文献速递眼底病与葡萄膜炎

基于深度学习的眼底图像激光光凝自主筛查

Autonomous screening for laser photocoagulation in fundus images using deep learning.
PubMed 文献 · Br J Ophthalmol · 2024-05-21

该研究利用EyePACs数据集训练深度学习模型检测眼底图像中的激光光凝治疗,数据按参与者随机分为开发集(n=18945)和验证集(n=2105),在患者、图像和眼水平进行单图分析。模型在患者、图像和眼水平的AUC分别为0.981、0.95和0.979,且用该模型过滤输入后,三个独立AI模型的效能均得到改善。

要点

  • 激光光凝检测模型在患者、图像和眼水平的AUC分别为0.981、0.95和0.979。
  • 过滤有伪影图像后,糖尿病黄斑水肿检测AUC从0.932升至0.955。
  • 过滤有伪影图像后,参与者性别检测AUC从0.872升至0.922。

核心结论

  • 所提出的激光治疗检测模型在所有分析指标上均取得高性能,并已证明能正向影响不同AI模型的效能,提示激光检测可普遍改善眼底图像的AI应用。

研究设计与样本

  • 使用EyePACs数据集训练深度学习模型进行激光治疗检测,数据按参与者随机分为开发集(n=18945)和验证集(n=2105),在单图像、眼和患者水平进行分析。

主要发现

  • 激光光凝检测在患者水平的AUC为0.981,在图像水平的AUC为0.95,在眼水平的AUC为0.979。
  • 分析独立模型时,过滤后效能全面改善:有伪影图像的糖尿病黄斑水肿检测AUC为0.932,无伪影图像为0.955。
  • 有伪影图像的参与者性别检测AUC为0.872,无伪影图像为0.922。
  • 有伪影图像的参与者年龄检测MAE为5.33,无伪影图像为3.81。

关键数值与推荐

  • 激光光凝检测模型在患者、图像和眼水平的AUC分别为0.981、0.95和0.979。
  • 有伪影图像糖尿病黄斑水肿检测AUC为0.932,无伪影图像为0.955。
  • 有伪影图像参与者性别检测AUC为0.872,无伪影图像为0.922。
  • 有伪影图像参与者年龄检测MAE为5.33,无伪影图像为3.81。

局限性

  • 原文未报告局限性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Diabetic retinopathy (DR) is a leading cause of blindness in adults worldwide. Artificial intelligence (AI) with autonomous deep learning algorithms has been increasingly used in retinal image analysis, particularly for the screening of referrable DR. An established treatment for proliferative DR is panretinal or focal laser photocoagulation. Training autonomous models to discern laser patterns can be important in disease management and follow-up. 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. CONCLUSION: 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.

来源:Br J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Bressler I, Aviv R, Margalit D, et al. Autonomous screening for laser photocoagulation in fundus images using deep learning. Br J Ophthalmol. 2024. PMID: 37217293. doi:10.1136/bjo-2023-323376

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。