A Novel Approach to Tradition: Torres Strait Islanders and Ion Idriess

This paper considers the significance of the novel Drums of Mer (1941) in contemporary Torres Strait Islanders' lives. Its use as narrative by many Islanders today constitutes one means by which men especially have come to know themselves, white others, and their past. In particular, I explore the ways in which this story appeals to and is appealed to by Yam Island people. Contrary to literary deconstructions of Idriess's representations of Aboriginal and Torres Strait Islander people, my paper argues that in seriously attending to Torres Strait readings of Drums of Mer we can see that for contemporary Islander readers, it is not themselves who are other but rather the white protagonists. I employ Said's (1994) notion of ‘cultural overlap’ and de Certeau's (1988) understandings of reading and writing as ‘everyday practices’ to frame my analysis of the differing impacts of the historical novel, Drums of Mer, and the Reports of the Cambridge Anthropological Expedition to Torres Straits. It is through story telling that Yam Island selves are placed in the past and the present, and in Idriess's memorable story a similar effect is achieved. In his novel approach, the past becomes his-story, a romanticised refraction of the Reports. Unlike the Reports, this novel is a sensual rendering of a Torres Strait past, and at this level it operates as a mnemonic device for Yam Island people, triggering memories and the imagination through the senses. This Torres Strait Islander detour by way of a past via a story, can be understood as a means by which Yam Island people continue to actively produce powerful images of themselves, for both themselves and for others.     

The National QAAMS Program – A Practical Example of PoCT Working in the Community

The Quality Assurance for Aboriginal and Torres Strait Islander Medical Services (QAAMS) Program is the largest and longest-standing national point-of-care testing (PoCT) program in Australia. With a focus on PoCT for diabetes management, it now operates in 115 Indigenous medical services and has been funded continuously by the Australian Government for 11 years. A recent independent evaluation of the QAAMS Program concluded that the program continues to meet best practice standards for Indigenous healthcare, diabetes management and PoCT.     

The Reading of Components of Diabetic Retinopathy: An Evolutionary Approach for Filtering Normal Digital Fundus Imaging in Screening and Population Based Studies

In any diabetic retinopathy screening program, about two-thirds of patients have no retinopathy. However, on average, it takes a human expert about one and a half times longer to decide an image is normal than to recognize an abnormal case with obvious features. In this work, we present an automated system for filtering out normal cases to facilitate a more effective use of grading time. The key aim with any such tool is to achieve high sensitivity and specificity to ensure patients'' safety and service efficiency. There are many challenges to overcome, given the variation of images and characteristics to identify. The system combines computed evidence obtained from various processing stages, including segmentation of candidate regions, classification and contextual analysis through Hidden Markov Models. Furthermore, evolutionary algorithms are employed to optimize the Hidden Markov Models, feature selection and heterogeneous ensemble classifiers. In order to evaluate its capability of identifying normal images across diverse populations, a population-oriented study was undertaken comparing the software''s output to grading by humans. In addition, population based studies collect large numbers of images on subjects expected to have no abnormality. These studies expect timely and cost-effective grading. Altogether 9954 previously unseen images taken from various populations were tested. All test images were masked so the automated system had not been exposed to them before. This system was trained using image subregions taken from about 400 sample images. Sensitivities of 92.2% and specificities of 90.4% were achieved varying between populations and population clusters. Of all images the automated system decided to be normal, 98.2% were true normal when compared to the manual grading results. These results demonstrate scalability and strong potential of such an integrated computational intelligence system as an effective tool to assist a grading service.     

Adding retinal photography to screening for diabetic retinopathy: a prospective study in primary care.

OBJECTIVE--To evaluate whether adding retinal photography improved community screening for diabetic retinopathy. SETTING--Mobile screening unit at rural and urban general practices in south west England. SUBJECTS--1010 diabetic patients from primary care. DESIGN--Prospective study; patients were examined by ophthalmoscopy by general practitioners or opticians without fundal photographs and again with photographs, and assessments were compared to those of an ophthalmologist. MAIN OUTCOME MEASURES--Whether fundal photography improved the sensitivity of detection of retinopathy and referrable diabetic retinopathy, and whether this sensitivity could be improved by including a review of the films by the specialist. RESULTS--Diabetic retinopathy was detected by the ophthalmologist in 205 patients (20.5%) and referrable retinopathy in 49 (4.9%). The sensitivity of the general practitioners and opticians for referrable retinopathy with ophthalmoscopy was 65%, and improved to 84% with retinal photographs. General practitioners'' sensitivity in detecting background retinopathy improved with photographs from 22% to 65%; opticians'' sensitivity in detecting background retinopathy improved from 43% to 71%. The sensitivity of detecting referrable retinopathy by general practitioners improved from 56% to 80% with photographs; for opticians it improved from 75% to 88%. CONCLUSIONS--Combining modalities of screening by providing photography with specialist review of all films in addition to direct ophthalmoscopy through dilated pupils improves assessment and referral for diabetic retinopathy by general practitioners and opticians. With further training and experience, primary care screeners should be able to achieve a sensitivity that will achieve an effective, acceptable, and economical community based screening programme for this condition.     

A Novel Image Recuperation Approach for Diagnosing and Ranking Retinopathy Disease Level Using Diabetic Fundus Image

Retinal fundus images are widely used in diagnosing and providing treatment for several eye diseases. Prior works using retinal fundus images detected the presence of exudation with the aid of publicly available dataset using extensive segmentation process. Though it was proved to be computationally efficient, it failed to create a diabetic retinopathy feature selection system for transparently diagnosing the disease state. Also the diagnosis of diseases did not employ machine learning methods to categorize candidate fundus images into true positive and true negative ratio. Several candidate fundus images did not include more detailed feature selection technique for diabetic retinopathy. To apply machine learning methods and classify the candidate fundus images on the basis of sliding window a method called, Diabetic Fundus Image Recuperation (DFIR) is designed in this paper. The initial phase of DFIR method select the feature of optic cup in digital retinal fundus images based on Sliding Window Approach. With this, the disease state for diabetic retinopathy is assessed. The feature selection in DFIR method uses collection of sliding windows to obtain the features based on the histogram value. The histogram based feature selection with the aid of Group Sparsity Non-overlapping function provides more detailed information of features. Using Support Vector Model in the second phase, the DFIR method based on Spiral Basis Function effectively ranks the diabetic retinopathy diseases. The ranking of disease level for each candidate set provides a much promising result for developing practically automated diabetic retinopathy diagnosis system. Experimental work on digital fundus images using the DFIR method performs research on the factors such as sensitivity, specificity rate, ranking efficiency and feature selection time.     

Hybrid Nature Inspired SMO-GBM Classifier for Exudate Classification on Fundus Retinal Images

Background: The diabetic retinopathy can result in loss of vision if not detected in the earlier stages. Exudates are the lesions which play a crucial role in early diagnosis of diabetic retinopathy. The localization of exudates lesions with high values of performance metrics is complicated due to presence of blood vessels and other noisy artifacts. Method: We present computer aided system for classification of retinal fundus images using a novel nature inspired spider monkey optimization for parameter tuning of gradient boosting machines classifier. The image enhancement has been performed with histogram equalization and contourlet transform. The pixels belonging to optic disc region are detected and eliminated using circular Hough transform and Otsu's segmentation method. We have employed Kirsch's matrices for blood vessel detection. The GLCM based feature vector extraction has been employed for textural features. The classification has been performed with hybrid SMO-GBM classifier. Result: We have utilized the STARE database for validation of proposed technique. The proposed system can effectively classify entire image set from test data. The SMO-GBM classifier can further sub-segregate into sub classes with an average accuracy of 97.5%. Conclusion: The proposed approach provides detection and grading of diabetic retinopathy. The abnormality is further categories as soft, moderate and severe. The hybrid SMO-GBM classifier yields a better statistical metrics than the existing exudates classification approaches.     

Results of Automated Retinal Image Analysis for Detection of Diabetic Retinopathy from the Nakuru Study,Kenya

Objective

Digital retinal imaging is an established method of screening for diabetic retinopathy (DR). It has been established that currently about 1% of the world’s blind or visually impaired is due to DR. However, the increasing prevalence of diabetes mellitus and DR is creating an increased workload on those with expertise in grading retinal images. Safe and reliable automated analysis of retinal images may support screening services worldwide. This study aimed to compare the Iowa Detection Program (IDP) ability to detect diabetic eye diseases (DED) to human grading carried out at Moorfields Reading Centre on the population of Nakuru Study from Kenya.

Participants

Retinal images were taken from participants of the Nakuru Eye Disease Study in Kenya in 2007/08 (n = 4,381 participants [NW6 Topcon Digital Retinal Camera]).

Methods

First, human grading was performed for the presence or absence of DR, and for those with DR this was sub-divided in to referable or non-referable DR. The automated IDP software was deployed to identify those with DR and also to categorize the severity of DR.

Main Outcome Measures

The primary outcomes were sensitivity, specificity, and positive and negative predictive value of IDP versus the human grader as reference standard.

Results

Altogether 3,460 participants were included. 113 had DED, giving a prevalence of 3.3% (95% CI, 2.7–3.9%). Sensitivity of the IDP to detect DED as by the human grading was 91.0% (95% CI, 88.0–93.4%). The IDP ability to detect DED gave an AUC of 0.878 (95% CI 0.850–0.905). It showed a negative predictive value of 98%. The IDP missed no vision threatening retinopathy in any patients and none of the false negative cases met criteria for treatment.

Conclusions

In this epidemiological sample, the IDP’s grading was comparable to that of human graders’. It therefore might be feasible to consider inclusion into usual epidemiological grading.     

A Comprehensive Texture Segmentation Framework for Segmentation of Capillary Non-Perfusion Regions in Fundus Fluorescein Angiograms

Capillary non-perfusion (CNP) in the retina is a characteristic feature used in the management of a wide range of retinal diseases. There is no well-established computation tool for assessing the extent of CNP. We propose a novel texture segmentation framework to address this problem. This framework comprises three major steps: pre-processing, unsupervised total variation texture segmentation, and supervised segmentation. It employs a state-of-the-art multiphase total variation texture segmentation model which is enhanced by new kernel based region terms. The model can be applied to texture and intensity-based multiphase problems. A supervised segmentation step allows the framework to take expert knowledge into account, an AdaBoost classifier with weighted cost coefficient is chosen to tackle imbalanced data classification problems. To demonstrate its effectiveness, we applied this framework to 48 images from malarial retinopathy and 10 images from ischemic diabetic maculopathy. The performance of segmentation is satisfactory when compared to a reference standard of manual delineations: accuracy, sensitivity and specificity are 89.0%, 73.0%, and 90.8% respectively for the malarial retinopathy dataset and 80.8%, 70.6%, and 82.1% respectively for the diabetic maculopathy dataset. In terms of region-wise analysis, this method achieved an accuracy of 76.3% (45 out of 59 regions) for the malarial retinopathy dataset and 73.9% (17 out of 26 regions) for the diabetic maculopathy dataset. This comprehensive segmentation framework can quantify capillary non-perfusion in retinopathy from two distinct etiologies, and has the potential to be adopted for wider applications.     

A Multi-Branch Convolutional Neural Network for Screening and Staging of Diabetic Retinopathy Based on Wide-Field Optical Coherence Tomography Angiography

BackgroundDiabetic retinopathy (DR) is one of the major causes of blindness in adults suffering from diabetes. With the development of wide-field optical coherence tomography angiography (WF-OCTA), it is to become a gold standard for diagnosing DR. The demand for automated DR diagnosis system based on OCTA images have been fostered due to large diabetic population and pervasiveness of retinopathy cases.Materials and methodsIn this study, 288 diabetic patients and 97 healthy people were imaged by the swept-source optical coherence tomography (SS-OCT) with 12 mm × 12 mm single scan centered on the fovea. A multi-branch convolutional neural network (CNN) was proposed to classify WF-OCTA images into four grades: no DR, mild non-proliferative diabetic retinopathy (NPDR), moderate to severe NPDR, and proliferative diabetic retinopathy (PDR).ResultsThe proposed model achieved a classification accuracy of 96.11%, sensitivity of 98.08% and specificity of 89.43% in detecting DR. The accuracy of the model for DR staging is 90.56%, which is higher than that of other mainstream convolution neural network models.ConclusionThis technology enables early diagnosis and objective tracking of disease progression, which may be useful for optimal treatment to reduce vision loss.     

Prenatal influenza vaccination and allergic and autoimmune diseases in childhood: A longitudinal,population-based linked cohort study

BackgroundFew studies have evaluated the effect of maternal influenza vaccination on the development of allergic and autoimmune diseases in children beyond 6 months of age. We aimed to investigate the association between in utero exposure to seasonal inactivated influenza vaccine (IIV) and subsequent diagnosis of allergic and autoimmune diseases.Methods and findingsThis longitudinal, population-based linked cohort study included 124,760 singleton, live-born children from 106,206 mothers in Western Australia (WA) born between April 2012 and July 2016, with up to 5 years of follow-up from birth. In our study cohort, 64,169 (51.4%) were male, 6,566 (5.3%) were Aboriginal and/or Torres Strait Islander children, and the mean age at the end of follow-up was 3.0 (standard deviation, 1.3) years. The exposure was receipt of seasonal IIV during pregnancy. The outcomes were diagnosis of an allergic or autoimmune disease, including asthma and anaphylaxis, identified from hospital and/or emergency department (ED) records. Inverse probability of treatment weights (IPTWs) accounted for baseline probability of vaccination by maternal age, Aboriginal and/or Torres Strait Islander status, socioeconomic status, body mass index, parity, medical conditions, pregnancy complications, prenatal smoking, and prenatal care. The models additionally adjusted for the Aboriginal and/or Torres Strait Islander status of the child. There were 14,396 (11.5%) maternally vaccinated children; 913 (6.3%) maternally vaccinated and 7,655 (6.9%) maternally unvaccinated children had a diagnosis of allergic or autoimmune disease, respectively. Overall, maternal influenza vaccination was not associated with diagnosis of an allergic or autoimmune disease (adjusted hazard ratio [aHR], 1.02; 95% confidence interval [CI], 0.95 to 1.09). In trimester-specific analyses, we identified a negative association between third trimester influenza vaccination and the diagnosis of asthma (n = 40; aHR, 0.70; 95% CI, 0.50 to 0.97) and anaphylaxis (n = 36; aHR, 0.67; 95% CI, 0.47 to 0.95).We did not capture outcomes diagnosed in a primary care setting; therefore, our findings are only generalizable to more severe events requiring hospitalization or presentation to the ED. Due to small cell sizes (i.e., <5), estimates could not be determined for all outcomes after stratification.ConclusionsIn this study, we observed no association between in utero exposure to influenza vaccine and diagnosis of allergic or autoimmune diseases. Although we identified a negative association of asthma and anaphylaxis diagnosis when seasonal IIV was administered later in pregnancy, additional studies are needed to confirm this. Overall, our findings support the safety of seasonal inactivated influenza vaccine during pregnancy in relation to allergic and autoimmune diseases in early childhood and support the continuation of current global maternal vaccine programs and policies.

Damien Foo and colleagues evaluate the association between prenatal influenza vaccination and diagnosis of allergic and autoimmune diseases in childhood.     

Assessment of non-mydriatic fundus photography in detection of diabetic retinopathy.

Non-mydriatic retinal photography with later interpretation of the photographs was assessed as a screening method for the detection of diabetic retinopathy; when compared with an ophthalmologist''s clinical assessment in a random group of 62 diabetic patients it was accurate (false negative 6.8%, false positive 2%) and sensitive (sensitivity 96%, specificity 98%). The assessment of further management required based on analysis of the photographs was 96.5% in agreement with the further management suggested by the ophthalmologist after direct clinical assessment of the patient. If this technique were used to screen patients in a typical diabetic clinic the predicted positive accuracy rate would be 84% and the predicted negative accuracy rate 99.5%.     

Assessment of automated disease detection in diabetic retinopathy screening using two-field photography

Aim

To assess the performance of automated disease detection in diabetic retinopathy screening using two field mydriatic photography.

Methods

Images from 8,271 sequential patient screening episodes from a South London diabetic retinopathy screening service were processed by the Medalytix iGrading™ automated grading system. For each screening episode macular-centred and disc-centred images of both eyes were acquired and independently graded according to the English national grading scheme. Where discrepancies were found between the automated result and original manual grade, internal and external arbitration was used to determine the final study grades. Two versions of the software were used: one that detected microaneurysms alone, and one that detected blot haemorrhages and exudates in addition to microaneurysms. Results for each version were calculated once using both fields and once using the macula-centred field alone.

Results

Of the 8,271 episodes, 346 (4.2%) were considered unassessable. Referable disease was detected in 587 episodes (7.1%). The sensitivity of the automated system for detecting unassessable images ranged from 97.4% to 99.1% depending on configuration. The sensitivity of the automated system for referable episodes ranged from 98.3% to 99.3%. All the episodes that included proliferative or pre-proliferative retinopathy were detected by the automated system regardless of configuration (192/192, 95% confidence interval 98.0% to 100%). If implemented as the first step in grading, the automated system would have reduced the manual grading effort by between 2,183 and 3,147 patient episodes (26.4% to 38.1%).

Conclusion

Automated grading can safely reduce the workload of manual grading using two field, mydriatic photography in a routine screening service.     

SDOCT imaging to identify macular pathology in patients diagnosed with diabetic maculopathy by a digital photographic retinal screening programme

Introduction

Diabetic macular edema (DME) is an important cause of vision loss. England has a national systematic photographic retinal screening programme to identify patients with diabetic eye disease. Grading retinal photographs according to this national protocol identifies surrogate markers for DME. We audited a care pathway using a spectral-domain optical coherence tomography (SDOCT) clinic to identify macular pathology in this subset of patients.

Methods

A prospective audit was performed of patients referred from screening with mild to moderate non-proliferative diabetic retinopathy (R1) and surrogate markers for diabetic macular edema (M1) attending an SDOCT clinic. The SDOCT images were graded by an ophthalmologist as SDOCT positive, borderline or negative. SDOCT positive patients were referred to the medical retina clinic. SDOCT negative and borderline patients were further reviewed in the SDOCT clinic in 6 months.

Results

From a registered screening population of 17 551 patients with diabetes mellitus, 311 patients met the inclusion criteria between (March 2008 and September 2009). We analyzed images from 311 patients’ SDOCT clinic episodes. There were 131 SDOCT negative and 12 borderline patients booked for revisit in the OCT clinic. Twenty-four were referred back to photographic screening for a variety of reasons. A total of 144 were referred to ophthalmology with OCT evidence of definite macular pathology requiring review by an ophthalmologist.

Discussion

This analysis shows that patients with diabetes, mild to moderate non-proliferative diabetic retinopathy (R1) and evidence of diabetic maculopathy on non-stereoscopic retinal photographs (M1) have a 42.1% chance of having no macular edema on SDOCT imaging as defined by standard OCT definitions of DME when graded by a retinal specialist. SDOCT imaging is a useful adjunct to colour fundus photography in screening for referable diabetic maculopathy in our screening population.     

Adding Value: Rethinking Late 19th-Century Torres Strait Islander Drawings in Anthropological Inquiry

This article focuses on the cultural and artistic value of a collection of Torres Strait Islander drawings that were commissioned and collected in the late 19th century. I argue that these drawings, made during Alfred C. Haddon's “salvage anthropology” expeditions, can provide insight into the nature of Islander graphic systems and the production of contemporary Islander art. By focusing on stylistic links between the drawings and other forms of decorative art, and their role as resources and inspiration for contemporary Islander artists, I explore the role these collections play in investigating regional artistic traditions, and how they act as agents in reaffirming Islander identity.     

The intergenerational transmission of Australian Indigenous languages: why language maintenance programmes should be family-focused

By 2050, the majority of Australia’s surviving Indigenous languages are likely to become extinct. The intergenerational transmission of languages in which children acquire languages from their parents and grandparents is a key mechanism for reversing language shift, but many Australian children whose parents speak an Indigenous language do not speak that language. Using a unique, national survey of Australian Indigenous children, I identify factors associated with the successful intergenerational transmission of Indigenous languages within Aboriginal and Torres Strait Islander families. Results highlight the importance of parents’ language use. Although community-level characteristics account for some of the variance in successful language transmission, parents who use Indigenous languages at home, speak them as well as they speak English, and do not also speak a creole language are more likely to pass those languages onto their children.     

Scabies in remote Aboriginal and Torres Strait Islander populations in Australia: A narrative review

Scabies has recently gained international attention, with the World Health Organization (WHO) recognizing it as a neglected tropical disease. The International Alliance for the Control of Scabies recently formed as a partnership of more than 15 different countries, with an aim to lead a consistent and collaborative approach to preventing and controlling scabies globally. Scabies is most prevalent in low-resource and low socioeconomic areas that experience overcrowding and has a particularly high prevalence in children, with an estimated 5% to 10% in endemic countries. Scabies is widespread in remote Aboriginal and Torres Strait Islander communities in Australia with the prevalence of scabies in Aboriginal and Torres Strait Islander children in remote communities estimated to be as high as 33%, making it the region with the third highest prevalence in the world. This population group also have very high rates of secondary complications of scabies such as impetigo, poststreptococcal glomerulonephritis (PSGN), and rheumatic heart disease (RHD). This article is a narrative review of scabies in remote Aboriginal and Torres Strait Islander populations in Australia, including clinical manifestations of disease and current treatment options and guidelines. We discuss traditional approaches to prevention and control as well as suggestions for future interventions including revising Australian treatment guidelines to widen the use of oral ivermectin in high-risk groups or as a first-line treatment.

Scabies has recently gained international attention, with the World Health Organization (WHO) recognizing it as a neglected tropical disease [1]. The International Alliance for the Control of Scabies recently formed as a partnership of more than 15 different countries, with an aim to lead a consistent and collaborative approach to preventing and controlling scabies globally [2]. In Australia, 10 million dollars was awarded to the Murdoch Children’s Research Institute to implement the World Scabies Elimination Program—an initiative aimed at collecting data from many affected countries and scaling up mass drug administration (MDA) [3].Scabies is most prevalent in low-resource and low socioeconomic areas that experience overcrowding and has a particularly high prevalence in children, with an estimated 5% to 10% in endemic countries [4,5]. The 2015 Global Burden of Disease Study ranked scabies with the 101st highest disability-adjusted life years (DALYs) estimate out of 246 conditions [6]. This is, however, likely underestimated as secondary complications, such as impetigo and kidney damage, were not included in this study [6,7]. A study from Fiji showed that 94% of impetigo was attributable to scabies [8], and it is estimated that approximately half of the instances of acute poststreptococcal glomerulonephritis (PSGN) in tropical regions can be attributed to skin infections [9].     

The English national risk-reduction programme for preservation of sight in diabetes

This paper discusses the new national guidelines for a systematic screening programme to detect sight-threatening diabetic retinopathy in the population of people with diabetes in England. A review of the literature examines the evidence base to support screening interventions and effective management and treatments in diabetic retinopathy. The current evidence supports the establishment of a digital retinal photography system using pupil dilation. A Policy Advisory Group has been formulated by the National Screening Committee to guide the meeting of this target in England. A conclusion is made that with increased effort and organisation, health care professionals can ensure that the screening programme is successfully implemented and rates of visual impairment and blindness caused by diabetic retinopathy can be reduced significantly. (Mol Cell Biochem 261: 183–185, 2004)     

The English national risk-reduction programme for preservation of sight in diabetes

This paper discusses the new national guidelines for a systematic screening programme to detect sight-threatening diabetic retinopathy in the population of people with diabetes in England. A review of the literature examines the evidence base to support screening interventions and effective management and treatments in diabetic retinopathy. The current evidence supports the establishment of a digital retinal photography system using pupil dilation. A Policy Advisory Group has been formulated by the National Screening Committee to guide the meeting of this target in England. A conclusion is made that with increased effort and organisation, health care professionals can ensure that the screening programme is successfully implemented and rates of visual impairment and blindness caused by diabetic retinopathy can be reduced significantly.     

Ethnopharmacology,Biological Activity and Phytochemistry of Scaevola spinescens

Scaevola spinescens is endemic to Australia and has traditionally been used by Aboriginal and Torres Strait Islander communities to treat a variety of conditions including colds, flu, fever, stomach pain, urinary disorders, sores, tinea, leprosy, and cancer. Extracts prepared from S. spinescens are non-toxic and have been linked with various medicinal properties including antiviral, antibacterial, anti-inflammatory, and anticancer activities. These studies support the ethnopharmacological use of S. spinescens by Indigenous peoples of Australia and highlight the need for further investigations on the plant for potential use in pharmaceutical and food applications. This review provides a comprehensive, up-to-date review of the literature on S. spinescens focusing on the traditional use, medicinal properties, phytochemicals, and factors that affect their composition during pre-treatment and extraction, as well as providing a framework for future studies of the plant.     

Automatic non-proliferative diabetic retinopathy screening system based on color fundus image

Background

Non-proliferative diabetic retinopathy is the early stage of diabetic retinopathy. Automatic detection of non-proliferative diabetic retinopathy is significant for clinical diagnosis, early screening and course progression of patients.

Methods

This paper introduces the design and implementation of an automatic system for screening non-proliferative diabetic retinopathy based on color fundus images. Firstly, the fundus structures, including blood vessels, optic disc and macula, are extracted and located, respectively. In particular, a new optic disc localization method using parabolic fitting is proposed based on the physiological structure characteristics of optic disc and blood vessels. Then, early lesions, such as microaneurysms, hemorrhages and hard exudates, are detected based on their respective characteristics. An equivalent optical model simulating human eyes is designed based on the anatomical structure of retina. Main structures and early lesions are reconstructed in the 3D space for better visualization. Finally, the severity of each image is evaluated based on the international criteria of diabetic retinopathy.

Results

The system has been tested on public databases and images from hospitals. Experimental results demonstrate that the proposed system achieves high accuracy for main structures and early lesions detection. The results of severity classification for non-proliferative diabetic retinopathy are also accurate and suitable.

Conclusions

Our system can assist ophthalmologists for clinical diagnosis, automatic screening and course progression of patients.