Automated detection of diabetic retinopathy in retinal images

The use of artificial intelligence to assess diabetic eye disease among the Greenlandic population

Background: Retina fundus images conducted in Greenland are telemedically assessed for diabetic retinopathy by ophthalmological nurses in Denmark. Applying an AI grading solution, in a Greenlandic setting, could potentially improve the efficiency and cost-effectiveness of DR screening.Method: We developed an AI model using retina fundus photos, performed on persons registered with diabetes in Greenland and Denmark, using Optos® ultra wide-field scanning laser ophthalmoscope, graded according to ICDR.Using the ResNet50 network we compared the model's ability to distinguish between different images of ICDR severity levels in a confusion matrix.Results: Comparing images with ICDR level 0 to images of ICDR level 4 resulted in an accuracy of 0.9655, AUC of 0.9905, sensitivity and specificity of 96.6%.Comparing ICDR levels 0,1,2 with ICDR levels 3,4, we achieved a performance with an accuracy of 0.8077, an AUC of 0.8728, a sensitivity of 84.6% and a specificity of 78.8%. For the other comparisons, we achieved a modest performance.Conclusion: We developed an AI model using Greenlandic data, to automatically detect DR on Optos retina fundus images. The sensitivity and specificity were too low for our model to be applied directly in a clinical setting, thus optimising the model should be prioritised.

Intra- and Inter-expert Validation of an Automatic Segmentation Method for Fluid Regions Associated with Central Serous Chorioretinopathy in OCT Images

Central Serous Chorioretinopathy (CSC) is a retinal disorder caused by the accumulation of fluid, resulting in vision distortion. The diagnosis of this disease is typically performed through Optical Coherence Tomography (OCT) imaging, which displays any fluid buildup between the retinal layers. Currently, these fluid regions are manually detected by visual inspection a time-consuming and subjective process that can be prone to errors. A series of six deep learning-based automatic segmentation architectural configurations of different levels of complexity were trained and compared in order to determine the best model intended for the automatic segmentation of CSC-related lesions in OCT images. The best performing models were then evaluated in an external validation study. Furthermore, an intra- and inter-expert analysis was conducted in order to compare the manual segmentation performed by expert ophthalmologists with the automatic segmentation provided by the models. Test results of the best performing configuration achieved a mean Dice of 0.868 ± 0.056 in the internal dataset. In the external validation set, these models achieved a level of agreement with human experts of up to 0.960 in terms of Kappa coefficient, contrasting with a value of 0.951 for agreement between human experts. Overall, the models reached a better agreement with either of the human experts than these experts with each other, suggesting that automatic segmentation models for the detection of CSC-related lesions in OCT imaging can be useful tools for assessing this disease, reducing the workload of manual inspection and leading to a more robust and objective diagnosis method.

Variability in Grading Diabetic Retinopathy Using Retinal Photography and Its Comparison with an Automated Deep Learning Diabetic Retinopathy Screening Software

BACKGROUND

Diabetic retinopathy (DR) screening using colour retinal photographs is cost-effective and time-efficient. In real-world clinical settings, DR severity is frequently graded by individuals of different expertise levels. We aim to determine the agreement in DR severity grading between human graders of varying expertise and an automated deep learning DR screening software (ADLS).

METHODS

Using the International Clinical DR Disease Severity Scale, two hundred macula-centred fundus photographs were graded by retinal specialists, ophthalmology residents, family medicine physicians, medical students, and the ADLS. Based on referral urgency, referral grading was divided into no referral, non-urgent referral, and urgent referral to an ophthalmologist. Inter-observer and intra-group variations were analysed using Gwet's agreement coefficient, and the performance of ADLS was evaluated using sensitivity and specificity.

RESULTS

The agreement coefficient for inter-observer and intra-group variability ranged from fair to very good, and moderate to good, respectively. The ADLS showed a high area under curve of 0.879, 0.714, and 0.836 for non-referable DR, non-urgent referable DR, and urgent referable DR, respectively, with varying sensitivity and specificity values.

CONCLUSION

Inter-observer and intra-group agreements among human graders vary widely, but ADLS is a reliable and reasonably sensitive tool for mass screening to detect referable DR and urgent referable DR.

Deep Learning and Medical Image Processing Techniques for Diabetic Retinopathy: A Survey of Applications, Challenges, and Future Trends

Diabetic retinopathy (DR) is a common eye retinal disease that is widely spread all over the world. It leads to the complete loss of vision based on the level of severity. It damages both retinal blood vessels and the eye's microscopic interior layers. To avoid such issues, early detection of DR is essential in association with routine screening methods to discover mild causes in manual initiation. But these diagnostic procedures are extremely difficult and expensive. The unique contributions of the study include the following: first, providing detailed background of the DR disease and the traditional detection techniques. Second, the various imaging techniques and deep learning applications in DR are presented. Third, the different use cases and real-life scenarios are explored relevant to DR detection wherein deep learning techniques have been implemented. The study finally highlights the potential research opportunities for researchers to explore and deliver effective performance results in diabetic retinopathy detection.

Characterization of technologies in digital health applied in vision care

Digital health technology is increasingly becoming part of the evolution of health services, not only for the innovation of equipment but also in support of health processes. Eye health is one of the areas that most explores this field, being a reference in different segments of digital health and the use of applied technological resources. Thus, the purpose of this review was to analyse and characterize the development of research in digital health applied to vision sciences in the last decade. An exploratory-quantitative review of the research based on studies indexed in the SCOPUS database in the last 10 years, which related aspects of digital health technologies with their use within the vision sciences, was conducted. The research results were filtered, including journal articles and excluding those not directly related to vision. The final sample was categorized and classified according to the technology used, the relationship with eye/visual health and its practical applications. A total of 1069 reports were identified (32.09% published since 2021). "Artificial Intelligence" (77.74%) was the most frequent technological tool cited, and posterior segment (68.10%) most eye structure studied, being diabetic retinopathy (27.88%) the main studied disease. The vast majority have potential for clinical use (93.73%), especially those aimed at supporting decision-making. Technologies in digital health in the vision sciences have had a huge growth in recent years, with emphasis on artificial intelligence applied to the posterior segment, but with a low development of studies aimed at using this technology in primary visual care.

Everything real about unreal artificial intelligence in diabetic retinopathy and in ocular pathologies

Artificial Intelligence is a multidisciplinary field with the aim of building platforms that can make machines act, perceive, reason intelligently and whose goal is to automate activities that presently require human intelligence. From the cornea to the retina, artificial intelligence (AI) is expected to help ophthalmologists diagnose and treat ocular diseases. In ophthalmology, computerized analytics are being viewed as efficient and more objective ways to interpret the series of images and come to a conclusion. AI can be used to diagnose and grade diabetic retinopathy, glaucoma, age-related macular degeneration, cataracts, IOL power calculation, retinopathy of prematurity and keratoconus. This review article intends to discuss various aspects of artificial intelligence in ophthalmology.

Automatic detection of microaneurysms in optical coherence tomography images of retina using convolutional neural networks and transfer learning

Microaneurysms (MAs) are pathognomonic signs that help clinicians to detect diabetic retinopathy (DR) in the early stages. Automatic detection of MA in retinal images is an active area of research due to its application in screening processes for DR which is one of the main reasons of blindness amongst the working-age population. The focus of these works is on the automatic detection of MAs in en face retinal images like fundus color and Fluorescein Angiography (FA). On the other hand, detection of MAs from Optical Coherence Tomography (OCT) images has 2 main advantages: first, OCT is a non-invasive imaging technique that does not require injection, therefore is safer. Secondly, because of the proven application of OCT in detection of Age-Related Macular Degeneration, Diabetic Macular Edema, and normal cases, thanks to detecting MAs in OCT, extensive information is obtained by using this imaging technique. In this research, the concentration is on the diagnosis of MAs using deep learning in the OCT images which represent in-depth structure of retinal layers. To this end, OCT B-scans should be divided into strips and MA patterns should be searched in the resulted strips. Since we need a dataset comprising OCT image strips with suitable labels and such large labelled datasets are not yet available, we have created it. For this purpose, an exact registration method is utilized to align OCT images with FA photographs. Then, with the help of corresponding FA images, OCT image strips are created from OCT B-scans in four labels, namely MA, normal, abnormal, and vessel. Once the dataset of image strips is prepared, a stacked generalization (stacking) ensemble of four fine-tuned, pre-trained convolutional neural networks is trained to classify the strips of OCT images into the mentioned classes. FA images are used once to create OCT strips for training process and they are no longer needed for subsequent steps. Once the stacking ensemble model is obtained, it will be used to classify the OCT strips in the test process. The results demonstrate that the proposed framework classifies overall OCT image strips and OCT strips containing MAs with accuracy scores of 0.982 and 0.987, respectively.

Reduced serum calcium is associated with a higher risk of retinopathy in non-diabetic individuals: The Chinese Multi-provincial Cohort Study

AIMS

As a common micro-vascular disease, retinopathy can also present in non-diabetic individuals and increase the risk of clinical cardiovascular disease. Understanding the relationship between serum calcium and retinopathy would contribute to etiological study and disease prevention.

METHODS

A total of 1836 participants (aged 55-84 years and diabetes-free) from the Chinese Multi-Provincial Cohort Study-Beijing Project in 2012 were included for analyzing the relation between serum calcium level and retinopathy prevalence. Of these, 1407 non-diabetic participants with data on serum calcium in both the 2007 and 2012 surveys were included for analyzing the association of five-year changes in serum calcium with retinopathy risk. The retinopathy was determined from retinal images by ophthalmologists and a computer-aided system using convolutional neural network (CNN). The association between serum calcium and retinopathy risk was assessed by multivariate logistic regression.

RESULTS

Among the 1836 participants (male, 42.5%), 330 (18.0%) had retinopathy determined by CNN. After multivariate adjustment, the odds ratio (OR) comparing the lowest quartiles (serum calcium < 2.38 mmol/L) to the highest quartiles (serum calcium ≥ 2.50 mmol/L) for the prevalence of retinopathy determined by CNN was 1.58 (95% confidence interval [CI]: 1.10 - 2.27). The findings were consistent with the result discerned by ophthalmologists, and either by CNN or ophthalmologists. These relationships are preserved even in those without metabolic risk factors, including hypertension, high hemoglobin A1c, high fasting blood glucose, or high low-density lipoprotein cholesterol. Over 5 years, participants with the sustainably low levels of serum calcium (OR: 1.58; 95%CI: 1.05 - 2.39) and those who experienced a decrease in serum calcium (OR: 1.56; 95%CI: 1.04 - 2.35) had an increased risk of retinopathy than those with the sustainably high level of serum calcium.

CONCLUSIONS

Reduced serum calcium was independently associated with an increased risk of retinopathy in non-diabetic individuals. Moreover, reduction of serum calcium could further increase the risk of retinopathy even in the absence of hypertension, high glucose, or high cholesterol. This study suggested that maintaining a high level of serum calcium may be recommended for reducing the growing burden of retinopathy. Further large prospective studies will allow more detailed information.

Five regions, five retinopathy screening programmes: a systematic review of how Portugal addresses the challenge

BACKGROUND

The implementation of a population-based screening programme for diabetic retinopathy involves several challenges, often leading to postponements and setbacks at high human and material costs. Thus, it is of the utmost importance to promote the sharing of experiences, successes, and difficulties. However, factors such as the existence of regional programmes, specificities of each country's health systems, organisational and even linguistic barriers, make it difficult to create a solid framework that can be used as a basis for future projects.

METHODS

Web of Science and PubMed platforms were searched using appropriate key words. The review process resulted in 423 articles adherent to the search criteria, 28 of which were accepted and analysed. Web sites of all Portuguese governmental and non-governmental organisations, with a relevant role on the research topic, were inspected and 75 official documents were retrieved and analysed.

RESULTS

Since 2001, five regional screening programmes were gradually implemented under the guidelines of Portuguese General Health Department. However, complete population coverage was still not achieved. Among the main difficulties reported are the complex articulation between different levels of care providers, the low number of orthoptic technician in the national health system, the high burden that images grading, and treatment of positive cases represents for hospitals ophthalmology services, and low adherence rates. Yet, the comparison between strategies adopted in the different regions allowed the identification of potential solutions: hire orthoptic technician for primary health care units, eliminating the dependence of hospital professionals; use artificial intelligence algorithms for automatic retinographies grading, avoiding ophthalmologists overload; adoption of proximity strategies, as the use of portable retinographers, to promote adherence to screening.

CONCLUSION

Access to diabetic retinopathy screening remains remarkably variable in Portugal and needs urgent attention. However, several characteristics of effective screening programmes were found in Portuguese screening programmes, what seems to point toward promising outcomes, especially if each other highlights are considered. The findings of this research could be very useful for the other countries with similar socio-political characteristics.

TRIAL REGISTRATION

PROSPERO registration ID CRD42020200115 .

Fundamental principles of an effective diabetic retinopathy screening program

BACKGROUND

Diabetic retinopathy (DR) is the leading cause of blindness among working-age adults worldwide. Early detection and treatment are necessary to forestall vision loss from DR.

METHODS

A working group of ophthalmic and diabetes experts was established to develop a consensus on the key principles of an effective DR screening program. Recommendations are based on analysis of a structured literature review.

RESULTS

The recommendations for implementing an effective DR screening program are: (1) Examination methods must be suitable for the screening region, and DR classification/grading systems must be systematic and uniformly applied. Two-field retinal imaging is sufficient for DR screening and is preferable to seven-field imaging, and referable DR should be well defined and reliably identifiable by qualified screening staff; (2) in many countries/regions, screening can and should take place outside the ophthalmology clinic; (3) screening staff should be accredited and show evidence of ongoing training; (4) screening programs should adhere to relevant national quality assurance standards; (5) studies that use uniform definitions of risk to determine optimum risk-based screening intervals are required; (6) technology infrastructure should be in place to ensure that high-quality images can be stored securely to protect patient information; (7) although screening for diabetic macular edema (DME) in conjunction with DR evaluations may have merit, there is currently insufficient evidence to support implementation of programs solely for DME screening.

CONCLUSION

Use of these recommendations may yield more effective DR screening programs that reduce the risk of vision loss worldwide.

Automatic Characterization of Retinal Blood Flow Using OCT Angiograms

Purpose

To quantitatively characterize the retinal vascular network in healthy and pathological cases using optical coherence tomography angiography (OCTA) images.

Methods

The study included 56 eyes of 28 patients as follows: 26 healthy, 20 with diabetic retinopathy (DR), 6 with age-related macular degeneration (AMD), and 4 with retinal vein occlusion (RVO). For 33 eyes (16 healthy and 17 with DR), vessel density maps were provided by the OCTA machine. An automatic algorithm classified the image (as healthy, DR, AMD, or RVO) and provided quantitative information obtained from the angiograms, including global vessel density, global fractal dimension, and fovea avascular zone (FAZ) area. Classification results were compared with the diagnosis made by a retina specialist. The quantitative values were compared with the literature and to values provided by the OCTA machine.

Results

The success rate of classification was 83.9%. Vessel densities obtained by our algorithm (in healthy and DR cases) were significantly lower than the values reported in previous studies using OCTA. Similarly, they were much lower than the values provided by the OCTA machine. However, vessel densities in the healthy cases were similar to or higher than (depending on the retinal layer) the recently published values that may be considered as gold standard. Our values of fractal dimension were similar to those previously reported.

Conclusions

Our algorithm provides significantly improved vessel density values compared with previous studies. We believe our algorithm successfully omits false vessels.

Translational Relevance

Accurately assessing retinal vessel density enables better evaluation of retinal disorders.

A Clinical Decision Support System for Diabetic Retinopathy Screening: Creating a Clinical Support Application

BACKGROUND

The aim of this study was to build a clinical decision support system (CDSS) in diabetic retinopathy (DR), based on type 2 diabetes mellitus (DM) patients.

METHOD

We built a CDSS from a sample of 2,323 patients, divided into a training set of 1,212 patients, and a testing set of 1,111 patients. The CDSS is based on a fuzzy random forest, which is a set of fuzzy decision trees. A fuzzy decision tree is a hierarchical data structure that classifies a patient into several classes to some level, depending on the values that the patient presents in the attributes related to the DR risk factors. Each node of the tree is an attribute, and each branch of the node is related to a possible value of the attribute. The leaves of the tree link the patient to a particular class (DR, no DR).

RESULTS

A CDSS was built with 200 trees in the forest and three variables at each node. Accuracy of the CDSS was 80.76%, sensitivity was 80.67%, and specificity was 85.96%. Applied variables were current age, gender, DM duration and treatment, arterial hypertension, body mass index, HbA1c, estimated glomerular filtration rate, and microalbuminuria.

DISCUSSION

Some studies concluded that screening every 3 years was cost effective, but did not personalize risk factors. In this study, the random forest test using fuzzy rules permit us to build a personalized CDSS.

CONCLUSIONS

We have developed a CDSS that can help in screening diabetic retinopathy programs, despite our results more testing is essential.

Validation of automated screening for referable diabetic retinopathy with the IDx-DR device in the Hoorn Diabetes Care System

Purpose

To increase the efficiency of retinal image grading, algorithms for automated grading have been developed, such as the IDx‐DR 2.0 device. We aimed to determine the ability of this device, incorporated in clinical work flow, to detect retinopathy in persons with type 2 diabetes.

Methods

Retinal images of persons treated by the Hoorn Diabetes Care System (DCS) were graded by the IDx‐DR device and independently by three retinal specialists using the International Clinical Diabetic Retinopathy severity scale (ICDR) and EURODIAB criteria. Agreement between specialists was calculated. Results of the IDx‐DR device and experts were compared using sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV), distinguishing between referable diabetic retinopathy (RDR) and vision‐threatening retinopathy (VTDR). Area under the receiver operating characteristic curve (AUC) was calculated.

Results

Of the included 1415 persons, 898 (63.5%) had images of sufficient quality according to the experts and the IDx‐DR device. Referable diabetic retinopathy (RDR) was diagnosed in 22 persons (2.4%) using EURODIAB and 73 persons (8.1%) using ICDR classification. Specific intergrader agreement ranged from 40% to 61%. Sensitivity, specificity, PPV and NPV of IDx‐DR to detect RDR were 91% (95% CI: 0.69–0.98), 84% (95% CI: 0.81–0.86), 12% (95% CI: 0.08–0.18) and 100% (95% CI: 0.99–1.00; EURODIAB) and 68% (95% CI: 0.56–0.79), 86% (95% CI: 0.84–0.88), 30% (95% CI: 0.24–0.38) and 97% (95% CI: 0.95–0.98; ICDR). The AUC was 0.94 (95% CI: 0.88–1.00; EURODIAB) and 0.87 (95% CI: 0.83–0.92; ICDR). For detection of VTDR, sensitivity was lower and specificity was higher compared to RDR. AUC's were comparable.

Conclusion

Automated grading using the IDx‐DR device for RDR detection is a valid method and can be used in primary care, decreasing the demand on ophthalmologists.

Automated Screening for Diabetic Retinopathy - A Systematic Review

PURPOSE

Worldwide ophthalmologists are challenged by the rapid rise in the prevalence of diabetes. Diabetic retinopathy (DR) is the most common complication in diabetes, and possible consequences range from mild visual impairment to blindness. Repetitive screening for DR is cost-effective, but it is also a costly and strenuous affair. Several studies have examined the application of automated image analysis to solve this problem. Large populations are needed to assess the efficacy of such programs, and a standardized and rigorous methodology is important to give an indication of system performance in actual clinical settings.

METHODS

In a systematic review, we aimed to identify studies with methodology and design that are similar or replicate actual screening scenarios. A total of 1,231 publications were identified through PubMed, Cochrane Library, and Embase searches. Three manual search strategies were carried out to identify publications missed in the primary search. Four levels of screening identified 7 studies applicable for inclusion.

RESULTS

Seven studies were included. The detection of DR had high sensitivities (87.0-95.2%) but lower specificities (49.6-68.8%). False-negative results were related to mild DR with a low risk of progression within 1 year. Several studies reported missed cases of diabetic macular edema. A meta-analysis was not conducted as studies were not suitable for direct comparison or statistical analysis.

CONCLUSION

The study demonstrates that despite limited specificity, automated retinal image analysis may potentially be valuable in different DR screening scenarios with a relatively high sensitivity and a substantial workload reduction.

Deep Convolutional Neural Network-Based Early Automated Detection of Diabetic Retinopathy Using Fundus Image

The automatic detection of diabetic retinopathy is of vital importance, as it is the main cause of irreversible vision loss in the working-age population in the developed world. The early detection of diabetic retinopathy occurrence can be very helpful for clinical treatment; although several different feature extraction approaches have been proposed, the classification task for retinal images is still tedious even for those trained clinicians. Recently, deep convolutional neural networks have manifested superior performance in image classification compared to previous handcrafted feature-based image classification methods. Thus, in this paper, we explored the use of deep convolutional neural network methodology for the automatic classification of diabetic retinopathy using color fundus image, and obtained an accuracy of 94.5% on our dataset, outperforming the results obtained by using classical approaches.