Search

Automated extraction of retinal vasculature is becoming a crucial task during the study of pathological disorders present in the retinal fundus image. In this work, we propose an unsupervised approach for automatically extracting blood vessels from fundus photographs. In this paper, Logarithmic transformation (Log) and contrast limited adaptive histogram equalisation (CLAHE) are being used to boost the contrast level of the fundus photographs. After that, Matched filtering technique is used for further vessel enhancement. Then, different thresholding techniques are evaluated and compared to find out the best thresholding scheme for this segmentation. We have found that Otsu with entropy weighting thresholding is the best threshold method for segmenting the blood vessels. In the post-processing step, the area-based thresholding process is considered, and it gives the final vessel segmented image. Using the following statistical measures, the final vessel segmented image is compared to the ground truth image, such as sensitivity (Sens), precision (Spec), and accuracy (Acc). This work is evaluated by freely accessible DRIVE (Digital Retinal Images for Vessel Extraction), STARE (Structured Analysis of the Retina), and CHASE_DB1 (Child Heart and Health Study in England) datasets. This work achieves an average accuracy of 0.9562, 0.946, and 0.946 on the DRIVE, STARE, and CHASE_DB1 datasets, respectively. [ABSTRACT FROM AUTHOR]

Retinal blood vessels possess a complex structure in the retina and are considered an important biomarker for several retinal diseases. Ophthalmic diseases result in specific changes in the retinal vasculature; for example, diabetic retinopathy causes the retinal vessels to swell, and depending upon disease severity, fluid or blood can leak. Similarly, hypertensive retinopathy causes a change in the retinal vasculature due to the thinning of these vessels. Central retinal vein occlusion (CRVO) is a phenomenon in which the main vein causes drainage of the blood from the retina and this main vein can close completely or partially with symptoms of blurred vision and similar eye problems. Considering the importance of the retinal vasculature as an ophthalmic disease biomarker, ophthalmologists manually analyze retinal vascular changes. Manual analysis is a tedious task that requires constant observation to detect changes. The deep learning-based methods can ease the problem by learning from the annotations provided by an expert ophthalmologist. However, current deep learning-based methods are relatively inaccurate, computationally expensive, complex, and require image preprocessing for final detection. Moreover, existing methods are unable to provide a better true positive rate (sensitivity), which shows that the model can predict most of the vessel pixels. Therefore, this study presents the so-called vessel segmentation ultra-lite network (VSUL-Net) to accurately extract the retinal vasculature from the background. The proposed VSUL-Net comprises only 0.37 million trainable parameters and uses an original image as input without preprocessing. The VSUL-Net uses a retention block that specifically maintains the larger feature map size and low-level spatial information transfer. This retention block results in better sensitivity of the proposed VSUL-Net without using expensive preprocessing schemes. The proposed method was tested on three publicly available datasets: digital retinal images for vessel extraction (DRIVE), structured analysis of retina (STARE), and children's heart health study in England database (CHASE-DB1) for retinal vasculature segmentation. The experimental results demonstrated that VSUL-Net provides robust segmentation of retinal vasculature with sensitivity (Sen), specificity (Spe), accuracy (Acc), and area under the curve (AUC) values of 83.80%, 98.21%, 96.95%, and 98.54%, respectively, for DRIVE, 81.73%, 98.35%, 97.17%, and 98.69%, respectively, for CHASE-DB1, and 86.64%, 98.13%, 97.27%, and 99.01%, respectively, for STARE datasets. The proposed method provides an accurate segmentation mask for deep ophthalmic analysis. [ABSTRACT FROM AUTHOR]

Introduction: Voretigene neparvovec (VN) is a gene therapy and the first approved pharmacological treatment for biallelic RPE65-mediated inherited retinal dystrophies (IRD), a rare condition that starts in early life and causes vision to progressively deteriorate towards complete blindness. In a phase III trial, treatment with VN significantly improved functional vision and visual function, and in October 2019 the National Institute for Health and Care Excellence (NICE) Highly Specialised Technologies (HST) process recommended VN for patients in England and Wales. We assessed the cost-effectiveness of VN compared with best supportive care (BSC) in individuals with biallelic RPE65-mediated IRD in the UK.Methods: A Markov model was developed to estimate the incremental cost per quality-adjusted life-year (QALY) gained for VN compared with BSC, from the perspective of the UK National Health Service and Personal Social Services. Phase III trial data were used to inform transition probabilities up to year 1, after which the treatment effect was assumed to be maintained for 40 years, followed by a decline in vision. A bespoke elicitation exercise involving clinical experts, patients and carers was conducted to estimate utility values for each model health state.Results: At list price, VN is associated with incremental costs of £612,404 and incremental QALYs of 6.4, resulting in an incremental cost-effectiveness ratio (ICER) of £95,072 per QALY gained. Voretigene neparvovec is associated with a significant undiscounted QALY gain (20.5) and is therefore eligible for additional QALY weighting under the NICE HST process; an ICER of up to £205,000 per QALY gained could be considered cost-effective under this framework.Conclusion: The results of the model show VN to be a cost-effective use of healthcare resources in the UK at list price. The availability of a commercial discount in the UK (as considered in the NICE appraisal) means that in reality the ICER will be even lower. Plain language summary available for this article. [ABSTRACT FROM AUTHOR]

Objective: To summarize the key methodological challenges identified by health technology assessment (HTA) agencies assessing gene therapy (GT) and consideration of broad elements of value., Method: Economic evaluations (EEs) of voretigene neparvovec (VN) in RPE65 -mediated inherited retinal disease (IRD) published in English were selected. HTA evaluations from Australia, Canada, Ireland, Scotland, England, and the United States were reviewed. An existing methodological framework was used to identify the challenges and considerations., Results: Eight unique EEs were identified of which six were evaluated by HTA agencies. Incremental cost-effectiveness ratios ranged from $68,951 to $643,813 per quality-adjusted life-years (QALY) gained (healthcare perspective) and dominant to $480,130 per QALY gained (societal perspective). The key challenges were the lack of validated surrogate outcome, utility values and indirect costs from IRD patients, and limited evidence of the long-term treatment effect. Two HTA agencies reviewed a range of novel broader elements of value and whether they were associated with VN while other agencies discussed some elements of broader value. Caregiver disutility was included in some, but not all, evaluations., Conclusion: The methodological challenges were consistent with innovative interventions for rare diseases and managed using standard methods. Broader value was important to decision-makers but inconsistently applied across agencies. Possible reasons are limitations in the evidence available of the broader benefits that VN offers and how to incorporate these within an EE. A need exists for greater guidance and consistency across jurisdictions regarding the consideration of broader value that considers latest best practice.

Retinal vessels are considered important biomarkers for the detection of retinal diseases, like diabetic retinopathy (caused by diabetes) and hypertensive retinopathy (caused by hypertension). The manual finding from this retinal vasculature is time-consuming and costly. The image quality of the fundus image directly affects the accurate segmentation of these vessels in the automatic methods. With such inferior quality images, deep-learning-based methods are better for dealing with segmentation. Conventional deep-learning-based vessel segmentation methods deal the segmentation task with deeper convolutional neural networks and many trainable parameters. Minor changes in the retinal vasculature, such as those that result from the creation of new smaller vessels, is crucial for the keen analysis of diseases (e.g., diabetic retinopathy). The small vessels are crucial to segment, owing to continuous max-pooling operations and deeper networks. We herein present a pool-less residual segmentation network that is capable of segmenting even smaller vessels using a shallower network with a low number of trainable parameters. Our proposed pool-less residual segmentation network (PLRS-Net) is a vessel segmentation network that provides the pooling effect with strided convolution for better segmentation sensitivity. The final PLRS-Net is an advanced form of a pool-less segmentation network (PLS-Net) wherein semantic segmentation was performed with a few layers, and the residual connection fulfilled the feature enhancement strategy to construct PLRS-Net. PLS-Net and PLRS-Net are two separate networks that can perform vessel segmentation without prior preprocessing and postprocessing. To evaluate our proposed method, the experiments include three publicly available datasets: Digital retinal images for vessel extraction (DRIVE), child heart health study in England database (CHASE-DB1), and structured analysis of retina (STARE). The results demonstrate that our proposed method provides a high segmentation performance, achieving an average sensitivity (Sen) of 82.69, specificity (Spe) of 98.17, accuracy (Acc) 96.82, and area under the curve (AUC) of 98.35 for the DRIVE dataset, Sen of 83.01, Spe of 98.39, Acc of 97.31, and AUC of 98.63 for the CHASE-DB1 dataset, and a Sen of 86.35, Spe of 98.03, Acc of 97.15, and AUC of 98.99 for the STARE dataset. These accuracies show exceptional segmentation performance of the proposed method compared to state-of-the-art approaches for automatic vessel detection for diagnosis purposes. [ABSTRACT FROM AUTHOR]

OBJECTIVE -- The American Diabetes Association and the English NHS Diabetic Eye Screening Program recommend annual screening for diabetic retinopathy (DR) with referral to ophthalmology clinics of patients with sight-threatening DR (STDR). Using only longitudinal data from retinal photographs in the population-based NHS Diabetic Eye Screening Program in Gloucestershire, we developed a simple means to estimate risk of STDR. RESEARCH DESIGN AND METHODS -- From 2005, 14,554 patients with no DR or mild nonproliferative DR only at two consecutive annual digital photographic screenings were categorized by the presence of DR in neither, one, or both eyes at each screening and were followed for a further median 2.8 years. RESULTS -- Of 7,246 with no DR at either screening, 120 progressed to STDR, equivalent to an annual rate of 0.7%. Of 1,778 with no DR in either eye at first screening and in one eye at second screening, 80 progressed to STDR, equivalent to an annual rate of 1.9% and to a hazard ratio (HR) of 2.9 (95% CI 2.2-3.8) compared with those with no DR. Of 1,159 with background DR in both eyes at both screenings, 299 progressed to STDR equivalent to an annual rate of 11% and an HR of 18.2 (14.7-22.5) compared with individuals with no DR. CONCLUSIONS -- Combining the results from 2 consecutive years of photographic screening enables estimation of the risk of future development of STDR. In countries with systematic screening programs, these results could inform decisions about screening frequency. [ABSTRACT FROM AUTHOR]

Objectives: To assess uptake of the diabetes retinopathy screening programme in South East London and examine variation in attendance and screening outcomes. Methods: Cross-sectional study of patients on a centralized disease register invited for retinal screening during 2003. The influence of age, gender, deprivation, region of birth and type of diabetes on screening attendance and outcomes was assessed. Results: An estimated 46% of residents with known diabetes (9750/21,104) were offered digital retinopathy screening during 2003. In all, 88.9% of patients who were invited for screening attended. Attendance rates were significantly lower in younger patients (≤40 years), in those with type 1 diabetes and in patients residing in areas with the highest levels of deprivation. A total of 28.9% of patients had background retinopathy or worse during 2003. Retinopathy was more common in older patients (>40 years) and in individuals with type 1 diabetes after adjusting for other factors. Patients born outside the United Kingdom and the Republic of Ireland were significantly more likely to present with retinopathy. Conclusions: This study identified considerable inequity in the delivery of a local diabetic retinopathy screening programme. Equity audits should form an integral component of ongoing quality assurance monitoring of retinopathy screening programmes. [ABSTRACT FROM AUTHOR]

AimA key aim of the photographic screening model for diabetic retinopathy advocated by the National Screening Committee is a reduction in new blindness due to diabetic retinopathy within 5 years. This study determines the incidence of visual impairment due to diabetic retinopathy in Leeds in 2002 and provides a benchmark against which the success of the retinopathy screening programme in Leeds will be judged.MethodsA retrospective review of all blind and partially sighted registrations for 2002 was conducted. The 2001 Census data and the diabetes prevalence model developed by the Yorkshire and Humber Public Health Observatory were used to determine the total and diabetic populations of Leeds.ResultsDiabetic retinopathy was the primary cause of registration in 24 of the 398 completed records obtained; seven patients were registered blind and 17 partially sighted. For the total population in 2002, the incidence of blind and partially sighted registration due to diabetic retinopathy was 10 per million and 24 per million per year, respectively. For the diabetic population of Leeds in 2002, the incidence of blind and partial sighted registration due to diabetic retinopathy was 337 and 817 per million per year, respectively.ConclusionsThe incidence of blind registration due to diabetic retinopathy in Leeds in 2002 is similar to the estimate provided by the National Screening Committee but higher than the figure from other UK centres.Eye (2006) 20, 455–459. doi:10.1038/sj.eye.6701908; published online 20 May 2005 [ABSTRACT FROM AUTHOR]

The article presents a calendar of events from November 2005 to April 2007. A conference in Ontario will explore recent findings about the causes of and treatments for retinal diseases. A conference titled Tactile Graphics 2005: Third International Conference on Tactile Diagrams, Maps, and Pictures will be held in England. The 58th Annual Scientific Meeting of the Gerontological Society of America will be held in Florida. A skiing event that pairs visually and mobility impaired skiers with nondisabled guides. The 4th Annual Hawaii International Conference on Education will be held in January.

Eyes from 88 otters found dead in south-west England between 1990 and 2000, were collected as part of a larger pathological study. Histopathological examination of 131 eyes revealed dysplastic changes such as rosetting and folding in the retinas of 26 of the otters. In the eyes of 42 of the otters there were postmortem and fixation-induced retinal detachment which complicated the differentiation of dysplastic from normal retina, but 11 eyes had folds which probably indicated a dysplastic pathology. The eyes of 18 of the otters had inflammatory or autolytic changes which precluded a definitive evaluation of their dysplastic status. Liver samples from 55 of the otters were analysed for a range of polychlorinated hydrocarbons and for vitamin A. The otters with dysplastic retinas had significantly lower concentrations of vitamin A and higher concentrations of dieldrin than the otters with normal retinas. [ABSTRACT FROM AUTHOR]

Clinical neurological involvement at various times throughout the illness was recorded in 52% of 122 patients seen in central London who died from acquired immunodeficiency syndrome (AIDS). Various metabolic encephalopathies, dementias, focal encephalopathies, retinopathies and peripheral nerve pathology were the most frequent manifestations. Seven of 9 patients with a neurological presentation had no other major systemic illness. The median time from diagnosis of AIDS to death was 9 months and from onset of neurological symptoms to death 4 months. Human immunodeficiency virus dementia, central nervous system opportunistic infections, presence of Kaposi sarcoma, neurological presentations and minor symptoms were not associated with major change in survival time. [ABSTRACT FROM PUBLISHER]

The article looks at an early experience with the PASCAL method of photocoagulation as a means to treat diabetic retinopathy. The new technology dubbed PASCAL Pattern Scan Laser Photocoagulation is being used and studied at Manchester Royal Eye Hospital in England. It has the ability to semi-automate retinal photocoagulation procedures by delivering multiple laser burns in rapid predetermined sequence in the form of a pattern array.

Jay Stone is a final year Ph.D. student based at the Institute of Ophthalmology in London. She is attempting to identify novel therapeutic targets for the treatment of vascular proliferation in retinal disease. She believes that to be effective in the laboratory, scientists need to communicate their work to all audiences. She currently writes articles for the British Society of Cell Biology and BioNews. [ABSTRACT FROM AUTHOR]

The article presents a study on the impact of intravitreal foscarnet and viral pathogens, herpes simplex virus (HSV) and varicella zoster virus (VZV), on the outcome of acute retinal necrosis (ARN). For the study, researchers examined patients with ARN from January 1994 to January 2008 at Saint Thomas' Hospital (STH) and Moorfields Eye Hospital (MEH) in London, England. They found that 33 eyes manifested HSV-ARN and 48 manifested VZV-ARN. They concluded that people under intravitreal foscarnet treatment showed lower risk of retinal detachment.

Discusses the inability of primary-care patients and to detect retinopathy in diabetic patients. Description of the approach used for the detection of retinopathy in Liverpool, England; Prevention of severe visual loss due to proliferative diabetic retinopathy; Risks encountered by screened individuals who are not under ophthalmological care; Suggestion that updated guidelines for intervals for retinal examination should be determined.

The article focuses on the study from researchers at the University of Southampton in England which has identified a new genetic link to age-related macular degeneration (AMD), a condition that represents the most common cause of blindness and visual impairment in developed countries. The researchers conducted a case-on-control study in a sample of patients with AMD and controls and carried out a low-density screen of 32 genes using 93 single-nucleotide polymorphisms.