Objective To evaluate the accuracy of convolutional neural networks technique (CNN) in detecting keratoconus using colour-coded corneal maps obtained by a Scheimpflug camera. Design Multicentre retrospective study. Methods and analysis We included the images of keratoconic and healthy volunteers’ eyes provided by three centres: Royal Liverpool University Hospital (Liverpool, UK), Sedaghat Eye Clinic (Mashhad, Iran) and The New Zealand National Eye Center (New Zealand). Corneal tomography scans were used to train and test CNN models, which included healthy controls. Keratoconic scans were classified according to the Amsler-Krumeich classification. Keratoconic scans from Iran were used as an independent testing set. Four maps were considered for each scan: axial map, anterior and posterior elevation map, and pachymetry map. Results A CNN model detected keratoconus versus health eyes with an accuracy of 0.9785 on the testing set, considering all four maps concatenated. Considering each map independently, the accuracy was 0.9283 for axial map, 0.9642 for thickness map, 0.9642 for the front elevation map and 0.9749 for the back elevation map. The accuracy of models in recognising between healthy controls and stage 1 was 0.90, between stages 1 and 2 was 0.9032, and between stages 2 and 3 was 0.8537 using the concatenated map. Conclusion CNN provides excellent detection performance for keratoconus and accurately grades different severities of disease using the colour-coded maps obtained by the Scheimpflug camera. CNN has the potential to be further developed, validated and adopted for screening and management of keratoconus. No data are available.

中文翻译：

---

使用颜色编码地图的深度学习来检测圆锥角膜的变化

目的 评估卷积神经网络技术 (CNN) 使用 Scheimpflug 相机获得的彩色角膜图检测圆锥角膜的准确性。设计多中心回顾性研究。方法和分析 我们纳入了三个中心提供的圆锥角膜和健康志愿者眼睛的图像：皇家利物浦大学医院（英国利物浦）、Sedaghat 眼科诊所（伊朗马什哈德）和新西兰国家眼科中心（新西兰）。角膜断层扫描用于训练和测试 CNN 模型，其中包括健康对照。根据 Amsler-Krumeich 分类对角膜角膜扫描进行分类。来自伊朗的角膜曲率扫描被用作独立的测试集。每次扫描都考虑了四个地图：轴向图、前后高程图和测厚图。结果 CNN 模型在测试集上检测到圆锥角膜与健康眼睛的准确度为 0.9785，考虑到所有四个地图连接在一起。单独考虑每张图，轴向图的精度为 0.9283，厚度图的精度为 0.9642，前高程图的精度为 0.9642，后高程图的精度为 0.9749。模型在健康对照和阶段 1 之间的识别准确率为 0.90，阶段 1 和阶段 2 之间是 0.9032，阶段 2 和阶段 3 之间是 0.8537，使用连接图。结论 CNN 为圆锥角膜提供了出色的检测性能，并使用 Scheimpflug 相机获得的颜色编码图准确地对不同严重程度的疾病进行分级。CNN 具有进一步开发、验证和采用圆锥角膜筛查和管理的潜力。没有可用的数据。