Automated multidimensional deep learning platform for referable diabetic retinopathy detection: a multicentre, retrospective study. Issue 7 (28th July 2022)

• Record Type: Journal Article
• Authors: Zhang, Guihua; Lin, Jian-Wei; Wang, Ji; Ji, Jie; Cen, Ling-Ping; Chen, Weiqi; Xie, Peiwen; Zheng, Yi; Xiong, Yongqun; Wu, Hanfu; Li, Dongjie; Ng, Tsz Kin; Pang, Chi Pui; Zhang, Mingzhi
• Is Part Of: BMJ open. Volume 12:Issue 7(2022)
• Publication Date: 2022-07-28
• Subjects: diabetic retinopathy -- vetreoretinal -- medical retina; Medicine -- Research -- Periodicals; 610.72
• DOI: 10.1136/bmjopen-2021-060155
• Languages: English
• ISSNs: 2044-6055

Abstract

Abstract : Objective: To develop and validate a real-world screening, guideline-based deep learning (DL) system for referable diabetic retinopathy (DR) detection. Design: This is a multicentre platform development study based on retrospective, cross-sectional data sets. Images were labelled by two-level certificated graders as the ground truth. According to the UK DR screening guideline, a DL model based on colour retinal images with five-dimensional classifiers, namely image quality, retinopathy, maculopathy gradability, maculopathy and photocoagulation, was developed. Referable decisions were generated by integrating the output of all classifiers and reported at the image, eye and patient level. The performance of the DL was compared with DR experts. Setting: DR screening programmes from three hospitals and the Lifeline Express Diabetic Retinopathy Screening Program in China. Participants: 83 465 images of 39 836 eyes from 21 716 patients were annotated, of which 53 211 images were used as the development set and 30 254 images were used as the external validation set, split based on centre and period. Main outcomes: Accuracy, F1 score, sensitivity, specificity, area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), Cohen's unweighted κ and Gwet's AC1 were calculated to evaluate the performance of the DL algorithm. Results: In the external validation set, the five classifiers achieved an accuracy of 0.915–0.980, F1 score of 0.682–0.966, sensitivity of 0.917–0.978, specificity of 0.907–0.981, AUROC of 0.9639–0.9944 and AUPRC of 0.7504–0.9949. Referable DR at three levels was detected with an accuracy of 0.918–0.967, F1 score of 0.822–0.918, sensitivity of 0.970–0.971, specificity of 0.905–0.967, AUROC of 0.9848–0.9931 and AUPRC of 0.9527–0.9760. With reference to the ground truth, the DL system showed comparable performance (Cohen's κ: 0.86–0.93; Gwet's AC1: 0.89–0.94) with three DR experts (Cohen's κ: 0.89–0.96; Gwet's AC1: 0.91–0.97) in detecting referable lesions. Conclusions: The automatic DL system for detection of referable DR based on the UK guideline could achieve high accuracy in multidimensional classifications. It is suitable for large-scale, real-world DR screening.