The efficacy of automated "disease/no disease" grading for diabetic retinopathy in a systematic screening programme

Deep learning detection of diabetic retinopathy in Scotland's diabetic eye screening programme

BACKGROUND/AIMS

Support vector machine-based automated grading (known as iGradingM) has been shown to be safe, cost-effective and robust in the diabetic retinopathy (DR) screening (DES) programme in Scotland. It triages screening episodes as gradable with no DR versus manual grading required. The study aim was to develop a deep learning-based autograder using images and gradings from DES and to compare its performance with that of iGradingM.

METHODS

Retinal images, quality assurance (QA) data and routine DR grades were obtained from national datasets in 179 944 patients for years 2006-2016. QA grades were available for 744 images. We developed a deep learning-based algorithm to detect whether either eye contained ungradable images or any DR. The sensitivity and specificity were evaluated against consensus QA grades and routine grades.

RESULTS

Images used in QA which were ungradable or with DR were detected by deep learning with better specificity compared with manual graders (p<0.001) and with iGradingM (p<0.001) at the same sensitivities. Any DR according to the DES final grade was detected with 89.19% (270 392/303 154) sensitivity and 77.41% (500 945/647 158) specificity. Observable disease and referable disease were detected with sensitivities of 96.58% (16 613/17 201) and 98.48% (22 600/22 948), respectively. Overall, 43.84% of screening episodes would require manual grading.

CONCLUSION

A deep learning-based system for DR grading was evaluated in QA data and images from 11 years in 50% of people attending a national DR screening programme. The system could reduce the manual grading workload at the same sensitivity compared with the current automated grading system.

Target Product Profile for a Machine Learning-Automated Retinal Imaging Analysis Software for Use in English Diabetic Eye Screening: Protocol for a Mixed Methods Study

BACKGROUND

Diabetic eye screening (DES) represents a significant opportunity for the application of machine learning (ML) technologies, which may improve clinical and service outcomes. However, successful integration of ML into DES requires careful product development, evaluation, and implementation. Target product profiles (TPPs) summarize the requirements necessary for successful implementation so these can guide product development and evaluation.

OBJECTIVE

This study aims to produce a TPP for an ML-automated retinal imaging analysis software (ML-ARIAS) system for use in DES in England.

METHODS

This work will consist of 3 phases. Phase 1 will establish the characteristics to be addressed in the TPP. A list of candidate characteristics will be generated from the following sources: an overview of systematic reviews of diagnostic test TPPs; a systematic review of digital health TPPs; and the National Institute for Health and Care Excellence's Evidence Standards Framework for Digital Health Technologies. The list of characteristics will be refined and validated by a study advisory group (SAG) made up of representatives from key stakeholders in DES. This includes people with diabetes; health care professionals; health care managers and leaders; and regulators and policy makers. In phase 2, specifications for these characteristics will be drafted following a series of semistructured interviews with participants from these stakeholder groups. Data collected from these interviews will be analyzed using the shortlist of characteristics as a framework, after which specifications will be drafted to create a draft TPP. Following approval by the SAG, in phase 3, the draft will enter an internet-based Delphi consensus study with participants sought from the groups previously identified, as well as ML-ARIAS developers, to ensure feasibility. Participants will be invited to score characteristic and specification pairs on a scale from "definitely exclude" to "definitely include," and suggest edits. The document will be iterated between rounds based on participants' feedback. Feedback on the draft document will be sought from a group of ML-ARIAS developers before its final contents are agreed upon in an in-person consensus meeting. At this meeting, representatives from the stakeholder groups previously identified (minus ML-ARIAS developers, to avoid bias) will be presented with the Delphi results and feedback of the user group and asked to agree on the final contents by vote.

RESULTS

Phase 1 was completed in November 2023. Phase 2 is underway and expected to finish in March 2024. Phase 3 is expected to be complete in July 2024.

CONCLUSIONS

The multistakeholder development of a TPP for an ML-ARIAS for use in DES in England will help developers produce tools that serve the needs of patients, health care providers, and their staff. The TPP development process will also provide methods and a template to produce similar documents in other disease areas.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/50568.

Teleophthalmology and retina: a review of current tools, pathways and services

Telemedicine, the use of telecommunication and information technology to deliver healthcare remotely, has evolved beyond recognition since its inception in the 1970s. Advances in telecommunication infrastructure, the advent of the Internet, exponential growth in computing power and associated computer-aided diagnosis, and medical imaging developments have created an environment where telemedicine is more accessible and capable than ever before, particularly in the field of ophthalmology. Ever-increasing global demand for ophthalmic services due to population growth and ageing together with insufficient supply of ophthalmologists requires new models of healthcare provision integrating telemedicine to meet present day challenges, with the recent COVID-19 pandemic providing the catalyst for the widespread adoption and acceptance of teleophthalmology. In this review we discuss the history, present and future application of telemedicine within the field of ophthalmology, and specifically retinal disease. We consider the strengths and limitations of teleophthalmology, its role in screening, community and hospital management of retinal disease, patient and clinician attitudes, and barriers to its adoption.

CHILDSTAR: CHIldren Living With Diabetes See and Thrive with AI Review

Background

Artificial intelligence (AI) appears capable of detecting diabetic retinopathy (DR) with a high degree of accuracy in adults; however, there are few studies in children and young adults.

Methods

Children and young adults (3-26 years) with type 1 diabetes mellitus (T1DM) or type 2 diabetes mellitus (T2DM) were screened at the Dhaka BIRDEM-2 hospital, Bangladesh. All gradable fundus images were uploaded to Cybersight AI for interpretation. Two main outcomes were considered at a patient level: 1) Any DR, defined as mild non-proliferative diabetic retinopathy (NPDR or more severe; and 2) Referable DR, defined as moderate NPDR or more severe. Diagnostic test performance comparing Orbis International's Cybersight AI with the reference standard, a fully qualified optometrist certified in DR grading, was assessed using the Matthews correlation coefficient (MCC), area under the receiver operating characteristic curve (AUC-ROC), area under the precision-recall curve (AUC-PR), sensitivity, specificity, positive and negative predictive values.

Results

Among 1274 participants (53.1% female, mean age 16.7 years), 19.4% (n = 247) had any DR according to AI. For referable DR, 2.35% (n = 30) were detected by AI. The sensitivity and specificity of AI for any DR were 75.5% (CI 69.7-81.3%) and 91.8% (CI 90.2-93.5%) respectively, and for referable DR, these values were 84.2% (CI 67.8-100%) and 98.9% (CI 98.3%-99.5%). The MCC, AUC-ROC and the AUC-PR for referable DR were 63.4, 91.2 and 76.2% respectively. AI was most successful in accurately classifying younger children with shorter duration of diabetes.

Conclusions

Cybersight AI accurately detected any DR and referable DR among children and young adults, despite its algorithms having been trained on adults. The observed high specificity is particularly important to avoid over-referral in low-resource settings. AI may be an effective tool to reduce demands on scarce physician resources for the care of children with diabetes in low-resource settings.

Artificial Intelligence and Diabetic Retinopathy: AI Framework, Prospective Studies, Head-to-head Validation, and Cost-effectiveness

Current guidelines recommend that individuals with diabetes receive yearly eye exams for detection of referable diabetic retinopathy (DR), one of the leading causes of new-onset blindness. For addressing the immense screening burden, artificial intelligence (AI) algorithms have been developed to autonomously screen for DR from fundus photography without human input. Over the last 10 years, many AI algorithms have achieved good sensitivity and specificity (>85%) for detection of referable DR compared with human graders; however, many questions still remain. In this narrative review on AI in DR screening, we discuss key concepts in AI algorithm development as a background for understanding the algorithms. We present the AI algorithms that have been prospectively validated against human graders and demonstrate the variability of reference standards and cohort demographics. We review the limited head-to-head validation studies where investigators attempt to directly compare the available algorithms. Next, we discuss the literature regarding cost-effectiveness, equity and bias, and medicolegal considerations, all of which play a role in the implementation of these AI algorithms in clinical practice. Lastly, we highlight ongoing efforts to bridge gaps in AI model data sets to pursue equitable development and delivery.

An effective and comprehensible method to detect and evaluate retinal damage due to diabetes complications

The leading cause of vision loss globally is diabetic retinopathy. Researchers are making great efforts to automatically detect and diagnose correctly diabetic retinopathy. Diabetic retinopathy includes five stages: no diabetic retinopathy, mild diabetic retinopathy, moderate diabetic retinopathy, severe diabetic retinopathy and proliferative diabetic retinopathy. Recent studies have offered several multi-tasking deep learning models to detect and assess the level of diabetic retinopathy. However, the explanation for the assessment of disease severity of these models is limited, and only stops at showing lesions through images. These studies have not explained on what basis the appraisal of disease severity is based. In this article, we present a system for assessing and interpreting the five stages of diabetic retinopathy. The proposed system is built from internal models including a deep learning model that detects lesions and an explanatory model that assesses disease stage. The deep learning model that detects lesions uses the Mask R-CNN deep learning network to specify the location and shape of the lesion and classify the lesion types. This model is a combination of two networks: one used to detect hemorrhagic and exudative lesions, and one used to detect vascular lesions like aneurysm and proliferation. The explanatory model appraises disease severity based on the severity of each type of lesion and the association between types. The severity of the disease will be decided by the model based on the number of lesions, the density and the area of the lesions. The experimental results on real-world datasets show that our proposed method achieves high accuracy of assessing five stages of diabetic retinopathy comparable to existing state-of-the-art methods and is capable of explaining the causes of disease severity.

Test accuracy of artificial intelligence-based grading of fundus images in diabetic retinopathy screening: A systematic review

OBJECTIVES

To systematically review the accuracy of artificial intelligence (AI)-based systems for grading of fundus images in diabetic retinopathy (DR) screening.

METHODS

We searched MEDLINE, EMBASE, the Cochrane Library and the ClinicalTrials.gov from 1st January 2000 to 27th August 2021. Accuracy studies published in English were included if they met the pre-specified inclusion criteria. Selection of studies for inclusion, data extraction and quality assessment were conducted by one author with a second reviewer independently screening and checking 20% of titles. Results were analysed narratively.

RESULTS

Forty-three studies evaluating 15 deep learning (DL) and 4 machine learning (ML) systems were included. Nine systems were evaluated in a single study each. Most studies were judged to be at high or unclear risk of bias in at least one QUADAS-2 domain. Sensitivity for referable DR and higher grades was ≥85% while specificity varied and was <80% for all ML systems and in 6/31 studies evaluating DL systems. Studies reported high accuracy for detection of ungradable images, but the latter were analysed and reported inconsistently. Seven studies reported that AI was more sensitive but less specific than human graders.

CONCLUSIONS

AI-based systems are more sensitive than human graders and could be safe to use in clinical practice but have variable specificity. However, for many systems evidence is limited, at high risk of bias and may not generalise across settings. Therefore, pre-implementation assessment in the target clinical pathway is essential to obtain reliable and applicable accuracy estimates.

Artificial Intelligence for Diabetic Retinopathy Screening Using Color Retinal Photographs: From Development to Deployment

Diabetic retinopathy (DR), a leading cause of preventable blindness, is expected to remain a growing health burden worldwide. Screening to detect early sight-threatening lesions of DR can reduce the burden of vision loss; nevertheless, the process requires intensive manual labor and extensive resources to accommodate the increasing number of patients with diabetes. Artificial intelligence (AI) has been shown to be an effective tool which can potentially lower the burden of screening DR and vision loss. In this article, we review the use of AI for DR screening on color retinal photographs in different phases of application, ranging from development to deployment. Early studies of machine learning (ML)-based algorithms using feature extraction to detect DR achieved a high sensitivity but relatively lower specificity. Robust sensitivity and specificity were achieved with the application of deep learning (DL), although ML is still used in some tasks. Public datasets were utilized in retrospective validations of the developmental phases in most algorithms, which require a large number of photographs. Large prospective clinical validation studies led to the approval of DL for autonomous screening of DR although the semi-autonomous approach may be preferable in some real-world settings. There have been few reports on real-world implementations of DL for DR screening. It is possible that AI may improve some real-world indicators for eye care in DR, such as increased screening uptake and referral adherence, but this has not been proven. The challenges in deployment may include workflow issues, such as mydriasis to lower ungradable cases; technical issues, such as integration into electronic health record systems and integration into existing camera systems; ethical issues, such as data privacy and security; acceptance of personnel and patients; and health-economic issues, such as the need to conduct health economic evaluations of using AI in the context of the country. The deployment of AI for DR screening should follow the governance model for AI in healthcare which outlines four main components: fairness, transparency, trustworthiness, and accountability.

Prediction of postoperative infection in elderly using deep learning-based analysis: an observational cohort study

Elderly patients are susceptible to postoperative infections with increased mortality. Analyzing with a deep learning model, the perioperative factors that could predict and/or contribute to postoperative infections may improve the outcome in elderly. This was an observational cohort study with 2014 elderly patients who had elective surgery from 28 hospitals in China from April to June 2014. We aimed to develop and validate deep learning-based predictive models for postoperative infections in the elderly. 1510 patients were randomly assigned to be training dataset for establishing deep learning-based models, and 504 patients were used to validate the effectiveness of these models. The conventional model predicted postoperative infections was 0.728 (95% CI 0.688-0.768) with the sensitivity of 66.2% (95% CI 58.2-73.6) and specificity of 66.8% (95% CI 64.6-68.9). The deep learning model including risk factors relevant to baseline clinical characteristics predicted postoperative infections was 0.641 (95% CI 0.545-0.737), and sensitivity and specificity were 34.2% (95% CI 19.6-51.4) and 88.8% (95% CI 85.6-91.6), respectively. Including risk factors relevant to baseline variables and surgery, the deep learning model predicted postoperative infections was 0.763 (95% CI 0.681-0.844) with the sensitivity of 63.2% (95% CI 46-78.2) and specificity of 80.5% (95% CI 76.6-84). Our feasibility study indicated that a deep learning model including risk factors for the prediction of postoperative infections can be achieved in elderly. Further study is needed to assess whether this model can be used to guide clinical practice to improve surgical outcomes in elderly.

Pre-hospital prediction of adverse outcomes in patients with suspected COVID-19: Development, application and comparison of machine learning and deep learning methods

BACKGROUND

COVID-19 infected millions of people and increased mortality worldwide. Patients with suspected COVID-19 utilised emergency medical services (EMS) and attended emergency departments, resulting in increased pressures and waiting times. Rapid and accurate decision-making is required to identify patients at high-risk of clinical deterioration following COVID-19 infection, whilst also avoiding unnecessary hospital admissions. Our study aimed to develop artificial intelligence models to predict adverse outcomes in suspected COVID-19 patients attended by EMS clinicians.

METHOD

Linked ambulance service data were obtained for 7,549 adult patients with suspected COVID-19 infection attended by EMS clinicians in the Yorkshire and Humber region (England) from 18-03-2020 to 29-06-2020. We used support vector machines (SVM), extreme gradient boosting, artificial neural network (ANN) models, ensemble learning methods and logistic regression to predict the primary outcome (death or need for organ support within 30 days). Models were compared with two baselines: the decision made by EMS clinicians to convey patients to hospital, and the PRIEST clinical severity score.

RESULTS

Of the 7,549 patients attended by EMS clinicians, 1,330 (17.6%) experienced the primary outcome. Machine Learning methods showed slight improvements in sensitivity over baseline results. Further improvements were obtained using stacking ensemble methods, the best geometric mean (GM) results were obtained using SVM and ANN as base learners when maximising sensitivity and specificity.

CONCLUSIONS

These methods could potentially reduce the numbers of patients conveyed to hospital without a concomitant increase in adverse outcomes. Further work is required to test the models externally and develop an automated system for use in clinical settings.

Diabetic retinopathy screening in the emerging era of artificial intelligence

Diabetic retinopathy is a frequent complication in diabetes and a leading cause of visual impairment. Regular eye screening is imperative to detect sight-threatening stages of diabetic retinopathy such as proliferative diabetic retinopathy and diabetic macular oedema in order to treat these before irreversible visual loss occurs. Screening is cost-effective and has been implemented in various countries in Europe and elsewhere. Along with optimised diabetes care, this has substantially reduced the risk of visual loss. Nevertheless, the growing number of patients with diabetes poses an increasing burden on healthcare systems and automated solutions are needed to alleviate the task of screening and improve diagnostic accuracy. Deep learning by convolutional neural networks is an optimised branch of artificial intelligence that is particularly well suited to automated image analysis. Pivotal studies have demonstrated high sensitivity and specificity for classifying advanced stages of diabetic retinopathy and identifying diabetic macular oedema in optical coherence tomography scans. Based on this, different algorithms have obtained regulatory approval for clinical use and have recently been implemented to some extent in a few countries. Handheld mobile devices are another promising option for self-monitoring, but so far they have not demonstrated comparable image quality to that of fundus photography using non-portable retinal cameras, which is the gold standard for diabetic retinopathy screening. Such technology has the potential to be integrated in telemedicine-based screening programmes, enabling self-captured retinal images to be transferred virtually to reading centres for analysis and planning of further steps. While emerging technologies have shown a lot of promise, clinical implementation has been sparse. Legal obstacles and difficulties in software integration may partly explain this, but it may also indicate that existing algorithms may not necessarily integrate well with national screening initiatives, which often differ substantially between countries.

A New Approach for Detecting Fundus Lesions Using Image Processing and Deep Neural Network Architecture Based on YOLO Model

Diabetic Retinopathy is one of the main causes of vision loss, and in its initial stages, it presents with fundus lesions, such as microaneurysms, hard exudates, hemorrhages, and soft exudates. Computational models capable of detecting these lesions can help in the early diagnosis of the disease and prevent the manifestation of more severe forms of lesions, helping in screening and defining the best form of treatment. However, the detection of these lesions through computerized systems is a challenge due to numerous factors, such as the characteristics of size and shape of the lesions, noise and the contrast of images available in the public datasets of Diabetic Retinopathy, the number of labeled examples of these lesions available in the datasets and the difficulty of deep learning algorithms in detecting very small objects in digital images. Thus, to overcome these problems, this work proposes a new approach based on image processing techniques, data augmentation, transfer learning, and deep neural networks to assist in the medical diagnosis of fundus lesions. The proposed approach was trained, adjusted, and tested using the public DDR and IDRiD Diabetic Retinopathy datasets and implemented in the PyTorch framework based on the YOLOv5 model. The proposed approach reached in the DDR dataset an mAP of 0.2630 for the IoU limit of 0.5 and F1-score of 0.3485 in the validation stage, and an mAP of 0.1540 for the IoU limit of 0.5 and F1-score of 0.2521, in the test stage. The results obtained in the experiments demonstrate that the proposed approach presented superior results to works with the same purpose found in the literature.

Diabetic Retinopathy Screening Using Artificial Intelligence and Handheld Smartphone-Based Retinal Camera

BACKGROUND

Portable retinal cameras and deep learning (DL) algorithms are novel tools adopted by diabetic retinopathy (DR) screening programs. Our objective is to evaluate the diagnostic accuracy of a DL algorithm and the performance of portable handheld retinal cameras in the detection of DR in a large and heterogenous type 2 diabetes population in a real-world, high burden setting.

METHOD

Participants underwent fundus photographs of both eyes with a portable retinal camera (Phelcom Eyer). Classification of DR was performed by human reading and a DL algorithm (PhelcomNet), consisting of a convolutional neural network trained on a dataset of fundus images captured exclusively with the portable device; both methods were compared. We calculated the area under the curve (AUC), sensitivity, and specificity for more than mild DR.

RESULTS

A total of 824 individuals with type 2 diabetes were enrolled at Itabuna Diabetes Campaign, a subset of 679 (82.4%) of whom could be fully assessed. The algorithm sensitivity/specificity was 97.8 % (95% CI 96.7-98.9)/61.4 % (95% CI 57.7-65.1); AUC was 0·89. All false negative cases were classified as moderate non-proliferative diabetic retinopathy (NPDR) by human grading.

CONCLUSIONS

The DL algorithm reached a good diagnostic accuracy for more than mild DR in a real-world, high burden setting. The performance of the handheld portable retinal camera was adequate, with over 80% of individuals presenting with images of sufficient quality. Portable devices and artificial intelligence tools may increase coverage of DR screening programs.

Capturing the clinical decision-making processes of expert and novice diabetic retinal graders using a 'think-aloud' approach

BACKGROUND

Diabetic eye screening programmes have been developed worldwide based on evidence that early detection and treatment of diabetic retinopathy are crucial to preventing sight loss. However, little is known about the decision-making processes and training needs of diabetic retinal graders, particularly in low- and middle-income countries.

OBJECTIVES

To provide data for improving evidence-based diabetic retinopathy training to help novice graders process fundus images more like experts.

SUBJECTS/METHODS

This is a mixed-methods qualitative study conducted in southern Vietnam and Northern Ireland. Novice diabetic retinal graders in Vietnam (n = 18) and expert graders in Northern Ireland (n = 5) were selected through a purposive sampling technique. Data were collected from 21st February to 3rd September 2019. The interviewer used neutral prompts during think-aloud sessions to encourage participants to verbalise their thought processes while grading fundus images from anonymised patients, followed by semi-structured interviews. Thematic framework analysis was used to identify themes, supported by illustrative quotes from interviews. Mann-Whitney U tests were used to compare graders' performance.

RESULTS

Expert graders used a more systematic approach when grading images, considered all four images per patient and used available software tools such as red-free filters prior to making a decision on management. The most challenging features for novice graders were intra-retinal microvascular abnormalities and new vessels, which were more accurately identified by experts.

CONCLUSION

Taking more time to grade fundus images and adopting a protocol-driven "checklist" approach may help novice graders to function more like experts.

Artificial intelligence promotes the diagnosis and screening of diabetic retinopathy

Deep learning evolves into a new form of machine learning technology that is classified under artificial intelligence (AI), which has substantial potential for large-scale healthcare screening and may allow the determination of the most appropriate specific treatment for individual patients. Recent developments in diagnostic technologies facilitated studies on retinal conditions and ocular disease in metabolism and endocrinology. Globally, diabetic retinopathy (DR) is regarded as a major cause of vision loss. Deep learning systems are effective and accurate in the detection of DR from digital fundus photographs or optical coherence tomography. Thus, using AI techniques, systems with high accuracy and efficiency can be developed for diagnosing and screening DR at an early stage and without the resources that are only accessible in special clinics. Deep learning enables early diagnosis with high specificity and sensitivity, which makes decisions based on minimally handcrafted features paving the way for personalized DR progression real-time monitoring and in-time ophthalmic or endocrine therapies. This review will discuss cutting-edge AI algorithms, the automated detecting systems of DR stage grading and feature segmentation, the prediction of DR outcomes and therapeutics, and the ophthalmic indications of other systemic diseases revealed by AI.

Validation of an Automated Screening System for Diabetic Retinopathy Operating under Real Clinical Conditions

Background. Retinopathy is the most common microvascular complication of diabetes mellitus. It is the leading cause of blindness among working-aged people in developed countries. The use of telemedicine in the screening system has enabled the application of large-scale population-based programs for early retinopathy detection in diabetic patients. However, the need to support ophthalmologists with other trained personnel remains a barrier to broadening its implementation. Methods. Automatic diagnosis of diabetic retinopathy was carried out through the analysis of retinal photographs using the 2iRetinex software. We compared the categorical diagnoses of absence/presence of retinopathy issued by family physicians (PCP) with the same categories provided by the algorithm (ALG). The agreed diagnosis of three specialist ophthalmologists is used as the reference standard (OPH). Results. There were 653 of 3520 patients diagnosed with diabetic retinopathy (DR). Diabetic retinopathy threatening to vision (STDR) was found in 82 patients (2.3%). Diagnostic sensitivity for STDR was 94% (ALG) and 95% (PCP). No patient with proliferating or severe DR was misdiagnosed in both strategies. The k-value of the agreement between the ALG and OPH was 0.5462, while between PCP and OPH was 0.5251 (p = 0.4291). Conclusions. The diagnostic capacity of 2iRetinex operating under normal clinical conditions is comparable to screening physicians.

Updates in deep learning research in ophthalmology

Ophthalmology has been one of the early adopters of artificial intelligence (AI) within the medical field. Deep learning (DL), in particular, has garnered significant attention due to the availability of large amounts of data and digitized ocular images. Currently, AI in Ophthalmology is mainly focused on improving disease classification and supporting decision-making when treating ophthalmic diseases such as diabetic retinopathy, age-related macular degeneration (AMD), glaucoma and retinopathy of prematurity (ROP). However, most of the DL systems (DLSs) developed thus far remain in the research stage and only a handful are able to achieve clinical translation. This phenomenon is due to a combination of factors including concerns over security and privacy, poor generalizability, trust and explainability issues, unfavorable end-user perceptions and uncertain economic value. Overcoming this challenge would require a combination approach. Firstly, emerging techniques such as federated learning (FL), generative adversarial networks (GANs), autonomous AI and blockchain will be playing an increasingly critical role to enhance privacy, collaboration and DLS performance. Next, compliance to reporting and regulatory guidelines, such as CONSORT-AI and STARD-AI, will be required to in order to improve transparency, minimize abuse and ensure reproducibility. Thirdly, frameworks will be required to obtain patient consent, perform ethical assessment and evaluate end-user perception. Lastly, proper health economic assessment (HEA) must be performed to provide financial visibility during the early phases of DLS development. This is necessary to manage resources prudently and guide the development of DLS.

Intelligent Solutions in Chest Abnormality Detection Based on YOLOv5 and ResNet50

Computer-aided diagnosis (CAD) has nearly fifty years of history and has assisted many clinicians in the diagnosis. With the development of technology, recently, researches use the deep learning method to get high accuracy results in the CAD system. With CAD, the computer output can be used as a second choice for radiologists and contribute to doctors doing the final right decisions. Chest abnormality detection is a classic detection and classification problem; researchers need to classify common thoracic lung diseases and localize critical findings. For the detection problem, there are two deep learning methods: one-stage method and two-stage method. In our paper, we introduce and analyze some representative model, such as RCNN, SSD, and YOLO series. In order to better solve the problem of chest abnormality detection, we proposed a new model based on YOLOv5 and ResNet50. YOLOv5 is the latest YOLO series, which is more flexible than the one-stage detection algorithms before. The function of YOLOv5 in our paper is to localize the abnormality region. On the other hand, we use ResNet, avoiding gradient explosion problems in deep learning for classification. And we filter the result we got from YOLOv5 and ResNet. If ResNet recognizes that the image is not abnormal, the YOLOv5 detection result is discarded. The dataset is collected via VinBigData's web-based platform, VinLab. We train our model on the dataset using Pytorch frame and use the mAP, precision, and F1-score as the metrics to evaluate our model's performance. In the progress of experiments, our method achieves superior performance over the other classical approaches on the same dataset. The experiments show that YOLOv5's mAP is 0.010, 0.020, 0.023 higher than those of YOLOv5, Fast RCNN, and EfficientDet. In addition, in the dimension of precision, our model also performs better than other models. The precision of our model is 0.512, which is 0.018, 0.027, 0.033 higher than YOLOv5, Fast RCNN, and EfficientDet.

Using transfer learning for diabetic retinopathy stage classification

Purpose

Diabetic retinopathy (DR) is one of the dangerous complications of diabetes. Its grade level must be tracked to manage its progress and to start the appropriate decision for treatment in time. Effective automated methods for the detection of DR and the classification of its severity stage are necessary to reduce the burden on ophthalmologists and diagnostic contradictions among manual readers.

Design/methodology/approach

In this research, convolutional neural network (CNN) was used based on colored retinal fundus images for the detection of DR and classification of its stages. CNN can recognize sophisticated features on the retina and provides an automatic diagnosis. The pre-trained VGG-16 CNN model was applied using a transfer learning (TL) approach to utilize the already learned parameters in the detection.

Findings

By conducting different experiments set up with different severity groupings, the achieved results are promising. The best-achieved accuracies for 2-class, 3-class, 4-class and 5-class classifications are 86.5, 80.5, 63.5 and 73.7, respectively.

Originality/value

In this research, VGG-16 was used to detect and classify DR stages using the TL approach. Different combinations of classes were used in the classification of DR severity stages to illustrate the ability of the model to differentiate between the classes and verify the effect of these changes on the performance of the model.

Facilitating diabetic retinopathy screening using automated retinal image analysis in underresourced settings

AIM

To evaluate an automated retinal image analysis (ARIA) of indigenous retinal fundus images against a human grading comparator for the classification of diabetic retinopathy (DR) status.

METHODS

Indigenous Australian adults with type 2 diabetes (n = 410) from three remote and very remote primary-care services in the Northern Territory, Australia, underwent teleretinal DR screening. A single, central retinal fundus photograph (opportunistic mydriasis) for each eye was later regraded using a single ARIA and a UK human grader and national DR classification system. The sensitivity and specificity of ARIA were assessed relative to the comparator. Proportionate agreement and a Kappa statistic were also computed.

RESULTS

Retinal images from 391 and 393 participants were gradable for 'Any DR' by the human grader and ARIA grader, respectively. 'Any DR' was detected by the human grader in 185 (47.3%) participants and by ARIA in 202 (48.6%) participants (agreement =88.0%, Kappa = 0.76,), whereas proliferative DR was detected in 31 (7.9%) and 37 (9.4%) participants (agreement = 98.2%, Kappa = 0.89,), respectively. The ARIA software had 91.4 (95% CI, 86.3-95.0) sensitivity and 85.0 (95% CI, 79.3-89.5) specificity for detecting 'Any DR' and 96.8 (95% CI, 83.3-99.9) sensitivity and 98.3 (95% CI, 96.4-99.4) specificity for detecting proliferative DR.

CONCLUSIONS

This ARIA software has high sensitivity for detecting 'Any DR', hence could be used as a triage tool for human graders. High sensitivity was also found for detection of proliferative DR by ARIA. Future versions of this ARIA should include maculopathy and referable DR (CSME and/or PDR). Such ARIA software may benefit diabetes care in less-resourced regions.

Assessing the Clinical Utility of Expanded Macular OCTs Using Machine Learning

Purpose

Optical coherence tomography (OCT) is widely used in the management of retinal pathologies, including age-related macular degeneration (AMD), diabetic macular edema (DME), and primary open-angle glaucoma (POAG). We used machine learning techniques to understand diagnostic performance gains from expanding macular OCT B-scans compared with foveal-only OCT B-scans for these conditions.

Methods

Electronic medical records were extracted to obtain 61 B-scans per eye from patients with AMD, diabetic retinopathy, or POAG. We constructed deep neural networks and random forest ensembles and generated area under the receiver operating characteristic (AUROC) and area under the precision recall (AUPR) curves.

Results

After extracting 630,000 OCT images, we achieved improved AUROC and AUPR curves when comparing the central image (one B-scan) to all images (61 B-scans). The AUROC and AUPR points of diminishing return for diagnostic accuracy for macular OCT coverage were found to be within 2.75 to 4.00 mm (14–19 B-scans), 4.25 to 4.50 mm (20–21 B-scans), and 4.50 to 6.25 mm (21–28 B-scans) for AMD, DME, and POAG, respectively. All models with >0.25 mm of coverage had statistically significantly improved AUROC/AUPR curves for all diseases (P < 0.05).

Conclusions

Systematically expanded macular coverage models demonstrated significant differences in total macular coverage required for improved diagnostic accuracy, with the largest macular area being relevant in POAG followed by DME and then AMD. These findings support our hypothesis that the extent of macular coverage by OCT imaging in the clinical setting, for any of the three major disorders, has a measurable impact on the functionality of artificial intelligence decision support.

Translational Relevance

We used machine learning techniques to improve OCT imaging standards for common retinal disease diagnoses.

Digital technology, tele-medicine and artificial intelligence in ophthalmology: A global perspective

The simultaneous maturation of multiple digital and telecommunications technologies in 2020 has created an unprecedented opportunity for ophthalmology to adapt to new models of care using tele-health supported by digital innovations. These digital innovations include artificial intelligence (AI), 5th generation (5G) telecommunication networks and the Internet of Things (IoT), creating an inter-dependent ecosystem offering opportunities to develop new models of eye care addressing the challenges of COVID-19 and beyond. Ophthalmology has thrived in some of these areas partly due to its many image-based investigations. Tele-health and AI provide synchronous solutions to challenges facing ophthalmologists and healthcare providers worldwide. This article reviews how countries across the world have utilised these digital innovations to tackle diabetic retinopathy, retinopathy of prematurity, age-related macular degeneration, glaucoma, refractive error correction, cataract and other anterior segment disorders. The review summarises the digital strategies that countries are developing and discusses technologies that may increasingly enter the clinical workflow and processes of ophthalmologists. Furthermore as countries around the world have initiated a series of escalating containment and mitigation measures during the COVID-19 pandemic, the delivery of eye care services globally has been significantly impacted. As ophthalmic services adapt and form a "new normal", the rapid adoption of some of telehealth and digital innovation during the pandemic is also discussed. Finally, challenges for validation and clinical implementation are considered, as well as recommendations on future directions.

Automatic Detection of Genetics and Genomics of Eye Disease Using Deep Assimilation Learning Algorithm

Diabetic retinopathy (DR) is one of the most prevalent genetic diseases in human and it is caused by damage to the blood vessels in the eye retina. If it is undetected and untreated at right time, it can lead to vision loss. There are many medical imaging and processing technologies to improve the diagnostic process of DR to overcome the lack of human experts. In the existing image processing methods, there are issues such as lack of noise removal, improper clustering segmentation and less classification accuracy. This can be accomplished by automatic diagnosis of DR using advanced image processing method. The cotton wool spot (CWS), hard exudates (HE) contains a common manifestation of many diseases in retina including DR and acquired immunodeficiency syndrome. In the present work, super iterative clustering algorithm (SICA) is proposed to identify the CWS, HE on retinal image. Feature-based medical image retrieval (FBMIR) datasets are utilized for this purpose. Noises present on the images and histogram-filtering technique is used to convert red, green, and blue (RGB) images into a perfect greyscale image without noise. After pre-processing, SICA is used to identify the CWS, HE detection on retinal images and eliminates unnecessary areas of interest. In the third stage, after detecting CWS and HE, various statistical features are extracted for further classification using deep assimilation learning algorithm (DALA). The performance of DALA technique is examined with various classification parameters like recall, precision, and F-measure. Finally, the false classification ratios are computed to compare the performance of the trained networks. The proposed method produces accurate detection of affected regions with an accuracy ratio of 98.5% and it is higher than the other conventional methods. This method may improve the accuracy of automatic detection and classification of eye diseases.

The Evolution of Diabetic Retinopathy Screening Programmes: A Chronology of Retinal Photography from 35 mm Slides to Artificial Intelligence

As a third of people with diabetes mellitus (DM) will suffer the microvascular complications of diabetic retinopathy (DR) and therapeutic options can effectively prevent visual impairment, systematic screening has substantially reduced disease burden in developed countries. In an effort to tackle the rising incidence of DM, screening programmes have modernized in synchrony with technical and infrastructural advancements. Patient evaluation has shifted from face-to-face ophthalmologist-based review delivered through community grassroots to asynchronous store-and-forward modern telemedicine platforms commissioned on a nationwide scale. First pioneered with primitive 35-mm slide film retinal photography, the last decade has seen an emergence of high resolution and widefield imaging devices, which may reveal extents of DR indiscernible to the clinician but with implications of potential earlier identification. Similar progress has been seen in image analysis approaches - automated image analysis of retinal photographs of DR has evolved from qualitative feature detection to rules-based algorithms to autonomous artificial intelligence-powered classification. Such models have, relatively rapidly, been validated and are now receiving approval from health regulation authorities with deployment into the clinical sphere. In this review, we chart the evolution of global DR screening programmes since their inception highlighting major milestones in healthcare infrastructure, telemedicine approaches and imaging devices that have shaped the robust and effective frameworks recognised today. We also provide an outlook for the future of DR screening in the context of recent technological advancements with respect to their limitations in current times.

Comparison of smartphone-based retinal imaging systems for diabetic retinopathy detection using deep learning

Background

Diabetic retinopathy (DR), the most common cause of vision loss, is caused by damage to the small blood vessels in the retina. If untreated, it may result in varying degrees of vision loss and even blindness. Since DR is a silent disease that may cause no symptoms or only mild vision problems, annual eye exams are crucial for early detection to improve chances of effective treatment where fundus cameras are used to capture retinal image. However, fundus cameras are too big and heavy to be transported easily and too costly to be purchased by every health clinic, so fundus cameras are an inconvenient tool for widespread screening. Recent technological developments have enabled to use of smartphones in designing small-sized, low-power, and affordable retinal imaging systems to perform DR screening and automated DR detection using image processing methods. In this paper, we investigate the smartphone-based portable retinal imaging systems available on the market and compare their image quality and the automatic DR detection accuracy using a deep learning framework.

Results

Based on the results, iNview retinal imaging system has the largest field of view and better image quality compared with iExaminer, D-Eye, and Peek Retina systems. The overall classification accuracy of smartphone-based systems are sorted as 61%, 62%, 69%, and 75% for iExaminer, D-Eye, Peek Retina, and iNview images, respectively. We observed that the network DR detection performance decreases as the field of view of the smartphone-based retinal systems get smaller where iNview is the largest and iExaminer is the smallest.

Conclusions

The smartphone-based retina imaging systems can be used as an alternative to the direct ophthalmoscope. However, the field of view of the smartphone-based retina imaging systems plays an important role in determining the automatic DR detection accuracy.

A survey on medical image analysis in diabetic retinopathy

Diabetic Retinopathy (DR) represents a highly-prevalent complication of diabetes in which individuals suffer from damage to the blood vessels in the retina. The disease manifests itself through lesion presence, starting with microaneurysms, at the nonproliferative stage before being characterized by neovascularization in the proliferative stage. Retinal specialists strive to detect DR early so that the disease can be treated before substantial, irreversible vision loss occurs. The level of DR severity indicates the extent of treatment necessary - vision loss may be preventable by effective diabetes management in mild (early) stages, rather than subjecting the patient to invasive laser surgery. Using artificial intelligence (AI), highly accurate and efficient systems can be developed to help assist medical professionals in screening and diagnosing DR earlier and without the full resources that are available in specialty clinics. In particular, deep learning facilitates diagnosis earlier and with higher sensitivity and specificity. Such systems make decisions based on minimally handcrafted features and pave the way for personalized therapies. Thus, this survey provides a comprehensive description of the current technology used in each step of DR diagnosis. First, it begins with an introduction to the disease and the current technologies and resources available in this space. It proceeds to discuss the frameworks that different teams have used to detect and classify DR. Ultimately, we conclude that deep learning systems offer revolutionary potential to DR identification and prevention of vision loss.

Automatic Grading System for Diabetic Retinopathy Diagnosis Using Deep Learning Artificial Intelligence Software

Purposes: To describe the development and validation of an artificial intelligence-based, deep learning algorithm (DeepDR) for the detection of diabetic retinopathy (DR) in retinal fundus photographs. Methods: Five hundred fundus images, which had detailed labelling of DR lesions, were transmitted to be analysed, including localization of the optic disk and macular, vessel segmentation, detection of lesions, and grading of DR. The multi-level iterative method of convolutional neural network and the strategy of enhanced learning were used to improve the accuracy of the system (DeepDR) for grading DR. Three public data sets were used to further train the software. The final grading results were tested based on the fundus images provided by the hospitals. Results: For 6788 fundus images (both macular and disc centred) of two Hospital Eye Center, the detection of microaneurysm, haemorrhage and hard exudates had an accuracy of 99.7%, 98.4% and 98.1%, respectively. The current algorithm accuracy was 0.96. Another 20,000 fundus images from community screening were selected, and 7593 photos of poor quality were excluded according to quality standards. Accuracy for accurate staging of fundus photos: accuracy was 0.9179. The sensitivity, specificity and area under the curve (AUC) were 80.58%, 95.77% and 0.9327, respectively. Conclusions: This artificial intelligence-based DeepDR can be used with high accuracy for the detection of DR in retinal images. This technology offers the potential to increase the efficiency and accessibility of DR screening programs.

Application of deep learning image assessment software VeriSee™ for diabetic retinopathy screening

PURPOSE

To develop a deep learning image assessment software VeriSee™ and to validate its accuracy in grading the severity of diabetic retinopathy (DR).

METHODS

Diabetic patients who underwent single-field, nonmydriatic, 45-degree color retinal fundus photography at National Taiwan University Hospital between July 2007 and June 2017 were retrospectively recruited. A total of 7524 judgeable color fundus images were collected and were graded for the severity of DR by ophthalmologists. Among these pictures, 5649 along with another 31,612 color fundus images from the EyePACS dataset were used for model training of VeriSee™. The other 1875 images were used for validation and were graded for the severity of DR by VeriSee™, ophthalmologists, and internal physicians. Area under the receiver operating characteristic curve (AUC) for VeriSee™, and the sensitivities and specificities for VeriSee™, ophthalmologists, and internal physicians in diagnosing DR were calculated.

RESULTS

The AUCs for VeriSee™ in diagnosing any DR, referable DR and proliferative diabetic retinopathy (PDR) were 0.955, 0.955 and 0.984, respectively. VeriSee™ had better sensitivities in diagnosing any DR and PDR (92.2% and 90.9%, respectively) than internal physicians (64.3% and 20.6%, respectively) (P < 0.001 for both). VeriSee™ also had better sensitivities in diagnosing any DR and referable DR (92.2% and 89.2%, respectively) than ophthalmologists (86.9% and 71.1%, respectively) (P < 0.001 for both), while ophthalmologists had better specificities.

CONCLUSION

VeriSee™ had good sensitivity and specificity in grading the severity of DR from color fundus images. It may offer clinical assistance to non-ophthalmologists in DR screening with nonmydriatic retinal fundus photography.

Health Economic and Safety Considerations for Artificial Intelligence Applications in Diabetic Retinopathy Screening

Systematic screening for diabetic retinopathy (DR) has been widely recommended for early detection in patients with diabetes to address preventable vision loss. However, substantial manpower and financial resources are required to deploy opportunistic screening and transition to systematic DR screening programs. The advent of artificial intelligence (AI) technologies may improve access and reduce the financial burden for DR screening while maintaining comparable or enhanced clinical effectiveness. To deploy an AI-based DR screening program in a real-world setting, it is imperative that health economic assessment (HEA) and patient safety analyses are conducted to guide appropriate allocation of resources and design safe, reliable systems. Few studies published to date include these considerations when integrating AI-based solutions into DR screening programs. In this article, we provide an overview of the current state-of-the-art of AI technology (focusing on deep learning systems), followed by an appraisal of existing literature on the applications of AI in ophthalmology. We also discuss practical considerations that drive the development of a successful DR screening program, such as the implications of false-positive or false-negative results and image gradeability. Finally, we examine different plausible methods for HEA and safety analyses that can be used to assess concerns regarding AI-based screening.

Validation of a Deep Learning Algorithm for Diabetic Retinopathy

Background: To validate our deep learning algorithm (DLA) to read diabetic retinopathy (DR) retinographies. Introduction: Currently DR detection is made by retinography; due to its increasing diabetes mellitus incidence we need to find systems that help us to screen DR. Materials and Methods: The DLA was built and trained using 88,702 images from EyePACS, 1,748 from Messidor-2, and 19,230 from our own population. For validation a total of 38,339 retinographies from 17,669 patients (obtained from our DR screening databases) were read by a DLA and compared by four senior retina ophthalmologists for detecting any-DR and referable-DR. We determined the values of Cohen's weighted Kappa (CWK) index, sensitivity (S), specificity (SP), positive predictive value (PPV) and negative predictive value (NPV), and errors type I and II. Results: The results of the DLA to detect any-DR were: CWK = 0.886 ± 0.004 (95% confidence interval [CI] 0.879-0.894), S = 0.967%, SP = 0.976%, PPV = 0.836%, and NPV = 0.996%. The error type I = 0.024, and the error type II = 0.004. Likewise, the referable-DR results were: CWK = 0.809 (95% CI 0.798-0.819), S = 0.998, SP = 0.968, PPV = 0.701, NPV = 0.928, error type I = 0.032, and error type II = 0.001. Discussion: Our DLA can be used as a high confidence diagnostic tool to help in DR screening, especially when it might be difficult for ophthalmologists or other professionals to identify. It can identify patients with any-DR and those that should be referred. Conclusions: The DLA can be valid to aid in screening of DR.

Imaging and Biomarkers in Diabetic Macular Edema and Diabetic Retinopathy

PURPOSE OF REVIEW

Diabetic retinopathy (DR) is the leading cause of acquired vision loss in adults across the globe. Early identification and treatment of patients with DR is paramount for vision preservation. The aim of this review paper is to outline current and new imaging techniques and biomarkers that are valuable for clinical diagnosis and management of DR.

RECENT FINDINGS

Ultrawide field imaging and automated deep learning algorithms are recent advancements on traditional fundus photography and fluorescein angiography. Optical coherence tomography (OCT) and OCT angiography are techniques that image retinal anatomy and vasculature and OCT is routinely used to monitor response to treatment. Many circulating, vitreous, and genetic biomarkers have been studied to facilitate disease detection and development of new treatments. Recent advancements in retinal imaging and identification of promising new biomarkers for DR have the potential to increase detection, risk stratification, and treatment for patients with DR.

Artificial intelligence-based screening for diabetic retinopathy at community hospital

OBJECTIVES

The purpose of this study is to assess the accuracy of artificial intelligence (AI)-based screening for diabetic retinopathy (DR) and to explore the feasibility of applying AI-based technique to community hospital for DR screening.

METHODS

Nonmydriatic fundus photos were taken for 889 diabetic patients who were screened in community hospital clinic. According to DR international classification standards, ophthalmologists and AI identified and classified these fundus photos. The sensitivity and specificity of AI automatic grading were evaluated according to ophthalmologists' grading.

RESULTS

DR was detected by ophthalmologists in 143 (16.1%) participants and by AI in 145 (16.3%) participants. Among them, there were 101 (11.4%) participants diagnosed with referable diabetic retinopathy (RDR) by ophthalmologists and 103 (11.6%) by AI. The sensitivity, specificity and area under the curve (AUC) of AI for detecting DR were 90.79% (95% CI 86.4-94.1), 98.5% (95% CI 97.8-99.0) and 0.946 (95% CI 0.935-0.956), respectively. For detecting RDR, the sensitivity, specificity and AUC of AI were 91.18% (95% CI 86.4-94.7), 98.79% (95% CI 98.1-99.3) and 0.950 (95% CI 0.939-0.960), respectively.

CONCLUSION

AI has high sensitivity and specificity in detecting DR and RDR, so it is feasible to carry out AI-based DR screening in outpatient clinic of community hospital.

Artificial Intelligence Screening for Diabetic Retinopathy: the Real-World Emerging Application

PURPOSE OF REVIEW

This paper systematically reviews the recent progress in diabetic retinopathy screening. It provides an integrated overview of the current state of knowledge of emerging techniques using artificial intelligence integration in national screening programs around the world. Existing methodological approaches and research insights are evaluated. An understanding of existing gaps and future directions is created.

RECENT FINDINGS

Over the past decades, artificial intelligence has emerged into the scientific consciousness with breakthroughs that are sparking increasing interest among computer science and medical communities. Specifically, machine learning and deep learning (a subtype of machine learning) applications of artificial intelligence are spreading into areas that previously were thought to be only the purview of humans, and a number of applications in ophthalmology field have been explored. Multiple studies all around the world have demonstrated that such systems can behave on par with clinical experts with robust diagnostic performance in diabetic retinopathy diagnosis. However, only few tools have been evaluated in clinical prospective studies. Given the rapid and impressive progress of artificial intelligence technologies, the implementation of deep learning systems into routinely practiced diabetic retinopathy screening could represent a cost-effective alternative to help reduce the incidence of preventable blindness around the world.

Automated Detection of Macular Diseases by Optical Coherence Tomography and Artificial Intelligence Machine Learning of Optical Coherence Tomography Images

Purpose

Although optical coherence tomography (OCT) is essential for ophthalmologists, reading of findings requires expertise. The purpose of this study is to test deep learning with image augmentation for automated detection of chorioretinal diseases.

Methods

A retina specialist diagnosed 1,200 OCT images. The diagnoses involved normal eyes (n=570) and those with wet age-related macular degeneration (AMD) (n=136), diabetic retinopathy (DR) (n=104), epiretinal membranes (ERMs) (n=90), and another 19 diseases. Among them, 1,100 images were used for deep learning training, augmented to 59,400 by horizontal flipping, rotation, and translation. The remaining 100 images were used to evaluate the trained convolutional neural network (CNN) model.

Results

Automated disease detection showed that the first candidate disease corresponded to the doctor's decision in 83 (83%) images and the second candidate disease in seven (7%) images. The precision and recall of the CNN model were 0.85 and 0.97 for normal eyes, 1.00 and 0.77 for wet AMD, 0.78 and 1.00 for DR, and 0.75 and 0.75 for ERMs, respectively. Some of rare diseases such as Vogt–Koyanagi–Harada disease were correctly detected by image augmentation in the CNN training.

Conclusion

Automated detection of macular diseases from OCT images might be feasible using the CNN model. Image augmentation might be effective to compensate for a small image number for training.

Deep Learning-Based Algorithms in Screening of Diabetic Retinopathy: A Systematic Review of Diagnostic Performance

TOPIC

Diagnostic performance of deep learning-based algorithms in screening patients with diabetes for diabetic retinopathy (DR). The algorithms were compared with the current gold standard of classification by human specialists.

CLINICAL RELEVANCE

Because DR is a common cause of visual impairment, screening is indicated to avoid irreversible vision loss. Automated DR classification using deep learning may be a suitable new screening tool that could improve diagnostic performance and reduce manpower.

METHODS

For this systematic review, we aimed to identify studies that incorporated the use of deep learning in classifying full-scale DR in retinal fundus images of patients with diabetes. The studies had to provide a DR grading scale, a human grader as a reference standard, and a deep learning performance score. A systematic search on April 5, 2018, through MEDLINE and Embase yielded 304 publications. To identify potentially missed publications, the reference lists of the final included studies were manually screened, yielding no additional publications. The Quality Assessment of Diagnostic Accuracy Studies 2 tool was used for risk of bias and applicability assessment.

RESULTS

By using objective selection, we included 11 diagnostic accuracy studies that validated the performance of their deep learning method using a new group of patients or retrospective datasets. Eight studies reported sensitivity and specificity of 80.28% to 100.0% and 84.0% to 99.0%, respectively. Two studies report accuracies of 78.7% and 81.0%. One study provides an area under the receiver operating curve of 0.955. In addition to diagnostic performance, one study also reported on patient satisfaction, showing that 78% of patients preferred an automated deep learning model over manual human grading.

CONCLUSIONS

Advantages of implementing deep learning-based algorithms in DR screening include reduction in manpower, cost of screening, and issues relating to intragrader and intergrader variability. However, limitations that may hinder such an implementation particularly revolve around ethical concerns regarding lack of trust in the diagnostic accuracy of computers. Considering both strengths and limitations, as well as the high performance of deep learning-based algorithms, automated DR classification using deep learning could be feasible in a real-world screening scenario.

Automated Detection of Diabetic Retinopathy using Deep Learning

Diabetic retinopathy is a leading cause of blindness among working-age adults. Early detection of this condition is critical for good prognosis. In this paper, we demonstrate the use of convolutional neural networks (CNNs) on color fundus images for the recognition task of diabetic retinopathy staging. Our network models achieved test metric performance comparable to baseline literature results, with validation sensitivity of 95%. We additionally explored multinomial classification models, and demonstrate that errors primarily occur in the misclassification of mild disease as normal due to the CNNs inability to detect subtle disease features. We discovered that preprocessing with contrast limited adaptive histogram equalization and ensuring dataset fidelity by expert verification of class labels improves recognition of subtle features. Transfer learning on pretrained GoogLeNet and AlexNet models from ImageNet improved peak test set accuracies to 74.5%, 68.8%, and 57.2% on 2-ary, 3-ary, and 4-ary classification models, respectively.

Deep learning applications in ophthalmology

PURPOSE OF REVIEW

To describe the emerging applications of deep learning in ophthalmology.

RECENT FINDINGS

Recent studies have shown that various deep learning models are capable of detecting and diagnosing various diseases afflicting the posterior segment of the eye with high accuracy. Most of the initial studies have centered around detection of referable diabetic retinopathy, age-related macular degeneration, and glaucoma.

SUMMARY

Deep learning has shown promising results in automated image analysis of fundus photographs and optical coherence tomography images. Additional testing and research is required to clinically validate this technology.

Retinal Telemedicine

PURPOSE OF REVIEW

An update and overview of the literature on current telemedicine applications in retina.

RECENT FINDINGS

The application of telemedicine to the field of Ophthalmology and Retina has been growing with advancing technologies in ophthalmic imaging. Retinal telemedicine has been most commonly applied to diabetic retinopathy and retinopathy of prematurity in adult and pediatric patients respectively. Telemedicine has the potential to alleviate the growing demand for clinical evaluation of retinal diseases. Subsequently, automated image analysis and deep learning systems may facilitate efficient processing of large, increasing numbers of images generated in telemedicine systems. Telemedicine may additionally improve access to education and standardized training through tele-education systems.

SUMMARY

Telemedicine has the potential to be utilized as a useful adjunct but not a complete replacement for physical clinical examinations. Retinal telemedicine programs should be carefully and appropriately integrated into current clinical systems.

An observational study to assess if automated diabetic retinopathy image assessment software can replace one or more steps of manual imaging grading and to determine their cost-effectiveness

BACKGROUND

Diabetic retinopathy screening in England involves labour-intensive manual grading of retinal images. Automated retinal image analysis systems (ARIASs) may offer an alternative to manual grading.

OBJECTIVES

To determine the screening performance and cost-effectiveness of ARIASs to replace level 1 human graders or pre-screen with ARIASs in the NHS diabetic eye screening programme (DESP). To examine technical issues associated with implementation.

DESIGN

Observational retrospective measurement comparison study with a real-time evaluation of technical issues and a decision-analytic model to evaluate cost-effectiveness.

SETTING

A NHS DESP.

PARTICIPANTS

Consecutive diabetic patients who attended a routine annual NHS DESP visit.

INTERVENTIONS

Retinal images were manually graded and processed by three ARIASs: iGradingM (version 1.1; originally Medalytix Group Ltd, Manchester, UK, but purchased by Digital Healthcare, Cambridge, UK, at the initiation of the study, purchased in turn by EMIS Health, Leeds, UK, after conclusion of the study), Retmarker (version 0.8.2, Retmarker Ltd, Coimbra, Portugal) and EyeArt (Eyenuk Inc., Woodland Hills, CA, USA). The final manual grade was used as the reference standard. Arbitration on a subset of discrepancies between manual grading and the use of an ARIAS by a reading centre masked to all grading was used to create a reference standard manual grade modified by arbitration.

MAIN OUTCOME MEASURES

Screening performance (sensitivity, specificity, false-positive rate and likelihood ratios) and diagnostic accuracy [95% confidence intervals (CIs)] of ARIASs. A secondary analysis explored the influence of camera type and patients' ethnicity, age and sex on screening performance. Economic analysis estimated the cost per appropriate screening outcome identified.

RESULTS

A total of 20,258 patients with 102,856 images were entered into the study. The sensitivity point estimates of the ARIASs were as follows: EyeArt 94.7% (95% CI 94.2% to 95.2%) for any retinopathy, 93.8% (95% CI 92.9% to 94.6%) for referable retinopathy and 99.6% (95% CI 97.0% to 99.9%) for proliferative retinopathy; and Retmarker 73.0% (95% CI 72.0% to 74.0%) for any retinopathy, 85.0% (95% CI 83.6% to 86.2%) for referable retinopathy and 97.9% (95% CI 94.9 to 99.1%) for proliferative retinopathy. iGradingM classified all images as either 'disease' or 'ungradable', limiting further iGradingM analysis. The sensitivity and false-positive rates for EyeArt were not affected by ethnicity, sex or camera type but sensitivity declined marginally with increasing patient age. The screening performance of Retmarker appeared to vary with patient's age, ethnicity and camera type. Both EyeArt and Retmarker were cost saving relative to manual grading either as a replacement for level 1 human grading or used prior to level 1 human grading, although the latter was less cost-effective. A threshold analysis testing the highest ARIAS cost per patient before which ARIASs became more expensive per appropriate outcome than human grading, when used to replace level 1 grader, was Retmarker £3.82 and EyeArt £2.71 per patient.

LIMITATIONS

The non-randomised study design limited the health economic analysis but the same retinal images were processed by all ARIASs in this measurement comparison study.

CONCLUSIONS

Retmarker and EyeArt achieved acceptable sensitivity for referable retinopathy and false-positive rates (compared with human graders as reference standard) and appear to be cost-effective alternatives to a purely manual grading approach. Future work is required to develop technical specifications to optimise deployment and address potential governance issues.

FUNDING

The National Institute for Health Research (NIHR) Health Technology Assessment programme, a Fight for Sight Grant (Hirsch grant award) and the Department of Health's NIHR Biomedical Research Centre for Ophthalmology at Moorfields Eye Hospital and the University College London Institute of Ophthalmology.

Automated segmentation of hyperreflective foci in spectral domain optical coherence tomography with diabetic retinopathy

We propose an automated segmentation method to detect, segment, and quantify hyperreflective foci (HFs) in three-dimensional (3-D) spectral domain optical coherence tomography (SD-OCT). The algorithm is divided into three stages: preprocessing, layer segmentation, and HF segmentation. In this paper, a supervised classifier (random forest) was used to produce the set of boundary probabilities in which an optimal graph search method was then applied to identify and produce the layer segmentation using the Sobel edge algorithm. An automated grow-cut algorithm was applied to segment the HFs. The proposed algorithm was tested on 20 3-D SD-OCT volumes from 20 patients diagnosed with proliferative diabetic retinopathy (PDR) and diabetic macular edema (DME). The average dice similarity coefficient and correlation coefficient ([Formula: see text]) are 62.30%, 96.90% for PDR, and 63.80%, 97.50% for DME, respectively. The proposed algorithm can provide clinicians with accurate quantitative information, such as the size and volume of the HFs. This can assist in clinical diagnosis, treatment, disease monitoring, and progression.

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.