METHODS: A deep learning model was trained for laser treatment detection using the EyePACs dataset. Data was randomly assigned, by participant, into development (n=18 945) and validation (n=2105) sets. Analysis was conducted at the single image, eye, and patient levels. The model was then used to filter input for three independent AI models for retinal indications; changes in model efficacy were measured using area under the receiver operating characteristic curve (AUC) and mean absolute error (MAE).
RESULTS: On the task of laser photocoagulation detection: AUCs of 0.981, 0.95, and 0.979 were achieved at the patient, image, and eye levels, respectively. When analysing independent models, efficacy was shown to improve across the board after filtering. Diabetic macular oedema detection on images with artefacts was AUC 0.932 vs AUC 0.955 on those without. Participant sex detection on images with artefacts was AUC 0.872 vs AUC 0.922 on those without. Participant age detection on images with artefacts was MAE 5.33 vs MAE 3.81 on those without.
CONCLUSIONS: The proposed model for laser treatment detection achieved high performance on all analysis metrics and has been demonstrated to positively affect the efficacy of different AI models, suggesting that laser detection can generally improve AI-powered applications for fundus images.
方法:使用EyePACs数据集训练深度学习模型以进行激光治疗检测。数据是随机分配的,参与者,进入开发(n=18945)和验证(n=2105)集。在单个图像上进行分析,眼睛,和患者水平。然后使用该模型过滤用于视网膜适应症的三个独立AI模型的输入;使用接收器工作特征曲线下面积(AUC)和平均绝对误差(MAE)测量模型功效的变化。
结果:关于激光光凝检测:患者的AUC分别为0.981、0.95和0.979,image,和眼睛水平,分别。在分析独立模型时,过滤后显示功效全面提高。在有伪影的图像上检测到的糖尿病性黄斑水肿为AUC0.932,而没有伪影的图像为AUC0.955。在有人工制品的图像上进行的参与性别检测为AUC0.872,而没有人工制品的图像为AUC0.922。在有伪影的图像上的参与者年龄检测为MAE5.33,而没有伪影的图像为MAE3.81。
结论:所提出的激光治疗检测模型在所有分析指标上都实现了高性能,并已被证明对不同AI模型的功效产生积极影响。这表明激光检测通常可以改善AI驱动的眼底图像应用。