Differentiation of Diabetic Status Using Statistical and Machine Learning Techniques on Optical Coherence Tomography Angiography Images.

Purpose: To investigate the potential of statistical and machine learning approaches to determine the diabetic status of patients from optical coherence tomography angiography (OCT-A) images. Methods: This was a retrospective cross-sectional observational study based at Manchester Royal Eye Hospital, United Kingdom. OCT-A scans were sequentially selected from one eye of each of 182 patients who were either not diabetic, diabetic without retinopathy, or diabetic with retinopathy requiring hospital follow-up. Eligible images were analyzed by expert purpose-built automated algorithms to calculate clinically relevant outcome measures. These were used in turn as inputs to machine learning and statistical procedures to derive algorithms to perform clinically relevant classifications of patient images into the clinical groups. Receiver operating characteristic curves for the classifiers were evaluated and predictive accuracy assessed using area under curve (AUC). Results: For distinguishing diabetic patients from those without diabetes, the Random Forest classifier provided the highest AUC (0.8). For distinguishing diabetic patients with significant retinopathy from those with no retinopathy, the highest AUC was represented by logistic regression (0.91). Conclusions: The study demonstrates the potential of novel techniques using automated analysis of OCT-A scans to diagnose patients with diabetes, or when diabetic status is known, to automatically determine those that require hospital input. Translational Relevance: This work advances the concept of a rapid and noninvasive clinical screening tool using OCT-A to determine a patient's diabetic status.

Iris recognition in the presence of ocular disease.

Iris recognition systems are among the most accurate of all biometric technologies with immense potential for use in worldwide security applications. This study examined the effect of eye pathology on iris recognition and in particular whether eye disease could cause iris recognition systems to fail. The experiment involved a prospective cohort of 54 patients with anterior segment eye disease who were seen at the acute referral unit of the Princess Alexandra Eye Pavilion in Edinburgh. Iris camera images were obtained from patients before treatment was commenced and again at follow-up appointments after treatment had been given. The principal outcome measure was that of mathematical difference in the iris recognition templates obtained from patients' eyes before and after treatment of the eye disease. Results showed that the performance of iris recognition was remarkably resilient to most ophthalmic disease states, including corneal oedema, iridotomies (laser puncture of iris) and conjunctivitis. Problems were, however, encountered in some patients with acute inflammation of the iris (iritis/anterior uveitis). The effects of a subject developing anterior uveitis may cause current recognition systems to fail. Those developing and deploying iris recognition should be aware of the potential problems that this could cause to this key biometric technology.

Perceptions and use of technology in older people with ophthalmic conditions.

Background: Technologies such as mobile applications are increasingly being developed for patients to help manage their clinical conditions. However there is a paucity of information confirming the capacity or willingness of older patients with ophthalmic complaints to engage with such computer applications. The aim of this paper is to assess the perception and use of a range of common computing technologies by older ophthalmic patients, in order to guide future ophthalmology-specific development and clinical use. Methods: Patients attending Manchester Royal Eye Hospital were surveyed with questions designed to measure their perceptions, attitudes and experiences of using technology.  Inclusion criteria included any patient aged 40 or over who attended the ophthalmology outpatients department. Results: A total of 300 patients completed the questionnaire. The male-to-female ratio was 128:169. The majority of patients owned predominantly mobile forms of technology such as tablets and smart phones. The most common uses of technology were for communicating with friends, watching television and gathering information. Patients aged over 80 had particular difficulty using technology and used it less regularly. Less than 10% overall stated eyesight as a reason for stopping using technology. Conclusions: Technology is used regularly by a large proportion of older ophthalmic patients, with numbers reducing significantly only in those aged 80 years or over. There appears to be potential for further medical use, though developers and clinicians should consider the perceptions and challenges highlighted through this survey.

Diagnostic Performance and Repeatability of a Novel Game-Based Visual Field Test for Children.

Purpose: To demonstrate utility of a game-based test ("Caspar's Castle") for the detection of visual field defects in children. Methods: A validity and reliability study was carried out at Manchester Royal Eye Hospital Pediatric Ophthalmology Outpatients Department. We recruited 108 children with no eye pathology (aged 4-12 years) and examined a single eye with the Caspar's Castle system using either normal thresholds or thresholds artificially adapted to recreate defects to assess diagnostic utility. Number of peripheral stimuli missed was used to determine sensitivity and specificity of artificial defect detection and to plot receiver-operator characteristic curves. A further 21 children (aged 4-16 years) with pathology were recruited and Caspar's fields compared qualitatively with established field testing. A total of 106 of the Caspar's Castle examinations were able to be performed twice and repeatability was determined through coefficient of repeatability and Bland-Altman chart. Results: In diagnostic testing using children with no eye pathology, 45 children completed a test using normal thresholds and 43 with tests using artificial defects. Area under receiver-operator characteristic curves for artificial defect detection was 0.895. Of the 21 children with pathology, seven had completed standard Humphreys field testing and Caspar's Castle fields corresponded with each of these by expert opinion. Coefficient of repeatability for number of points missed across all cohorts of children (106 patients) was 6.9 (95% confidence interval: 6.16-8.07). Conclusions: The Caspar's Castle system of assessing visual fields using novel game-based strategies demonstrates encouraging levels of sensitivity, specificity, and reliability. It could help address current difficulties in perimetry in young children.

Generative mathematical modelling to demonstrate virtual simulations of neovascular age related macular degeneration.

PURPOSE: To develop a generative mathematical model of wet age-related macular degeneration (AMD) and model the impact of injections of anti-vascular endothelial growth factor to virtual patients with the condition. METHODS: We isolated key pathophysiological components of macular degeneration in terms of macular edema development and response to anti-vascular endothelial growth factor (VEGF) agents. We developed mathematical models for each of these components using constants determined from published biological experimentation. Consequently, we combined the mathematical models of the separate components to arrive at an end-to-end model of the evolution of macular edema size and its response to treatment. RESULTS: We present a series of simulations based upon our idealised model. Initially, we demonstrate the theoretical change in macular edema height in wet macular degeneration over time without and with anti-VEGF interventions. In our final simulation, we demonstrate the powerful possibilities of virtual clinical trials by simulating a virtual model of a landmark study using our existing mathematical AMD model. CONCLUSIONS: Using our mathematical modelling based upon known pathological and pharmacological processes we have been able to model the effect of intravitreal injection of an anti-VEGF agent on macular edema from age related macular degeneration. We were subsequently able to mathematically simulate a major clinical trial with results that mirror many key features of the clinical established study. We anticipate that the generative model presented here can evolve to be a useful supportive tool in the challenge to deliver optimal therapy for patients with wet macular degeneration.

Swept-Source Optical Coherence Tomography Angiography Findings in Torpedo Maculopathy.

Torpedo maculopathy is a rare congenital anomaly of the retinal pigment epithelium (RPE). Various imaging modalities have been used to assess cases of torpedo maculopathy, including optical coherence tomography (OCT) and fundus autofluorescence (FAF). OCT angiography (OCTA) offers combined structural and flow characteristics of imaged lesions. The authors present OCTA findings in two cases of torpedo maculopathy. Common features include loss of RPE and choriocapillaris allowing greater visualization of larger vessels in the outer choroid. This confirms the potential of OCTA to provide greater detail of retinal and choroidal architecture and elucidate the histopathology of retino-choridal lesions. [Ophthalmic Surg Lasers Imaging Retina. 2017;48:932-935.].

Feasibility of Use of a Mobile Application for Nutrition Assessment Pertinent to Age-Related Macular Degeneration (MANAGER2).

PURPOSE: This is a feasibility study assessing use of a mobile phone application (app.) to measure nutrient intake relevant to age-related macular degeneration (AMD). METHODS: Inclusion criteria were age over 40 and ownership of a smartphone. Participants included healthy volunteers and those with ophthalmic conditions. They were asked to record daily food intake for a minimum of 3 days in a paper food diary and the app. A dietician analyzed the food diaries, and an independent researcher analyzed data from the app. Average daily intake of nutrients relevant to AMD (docosahexaenoic acid [DHA], eicosapentaenoic acid [EPA], vitamins E and C, copper, zinc, and lutein + zeaxanthin) were calculated for both and then compared. RESULTS: A total of 54 participants completed the app. and food diary. Male-to-female ratio was 7:20. Median (interquartile range [IQR]) age was 57 years (45.3-68.7 years). More than 90% of all values were within the limits of agreement for all micronutrients. Bland Altman agreement plots demonstrated clinically acceptable agreement between the two systems of analysis. CONCLUSIONS: This study has demonstrated that the app. is a feasible alternative to the food diary for assessing nutrient intake relevant to AMD. Further studies are suggested to assess long-term adherence and effect of the app. on nutrient intake in AMD patients. TRANSLATIONAL RELEVANCE: After smoking, nutritional modification is the key modifiable factor to reduce incidence of AMD. Use of the app. could be an efficient, easy way to monitor and improve dietary intake of required nutrients pertinent to AMD.

Use of iris recognition camera technology for the quantification of corneal opacification in mucopolysaccharidoses.

Mucopolysaccharidoses (MPS) can cause corneal opacification that is currently difficult to objectively quantify. With newer treatments for MPS comes an increased need for a more objective, valid and reliable index of disease severity for clinical and research use. Clinical evaluation by slit lamp is very subjective and techniques based on colour photography are difficult to standardise. In this article the authors present evidence for the utility of dedicated image analysis algorithms applied to images obtained by a highly sophisticated iris recognition camera that is small, manoeuvrable and adapted to achieve rapid, reliable and standardised objective imaging in a wide variety of patients while minimising artefactual interference in image quality.

Neodymium:YAG laser capsulotomy: a clinical morphological analysis.

BACKGROUND: There are no prospective controlled trials comparing methods of capsulotomy or patterns of capsulotomy openings in similarly graded opacified posterior capsules. This paper aims to investigate the effect of various forms of posterior capsular opacification (PCO) capsulotomy openings on visual function METHODS: Thirty-six eyes of 34 patients had vision tested and posterior capsules were digitally photographed. Each patient then underwent Nd:YAG laser capsulotomy. Patients returned 1 week later for repeat vision tests and photography. Analyses of areas of pearls and fibrosis were performed using the EPCO software system. Analyses of size and shape of capsulotomy was also done with image analysis software. The capsulotomy characteristics were analysed with respect to improvements in vision, taking into consideration the PCO scores. RESULTS: No correlation was found between capsulotomy dimensions and visual function improvement, even when PCO details were included in the analyses. Neither capsulotomy area, eccentricity, nor shape irregularity in the ranges measured was found to correlate significantly with eventual visual outcome in terms of contrast sensitivity, near and distance visual acuity, or glare readings. CONCLUSION: Performing a small capsulotomy (at least 1.5 mm in diameter), even if decentred up to 1 mm, may allow for satisfactory visual performance as long as the aperture is clear and not obscured by residual strands.

Principles of pseudophakic photic phenomena.

As ophthalmic science develops, the expectations of surgeons and patients undergoing cataract or refractive surgery also advance. Good Snellen visual acuity is not always an indicator for patient satisfaction, and the surgeon must understand the nature and pathogenesis of problems with other less recognised visual functions. This paper discusses the phenomenon of unwanted light images that may occur after surgery due to optical media imperfections, termed pseudophakic photic phenomena. It covers definitions, assessment, high-risk groups and possible explanations for the occurrence of such phenomena.

Posterior capsule morphology determinants of visual function.

BACKGROUND: This study explores the relative influence of fibrosis and pearl-type posterior capsule opacification (PCO) on visual function. It also examines the relevance of analyzing different central areas of posterior capsule on visual function. METHODS: Thirty-eight eyes of 33 patients had their vision tested and posterior capsules photographed digitally. Each patient then underwent Nd:YAG laser capsulotomy. Patients returned 1 week later for repeat vision tests and photography. Analyses of areas of pearls and fibrosis were performed using the EPCO software system. The difference in these values before and after Nd:YAG laser capsulotomy was compared to change in vision for each patient. The effect of analyzing the central 1.5-, 2.5- and 3.5-mm zones was studied. RESULTS: Stepwise multiple linear regression analysis shows that improvements in distance and near acuity are most strongly related to the central 1.5-2.5 mm of fibrosis and the central 3.5 mm of pearls. Improvements in contrast sensitivity are most strongly related to the central 1.5 mm of both fibrosis and pearls. CONCLUSION: In the assessment of PCO, the location and morphology of opacification correlate with visual function. Central fibrosis and paraxial pearls are important determinants of visual dysfunction.