An Automated Grading System for Detection of Vision-Threatening Referable Diabetic Retinopathy on the Basis of Color Fundus Photographs.

The goal of this study was to describe the development and validation of an artificial intelligence-based, deep learning algorithm (DLA) for the detection of referable diabetic retinopathy (DR). A DLA using a convolutional neural network was developed for automated detection of vision-threatening referable DR (preproliferative DR or worse, diabetic macular edema, or both). The DLA was tested by using a set of 106,244 nonstereoscopic retinal images. A panel of ophthalmologists graded DR severity in retinal photographs included in the development and internal validation data sets (n = 71,043); a reference standard grading was assigned once three graders achieved consistent grading outcomes. For external validation, we tested our DLA using 35,201 images of 14,520 eyes (904 eyes with any DR; 401 eyes with vision-threatening referable DR) from population-based cohorts of Malays, Caucasian Australians, and Indigenous Australians. Among the 71,043 retinal images in the training and validation data sets, 12,329 showed vision-threatening referable DR. In the internal validation data set, the area under the curve (AUC), sensitivity, and specificity of the DLA for vision-threatening referable DR were 0.989, 97.0%, and 91.4%, respectively. Testing against the independent, multiethnic data set achieved an AUC, sensitivity, and specificity of 0.955, 92.5%, and 98.5%, respectively. Among false-positive cases, 85.6% were due to a misclassification of mild or moderate DR. Undetected intraretinal microvascular abnormalities accounted for 77.3% of all false-negative cases. This artificial intelligence-based DLA can be used with high accuracy in the detection of vision-threatening referable DR in retinal images. This technology offers potential to increase the efficiency and accessibility of DR screening programs.

Li Z ，Keel S ，Liu C ，He Y ，Meng W ，Scheetz J ，Lee PY ，Shaw J ，Ting D ，Wong TY ，Taylor H ，Chang R ，He M ... -  《-》

Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation study.

Radical measures are required to identify and reduce blindness due to diabetes to achieve the Sustainable Development Goals by 2030. Therefore, we evaluated the accuracy of an artificial intelligence (AI) model using deep learning in a population-based diabetic retinopathy screening programme in Zambia, a lower-middle-income country. We adopted an ensemble AI model consisting of a combination of two convolutional neural networks (an adapted VGGNet architecture and a residual neural network architecture) for classifying retinal colour fundus images. We trained our model on 76 370 retinal fundus images from 13 099 patients with diabetes who had participated in the Singapore Integrated Diabetic Retinopathy Program, between 2010 and 2013, which has been published previously. In this clinical validation study, we included all patients with a diagnosis of diabetes that attended a mobile screening unit in five urban centres in the Copperbelt province of Zambia from Feb 1 to June 31, 2012. In our model, referable diabetic retinopathy was defined as moderate non-proliferative diabetic retinopathy or worse, diabetic macular oedema, and ungradable images. Vision-threatening diabetic retinopathy comprised severe non-proliferative and proliferative diabetic retinopathy. We calculated the area under the curve (AUC), sensitivity, and specificity for referable diabetic retinopathy, and sensitivities of vision-threatening diabetic retinopathy and diabetic macular oedema compared with the grading by retinal specialists. We did a multivariate analysis for systemic risk factors and referable diabetic retinopathy between AI and human graders. A total of 4504 retinal fundus images from 3093 eyes of 1574 Zambians with diabetes were prospectively recruited. Referable diabetic retinopathy was found in 697 (22·5%) eyes, vision-threatening diabetic retinopathy in 171 (5·5%) eyes, and diabetic macular oedema in 249 (8·1%) eyes. The AUC of the AI system for referable diabetic retinopathy was 0·973 (95% CI 0·969-0·978), with corresponding sensitivity of 92·25% (90·10-94·12) and specificity of 89·04% (87·85-90·28). Vision-threatening diabetic retinopathy sensitivity was 99·42% (99·15-99·68) and diabetic macular oedema sensitivity was 97·19% (96·61-97·77). The AI model and human graders showed similar outcomes in referable diabetic retinopathy prevalence detection and systemic risk factors associations. Both the AI model and human graders identified longer duration of diabetes, higher level of glycated haemoglobin, and increased systolic blood pressure as risk factors associated with referable diabetic retinopathy. An AI system shows clinically acceptable performance in detecting referable diabetic retinopathy, vision-threatening diabetic retinopathy, and diabetic macular oedema in population-based diabetic retinopathy screening. This shows the potential application and adoption of such AI technology in an under-resourced African population to reduce the incidence of preventable blindness, even when the model is trained in a different population. National Medical Research Council Health Service Research Grant, Large Collaborative Grant, Ministry of Health, Singapore; the SingHealth Foundation; and the Tanoto Foundation.

Bellemo V ，Lim ZW ，Lim G ，Nguyen QD ，Xie Y ，Yip MYT ，Hamzah H ，Ho J ，Lee XQ ，Hsu W ，Lee ML ，Musonda L ，Chandran M ，Chipalo-Mutati G ，Muma M ，Tan GSW ，Sivaprasad S ，Menon G ，Wong TY ，Ting DSW ... -  《The Lancet Digital Health》

Screening Referable Diabetic Retinopathy Using a Semi-automated Deep Learning Algorithm Assisted Approach.

Purpose: To assess the accuracy and efficacy of a semi-automated deep learning algorithm (DLA) assisted approach to detect vision-threatening diabetic retinopathy (DR). Methods: We developed a two-step semi-automated DLA-assisted approach to grade fundus photographs for vision-threatening referable DR. Study images were obtained from the Lingtou Cohort Study, and captured at participant enrollment in 2009-2010 ("baseline images") and annual follow-up between 2011 and 2017. To begin, a validated DLA automatically graded baseline images for referable DR and classified them as positive, negative, or ungradable. Following, each positive image, all other available images from patients who had a positive image, and a 5% random sample of all negative images were selected and regraded by trained human graders. A reference standard diagnosis was assigned once all graders achieved consistent grading outcomes or with a senior ophthalmologist's final diagnosis. The semi-automated DLA assisted approach combined initial DLA screening and subsequent human grading for images identified as high-risk. This approach was further validated within the follow-up image datasets and its time and economic costs evaluated against fully human grading. Results: For evaluation of baseline images, a total of 33,115 images were included and automatically graded by the DLA. 2,604 images (480 positive results, 624 available other images from participants with a positive result, and 1500 random negative samples) were selected and regraded by graders. The DLA achieved an area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy of 0.953, 0.970, 0.879, and 88.6%, respectively. In further validation within the follow-up image datasets, a total of 88,363 images were graded using this semi-automated approach and human grading was performed on 8975 selected images. The DLA achieved an AUC, sensitivity, and specificity of 0.914, 0.852, 0.853, respectively. Compared against fully human grading, the semi-automated DLA-assisted approach achieved an estimated 75.6% time and 90.1% economic cost saving. Conclusions: The DLA described in this study was able to achieve high accuracy, sensitivity, and specificity in grading fundus images for referable DR. Validated against long-term follow-up datasets, a semi-automated DLA-assisted approach was able to accurately identify suspect cases, and minimize misdiagnosis whilst balancing safety, time, and economic cost.

Wang Y ，Shi D ，Tan Z ，Niu Y ，Jiang Y ，Xiong R ，Peng G ，He M ... -  《-》

Validation of Deep Convolutional Neural Network-based algorithm for detection of diabetic retinopathy - Artificial intelligence versus clinician for screening.

Shah P ，Mishra DK ，Shanmugam MP ，Doshi B ，Jayaraj H ，Ramanjulu R ... -  《-》

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

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. 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. 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. 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.

van der Heijden AA ，Abramoff MD ，Verbraak F ，van Hecke MV ，Liem A ，Nijpels G ... -  《-》