Taylor Joshua R, Drinkwater Jocelyn, Sousa David Cordeiro, Shah Vaibhav, Turner Angus W
Lions Outback Vision, Lions Eye Institute, Nedlands, Western Australia, Australia.
Centre for Ophthalmology and Visual Science, University of Western Australia, Crawley, Western Australia, Australia.
Clin Exp Optom. 2024 Aug 12:1-6. doi: 10.1080/08164622.2024.2385565.
The challenges of establishing retinal screening programs in rural settings may be mitigated by the emergence of deep-learning systems for early disease detection.
Deep-learning systems have demonstrated promising results in retinal disease detection and may be particularly useful in rural settings where accessibility remains a barrier to equitable service provision. This study aims to evaluate the real-world performance of Thirona RetCAD for the detection of referable diabetic retinopathy and age-related macular degeneration in a rural Australian population.
Colour fundus images from participants with known diabetic retinopathy or age-related macular degeneration were randomly selected from ophthalmology clinics in four rural Australian centres. Grading was confirmed retrospectively by two retinal specialists. RetCAD produced a quantitative measure (0-100) for DR and AMD severity. The area under the ROC curve (AUC) was calculated. Sensitivity, specificity, and positive and negative predictive values were calculated at a pre-defined cut-point of ≥50.
A total of 150 images from 82 participants were included. The mean age (SD) was 64.0 (12.8) years. Seventy-nine (52.7%) eyes had evidence of referable DR, while 54 (36.0%) had evidence of referable AMD. The AUC for referable DR detection was 0.971 (95% CI 0.950-0.936) with a sensitivity of 86.1% (76.8%-92.0%) and a specificity of 91.6% (82.8%-96.1%) at the pre-defined cut-point. Using the Youden Index method, the optimal cut-point was 41.2 (sensitivity 93.7%, specificity 90.1%). The AUC for the detection of referable AMD was 0.880 (0.824-0.936). At the pre-defined cut-point sensitivity was 88.9% (77.8%-94.8%) and specificity was 66.7% (56.8%-75.3%). The optimal cut-point was 52.6 (sensitivity 87.0%, specificity 75.0%).
RetCAD is comparable with but does not outperform equivalent deep-learning systems for retinal disease detection. RetCAD may be suitable as an automated screening tool in a rural Australian setting.
深度学习系统用于早期疾病检测的出现，可能会减轻在农村地区建立视网膜筛查项目的挑战。
深度学习系统在视网膜疾病检测中已显示出有前景的结果，在农村地区可能特别有用，因为在这些地区可及性仍然是公平提供服务的障碍。本研究旨在评估Thirona RetCAD在澳大利亚农村人群中检测可转诊糖尿病视网膜病变和年龄相关性黄斑变性的实际性能。
从澳大利亚四个农村中心的眼科诊所中随机选择患有已知糖尿病视网膜病变或年龄相关性黄斑变性参与者的彩色眼底图像。由两名视网膜专家进行回顾性分级确认。RetCAD对糖尿病视网膜病变和年龄相关性黄斑变性的严重程度产生定量测量值（0 - 100）。计算ROC曲线下面积（AUC）。在预先定义的≥50的切点处计算敏感性、特异性以及阳性和阴性预测值。
共纳入来自82名参与者的150张图像。平均年龄（标准差）为64.0（12.8）岁。79只（52.7%）眼睛有可转诊糖尿病视网膜病变的证据，而54只（36.0%）有可转诊年龄相关性黄斑变性的证据。可转诊糖尿病视网膜病变检测的AUC为0.971（95%可信区间0.950 - 0.936），在预先定义的切点处敏感性为86.1%（76.8% - 92.0%），特异性为91.6%（82.8% - 96.1%）。使用约登指数法，最佳切点为41.2（敏感性93.7%，特异性90.1%）。可转诊年龄相关性黄斑变性检测的AUC为0.880（0.824 - 0.936）。在预先定义的切点处敏感性为88.9%（77.8% - 94.8%），特异性为66.7%（56.8% - 75.3%）。最佳切点为52.6（敏感性87.0%，特异性75.0%）。
RetCAD在视网膜疾病检测方面与等效的深度学习系统相当，但并不优于它们。RetCAD可能适合作为澳大利亚农村地区的一种自动筛查工具。
