发表机构
Casey Eye Institute, Oregon Health & Science University; Department of Biomedical Engineering, Oregon Health & Science University（凯西眼科研究所，俄勒冈健康与科学大学; 生物医学工程系，俄勒冈健康与科学大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究开发了一种3D深度学习网络，利用OCT图像自动识别和体积分割糖尿病视网膜病变中的微动脉瘤，在体素级、病灶级和眼级均达到高准确性，有望辅助DR的诊断与管理。
AI 中文摘要
目的：开发并验证一种基于深度学习的方法，用于在糖尿病视网膜病变（DR）中利用OCT自动识别和体积分割微动脉瘤（MAs）。参与者：共纳入125名参与者，包括20只健康眼、27只轻度NPDR、30只中度NPDR、30只重度NPDR和18只PDR。方法：我们使用商用120-kHz谱域OCT系统（Solix；Visionix/Optovue，Inc.，加利福尼亚州，美国）对每位参与者获取多次重复的3x3-mm扫描，这些扫描经过配准和平均以生成高清晰度体积。我们开发了一个3D深度学习网络来对MAs进行体积分割。网络的输入由原始OCT体积与其反射率反转的对应部分拼接而成。专家评分员手动勾画MAs以生成标注。我们在多个层面评估模型性能，包括体素级分割、病灶级检测和眼级诊断。结果：在测试数据集（20只健康眼，20只DR眼）中，该算法展示了高体素级准确性，在单个体积上的F1分数为79.2%，在平均体积上为86.1%。病灶级检测的F1分数达到96.0%（单个）和97.1%（平均），而扫描级MA存在性的诊断准确率为97.5%（单个和平均）。结论：基于深度学习的方法可以在OCT上准确识别和体积分割MAs，实现量化和表征，并可能有助于DR的诊断、监测和管理。
英文摘要
Purpose: To develop and validate a deep learning-based method for the automated identification and volumetric segmentation of microaneurysms (MAs) in diabetic retinopathy (DR) using OCT. Participants: A total of 125 participants were enrolled, including 20 healthy eyes, 27 with mild NPDR, 30 with moderate NPDR, 30 with severe NPDR, and 18 with PDR. Methods: We obtained multiple repeated 3x3-mm scans from each participant using a commercial 120-kHz spectral-domain OCT system (Solix; Visionix/Optovue, Inc., California, USA), which were registered and averaged to generate high-definition volumes. We developed a 3D deep learning network to segment MAs volumetrically. The input to the network consists of the original OCT volume concatenated with its reflectance-inverted counterpart. Expert graders manually delineated MAs to generate annotations. We evaluated model performance at multiple levels, including voxel-level segmentation, lesion-level detection, and eye-level diagnosis. Results: In the test dataset (20 healthy, 20 DR eyes), the algorithm demonstrated high voxel-level accuracy, with F1 scores of 79.2% on single volumes and 86.1% on averaged volumes. Lesion-level detection reached an F1 score of 96.0% (single) and 97.1% (averaged), while scan-level diagnostic accuracy for MA presence was 97.5% (single and averaged). Conclusions: A deep learning-based method can accurately identify and segment MAs volumetrically on OCT, enabling quantification and characterization, and potentially aiding in the diagnosis, monitoring, and management of DR.
