Medios Technologies, Remidio Innovative Solutions, Singapore.
Remidio Innovative Solutions Inc, Glen Allen VA, Virginia, USA
BMJ Open. 2024 Sep 5;14(9):e081398. doi: 10.1136/bmjopen-2023-081398.
Despite global research on early detection of age-related macular degeneration (AMD), not enough is being done for large-scale screening. Automated analysis of retinal images captured via smartphone presents a potential solution; however, to our knowledge, such an artificial intelligence (AI) system has not been evaluated. The study aimed to assess the performance of an AI algorithm in detecting referable AMD on images captured on a portable fundus camera.
DESIGN, SETTING: A retrospective image database from the Age-Related Eye Disease Study (AREDS) and target device was used.
The algorithm was trained on two distinct data sets with macula-centric images: initially on 108,251 images (55% referable AMD) from AREDS and then fine-tuned on 1108 images (33% referable AMD) captured on Asian eyes using the target device. The model was designed to indicate the presence of referable AMD (intermediate and advanced AMD). Following the first training step, the test set consisted of 909 images (49% referable AMD). For the fine-tuning step, the test set consisted of 238 (34% referable AMD) images. The reference standard for the AREDS data set was fundus image grading by the central reading centre, and for the target device, it was consensus image grading by specialists.
Area under receiver operating curve (AUC), sensitivity and specificity of algorithm.
Before fine-tuning, the deep learning (DL) algorithm exhibited a test set (from AREDS) sensitivity of 93.48% (95% CI: 90.8% to 95.6%), specificity of 82.33% (95% CI: 78.6% to 85.7%) and AUC of 0.965 (95% CI:0.95 to 0.98). After fine-tuning, the DL algorithm displayed a test set (from the target device) sensitivity of 91.25% (95% CI: 82.8% to 96.4%), specificity of 84.18% (95% CI: 77.5% to 89.5%) and AUC 0.947 (95% CI: 0.911 to 0.982).
The DL algorithm shows promising results in detecting referable AMD from a portable smartphone-based imaging system. This approach can potentially bring effective and affordable AMD screening to underserved areas.
尽管全球都在研究年龄相关性黄斑变性（AMD）的早期检测，但在大规模筛查方面做得还不够。通过智能手机捕获的视网膜图像的自动分析提供了一种潜在的解决方案；然而，据我们所知，这种人工智能（AI）系统尚未得到评估。本研究旨在评估一种 AI 算法在检测便携式眼底相机拍摄的图像中可治疗 AMD 的性能。
设计、设置：使用来自年龄相关性眼病研究（AREDS）的回顾性图像数据库和目标设备。
该算法在两个具有黄斑中心的图像数据集上进行了训练：最初在 AREDS 的 108251 张图像（55%为可治疗 AMD）上进行训练，然后在使用目标设备拍摄的亚洲人眼中的 1108 张图像（33%为可治疗 AMD）上进行微调。该模型旨在指示可治疗 AMD（中期和晚期 AMD）的存在。在第一训练步骤之后，测试集由 909 张图像（49%为可治疗 AMD）组成。在微调步骤中，测试集由 238 张（34%为可治疗 AMD）图像组成。AREDS 数据集的参考标准是中央阅读中心对眼底图像的分级，而对于目标设备，它是专家对图像的共识分级。
接收器工作曲线下的面积（AUC）、算法的敏感性和特异性。
在微调之前，深度学习（DL）算法在测试集（来自 AREDS）中显示出 93.48%（95%CI：90.8%至 95.6%）的敏感性、82.33%（95%CI：78.6%至 85.7%）的特异性和 0.965（95%CI：0.95 至 0.98）的 AUC。在微调之后，DL 算法在测试集（来自目标设备）中显示出 91.25%（95%CI：82.8%至 96.4%）的敏感性、84.18%（95%CI：77.5%至 89.5%）的特异性和 0.947（95%CI：0.911 至 0.982）的 AUC。
DL 算法在从便携式智能手机成像系统中检测可治疗 AMD 方面显示出有希望的结果。这种方法有可能为服务不足的地区带来有效的、负担得起的 AMD 筛查。
