tested showed acceptable validity for an evaluation tool. These results support the use of this indication algorithm as a screening tool for assessing the appropriateness of cataract extraction in field studies and for the development of practice guidelines.

Age-dependent accumulation of lipofuscin in perivascular and subretinal microglia in experimental mice

Fundus autofluorescence (AF) imaging by confocal scanning laser ophthalmoscopy has been widely used by ophthalmologists in the diagnosis/monitoring of various retinal disorders. It is believed that fundus AF is derived from lipofuscin in retinal pigment epithelial (RPE) cells; however, direct clinicopathological correlation has not been possible in humans. We examined fundus AF by confocal scanning laser ophthalmoscopy and confocal microscopy in normal C57BL/6 mice of different ages. Increasingly strong AF signals were observed with age in the neuroretina and subretinal/RPE layer by confocal scanning laser ophthalmoscopy. Unlike fundus AF detected in normal human subjects, mouse fundus AF appeared as discrete foci distributed throughout the retina. Most of the AF signals in the neuroretina were distributed around retinal vessels. Confocal microscopy of retinal and choroid/RPE flat mounts demonstrated that most of the AF signals were derived from Iba-1+ perivascular and subretinal microglia. An age-dependent accumulation of Iba-1+ microglia at the subretinal space was observed. Lipofuscin granules were detected in large numbers in subretinal microglia by electron microscopy. The number of AF+ microglia and the amount of AF granules/cell increased with age. AF granules/lipofuscin were also observed in RPE cells in mice older than 12 months, but the number of AF+ RPE cells was very low (1.48 mm-2 and 5.02 mm-2 for 12 and 24 months, respectively) compared to the number of AF+ microglial cells (20.63 mm-2 and 76.36 mm-2 for 6 and 24 months, respectively). The fluorescence emission fingerprints of AF granules in subretinal microglia were the same as those in RPE cells. Our observation suggests that perivascular and subretinal microglia are the main cells producing lipofuscin in normal aged mouse retina and are responsible for in vivo fundus AF. Microglia may play an important role in retinal aging and age-related retinal diseases.

Clinical risk factors for age-related macular degeneration: a systematic review and meta-analysis

Background: Age-related macular degeneration (AMD) is the leading cause of blindness in Western countries. Numerous risk factors have been reported but the evidence and strength of association is variable. We aimed to identify those risk factors with strong levels of evidence which could be easily assessed by physicians or ophthalmologists to implement preventive interventions or address current behaviours.

Epidemiology of giant retinal tears in the United Kingdom: The British giant retinal tear epidemiology eye study (BGEES)

To determine the incidence of giant retinal tear (GRT) in the United Kingdom and to provide epidemiologic data, clinical characteristics, treatment methods, and short-term outcomes in affected and fellow eyes. METHODS. Patients with a newly developed GRT (90° or greater in circumferential extent associated with posterior vitreous detachment) were identified prospectively over a 13-month period (January 2007-January 2008, inclusive) by active surveillance through the British Ophthalmic Surveillance Unit. Questionnaire-based data were obtained from reporting ophthalmologists at baseline and 12 months. RESULTS. Sixty patients (62 eyes) developed a new GRT, giving a U.K. annual incidence of 0.094 (95% CI 0.072-0.120) cases or 0.091 (95% CI 0.069-0.117) patients per 100,000. The GRTs were mostly idiopathic (54.8%), affected middle-aged (mean, 42.2 years), white British (93.3%) males (71.7%), with presenting vision worse than 20/40 in 59.7%, foveal detachment in 45.2%, and proliferative vitreoretinopathy of grade C (PVR-C) or worse in 11.3%. Treatment in most was managed by pars plana vitrectomy (93.5%) with laser retinopexy (52.5%) and silicone oil endotamponade (75.8%). Prophylactic 360° laser or cryotherapy was applied to 39.0% of the fellow eyes. At mean follow-up of 11.3 months, eventual retinal reattachment was attained in 94.7%, although only 42.1% achieved vision of =20/40. Neither GRT nor RD developed in any of the 19 nontraumatic, noniatrogenic, prophylactically treated fellow eyes. CONCLUSIONS. This study is the first population-based prospective effort to evaluate the epidemiology of GRT. Although onlya minority presented with PVR-C and high retinal reattachment rates were achieved, fewer than half had vision sufficient for driving in the GRT eye.

Interventions for prevention of giant retinal tear in the fellow eye

Background: A giant retinal tear is a full-thickness retinal break that extends circumferentially around the retina for 90 degrees ormore in the presence of a posteriorly detached vitreous. It causes significant visual morbidity from retinal detachment and proliferative vitreoretinopathy. The fellow eye of patients who have had a spontaneous giant retinal tear has an increased risk of developing a giant retinal tear, a retinal detachment or both. Interventions such as 360-degree encircling scleral buckling, 360-degree cryotherapy and 360-degree laser photocoagulation have been advocated by some ophthalmologists as prophylaxis for the fellow eye against the development of a giant retinal tear and/or a retinal detachment, or to prevent its extension. Objectives: To evaluate the effectiveness of prophylactic 360-degree interventions in the fellow eye of patients with unilateral giant retinal tear to prevent the occurrence of a giant retinal tear and/or a retinal detachment. Search strategy: We searched the Cochrane Central Register of Controlled Trials (CENTRAL) (which contains the Cochrane Eyes and Vision Group Trials Register) (The Cochrane Library 2008, Issue 4), MEDLINE (January 1950 to December 2008), EMBASE (January 1980 to December 2008) and Latin American and Caribbean Literature on Health Sciences (LILACS) (January 1982 to December 2008). In addition, we searched the proceedings of the Annual Meeting of the Association for Research in Vision and Ophthalmology (ARVO) up to 2008 for information about other relevant studies. There were no language or date restrictions in the search for trials. The electronic databases were last searched on 15 December 2008. Selection criteria: Prospective randomised controlled trials (RCTs) comparing one prophylactic treatment for fellow eyes of patients with giant retinal tear against observation (no treatment) or another form of prophylactic treatment. In the absence of RCTs, we planned to discuss case-control studies that met the inclusion criteria but we would not conduct a meta-analysis using these studies. Data collection and analysis: We did not find any studies that met the inclusion criteria for the review and therefore no assessment of methodological quality or meta-analysis could be performed. Main results: No studies met the inclusion criteria for this review. Authors' conclusions: No strong evidence in the literature was found to support or refute prophylactic 360-degree treatments to prevent a giant retinal tear or a retinal detachment in the fellow eye of patients with unilateral giant retinal tears. Copyright © 2009 The Cochrane Collaboration. Published by John Wiley & Sons, Ltd.

Interventions for prevention of giant retinal tear in the fellow eye.

BACKGROUND: A giant retinal tear is a full-thickness retinal break that extends circumferentially around the retina for 90 degrees or more in the presence of a posteriorly detached vitreous. It causes significant visual morbidity from retinal detachment and proliferative vitreoretinopathy. The fellow eye of patients who have had a spontaneous giant retinal tear has an increased risk of developing a giant retinal tear, a retinal detachment or both. Interventions such as 360-degree encircling scleral buckling, 360-degree cryotherapy and 360-degree laser photocoagulation have been advocated by some ophthalmologists as prophylaxis for the fellow eye against the development of a giant retinal tear and/or a retinal detachment, or to prevent its extension. OBJECTIVES: To evaluate the effectiveness of prophylactic 360-degree interventions in the fellow eye of patients with unilateral giant retinal tear to prevent the occurrence of a giant retinal tear and/or a retinal detachment. SEARCH STRATEGY: We searched the Cochrane Central Register of Controlled Trials (CENTRAL) (which contains the Cochrane Eyes and Vision Group Trials Register) (The Cochrane Library 2008, Issue 4), MEDLINE (January 1950 to December 2008), EMBASE (January 1980 to December 2008) and Latin American and Caribbean Literature on Health Sciences (LILACS) (January 1982 to December 2008). In addition, we searched the proceedings of the Annual Meeting of the Association for Research in Vision and Ophthalmology (ARVO) up to 2008 for information about other relevant studies. There were no language or date restrictions in the search for trials. The electronic databases were last searched on 15 December 2008. SELECTION CRITERIA: Prospective randomised controlled trials (RCTs) comparing one prophylactic treatment for fellow eyes of patients with giant retinal tear against observation (no treatment) or another form of prophylactic treatment. In the absence of RCTs, we planned to discuss case-control studies that met the inclusion criteria but we would not conduct a meta-analysis using these studies. DATA COLLECTION AND ANALYSIS: We did not find any studies that met the inclusion criteria for the review and therefore no assessment of methodological quality or meta-analysis could be performed. MAIN RESULTS: No studies met the inclusion criteria for this review. AUTHORS' CONCLUSIONS: No strong evidence in the literature was found to support or refute prophylactic 360-degree treatments to prevent a giant retinal tear or a retinal detachment in the fellow eye of patients with unilateral giant retinal tears.

Interventions for prevention of giant retinal tear in the fellow eye.

A giant retinal tear is a full-thickness retinal break that extends circumferentially around the retina for 90 degrees or more in the presence of a posteriorly detached vitreous. It causes significant visual morbidity from retinal detachment and proliferative vitreoretinopathy. The fellow eye of patients who have had a spontaneous giant retinal tear has an increased risk of developing a giant retinal tear, a retinal detachment or both. Interventions such as 360-degree encircling scleral buckling, 360-degree cryotherapy and 360-degree laser photocoagulation have been advocated by some ophthalmologists as prophylaxis for the fellow eye against the development of a giant retinal tear and/or a retinal detachment, or to prevent its extension. To evaluate the effectiveness of prophylactic 360-degree interventions in the fellow eye of patients with unilateral giant retinal tear to prevent the occurrence of a giant retinal tear, a retinal detachment or both. We searched CENTRAL (which contains the Cochrane Eyes and Vision Group Trials Register) (The Cochrane Library 2011, Issue 11), MEDLINE (January 1950 to December 2011), EMBASE (January 1980 to December 2011), Latin American and Caribbean Literature on Health Sciences (LILACS) (January 1982 to December 2011), the metaRegister of Controlled Trials (mRCT) (www.controlled-trials.com), ClinicalTrials.gov (www.clinicaltrials.gov) and the WHO International Clinical Trials Registry Platform (ICTRP) (www.who.int/ictrp/search/en). There were no date or language restrictions in the electronic searches for trials. The electronic databases were last searched on 6 December 2011. In addition, we searched the proceedings of the Annual Meeting of the Association for Research in Vision and Ophthalmology (ARVO) up to 2008 for information about other relevant studies. Prospective randomised controlled trials (RCTs) comparing one prophylactic treatment for fellow eyes of patients with giant retinal tear against observation (no treatment) or another form of prophylactic treatment. In the absence of RCTs, we planned to discuss case-control studies that met the inclusion criteria but we would not conduct a meta-analysis using these studies. We did not find any studies that met the inclusion criteria for the review and therefore no assessment of methodological quality or meta-analysis could be performed. No studies met the inclusion criteria for this review. No strong evidence in the literature was found to support or refute prophylactic 360-degree treatments to prevent a giant retinal tear or a retinal detachment in the fellow eye of patients with unilateral giant retinal tears.

Surveillance of severe chemical corneal injuries in the UK

AIM: To estimate the incidence of severe chemical corneal injuries in the UK and describe presenting clinical features and initial management.

METHODS: All patients with severe chemical corneal injury in the UK from December 2005 to November 2006 inclusive were prospectively identified using the British Ophthalmological Surveillance Unit. Reporting ophthalmologists provided information regarding presentation and follow-up.

RESULTS: Twelve cases were identified, giving a minimum estimated incidence in the UK of severe chemical corneal injury of 0.02 per 100,000. 66.7% of injuries were in males of working age, 50% occurred at work, and alkali was causative in 66.7%. Only one patient was wearing eye protection at the time of injury, 75% received immediate irrigation. Six patients required one or more surgical procedures, most commonly amniotic membrane graft. At 6 months' follow-up, the best-corrected visual acuity was 6/12 or better in five patients, and worse than 6/60 in two.

CONCLUSION: The incidence of severe chemical corneal injury in the UK is low. The cases that occur can require extended hospital treatment, with substantial ocular morbidity and visual sequelae. Current enforcement of eye protection in the workplace in the UK has probably contributed to a reduced incidence of severe ocular burns.

Developing the specifications of an open angle glaucoma screening intervention in the United Kingdom: a Delphi approach.

Abstract
BACKGROUND:
Glaucoma is a leading cause of blindness. Early detection is advocated but there is insufficient evidence from randomized controlled trials (RCTs) to inform health policy on population screening. Primarily, there is no agreed screening intervention. For a screening programme, agreement is required on the screening tests to be used, either individually or in combination, the person to deliver the test and the location where testing should take place. This study aimed to use ophthalmologists (who were experienced glaucoma subspecialists), optometrists, ophthalmic nurses and patients to develop a reduced set of potential screening tests and testing arrangements that could then be explored in depth in a further study of their feasibility for evaluation in a glaucoma screening RCT.
METHODS:
A two-round Delphi survey involving 38 participants was conducted. Materials were developed from a prior evidence synthesis. For round one, after some initial priming questions in four domains, specialists were asked to nominate three screening interventions, the intervention being a combination of the four domains; target population, (age and higher risk groups), site, screening test and test operator (provider). More than 250 screening interventions were identified. For round two, responses were condensed into 72 interventions and each was rated by participants on a 0-10 scale in terms of feasibility.
RESULTS:
Using a cut-off of a median rating of feasibility of =5.5 as evidence of agreement of intervention feasibility, six interventions were identified from round 2. These were initiating screening at age 50, with a combination of two or three screening tests (varying combinations of tonometry/measures of visual function/optic nerve damage) organized in a community setting with an ophthalmic trained technical assistant delivering the tests. An alternative intervention was a 'glaucoma risk score' ascertained by questionnaire. The advisory panel recommended that further exploration of the feasibility of screening higher risk populations and detailed specification of the screening tests was required.
CONCLUSIONS:
With systematic use of expert opinions, a shortlist of potential screening interventions was identified. Views of users, service providers and cost-effectiveness modeling are now required to identify a feasible intervention to evaluate in a future glaucoma screening trial.

Primary angle closure glaucoma:A descriptive study in Scottish Caucasians

Purpose: The aim of this study is to describe the ocular and demographic features of Caucasian patients newly presenting with primary angle closure glaucoma and the proportion of workload it represents at a tertiary university hospital glaucoma service. Methods: A retrospective case notes review was conducted for all Caucasian patients newly diagnosed with narrow angles, primary angle closure, acute primary angle closure and primary angle closure glaucoma that were seen over a period of 2 years. Demographic and ocular variables were compared and statistical analysis was carried out with the paired t -test and chi-squared test. Number of primary open angle closure glaucoma and acute angle closure cases were compared with total number of new referrals to the department, new patients diagnosed with glaucoma and population numbers for the North East of Scotland. Results: One hundred and four patients were analysed. Twenty-four (23.1%) had narrow angles, 30 (28.8%) had primary angle closure and 50 (48.1%) had primary angle closure glaucoma. Twelve (11.5%) presented with acute primary angle closure. There was no significant difference for gender, age, hypermetropia or visual acuity between groups. Primary angle closure glaucoma constituted 22.9% (50/128) of newly diagnosed glaucoma cases. Based on the 2001 Scotland census, the crude annual incidence of newly diagnosed primary angle closure glaucoma was estimated at 14.8 per 100000 and 3.6 per 100000 for acute primary angle closure in the over-45-year-old population. Conclusion: Our study confirms that primary angle closure glaucoma is uncommon in Caucasians, but not as rare as originally perceived as it makes up a fair proportion (22.9%) of glaucoma workload. © 2009 The Authors Journal Compilation © 2009 Royal Australian and New Zealand College of Ophthalmologists.