文献速递眼底病与葡萄膜炎

深度学习自动检测网状假性玻璃膜疣:AREDS2研究

Deep Learning Automated Detection of Reticular Pseudodrusen from Fundus Autofluorescence Images or Color Fundus Photographs in AREDS2.
PubMed 文献 · Ophthalmology · 2020-05-21

FAF模型AUC为0.939,性能优于4名眼科医生;CFP模型AUC为0.832,准确率仍超越眼科医生。深度学习可辅助甚至增强RPD的检测。

要点

  • FAF模型检测RPD的AUC为0.939,κ值0.718,准确率0.899。
  • CFP模型AUC为0.832,κ值0.470,准确率0.809。
  • FAF模型和CFP模型性能均优于4名眼科医生。

核心结论

  • 基于FAF图像的深度学习模型检测RPD达到高准确度,相当于或优于眼科医生。
  • 基于CFP的自动RPD检测准确度较低,但仍超过眼科医生。
  • 深度学习模型可辅助甚至增强这一临床重要AMD相关病变的检测。

研究设计与样本

  • 以阅读中心对FAF图像的分级作为金标准标签,并转移至对应CFP图像。
  • 训练FAF模型检测中晚期AMD患眼的RPD,并利用标签转移训练CFP模型。
  • 使用完整测试集的随机子集,将模型性能与4名眼科医生比较。

主要发现

  • FAF模型AUC为0.939(95%CI 0.927-0.950),κ值0.718(95%CI 0.685-0.751),准确率0.899(95%CI 0.887-0.911)。
  • CFP模型AUC为0.832(95%CI 0.812-0.851),κ值0.470(95%CI 0.426-0.511),准确率0.809(95%CI 0.793-0.825)。
  • FAF模型κ值0.789(95%CI 0.675-0.875)高于4名眼科医生的0.367至0.756,准确率0.937(95%CI 0.907-0.963)高于0.696至0.933。
  • CFP模型κ值0.471(95%CI 0.330-0.606)高于4名眼科医生的0.105至0.180,准确率0.844(95%CI 0.798-0.886)高于0.717至0.814。

关键数值与推荐

  • FAF模型性能指标:AUC 0.939,κ值0.718,准确率0.899。
  • CFP模型性能指标:AUC 0.832,κ值0.470,准确率0.809。
  • FAF模型对比眼科医生:κ值0.789 vs 0.367-0.756,准确率0.937 vs 0.696-0.933。
  • CFP模型对比眼科医生:κ值0.471 vs 0.105-0.180,准确率0.844 vs 0.717-0.814。

临床怎么用

  • FAF图像可用于高准确度自动检测RPD,辅助AMD评估。
  • 无FAF时,CFP图像的自动检测仍可提供优于部分眼科医生的RPD识别。
  • 深度学习模型可作为辅助工具,增强RPD的临床检测能力。

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

PURPOSE: To develop deep learning models for detecting reticular pseudodrusen (RPD) using fundus autofluorescence (FAF) images or, alternatively, color fundus photographs (CFP) in the context of age-related macular degeneration (AMD). DESIGN: Application of deep learning models to the Age-Related Eye Disease Study 2 (AREDS2) dataset. PARTICIPANTS: FAF and CFP images (n = 11 535) from 2450 AREDS2 participants. Gold standard labels from reading center grading of the FAF images were transferred to the corresponding CFP images. METHODS: A deep learning model was trained to detect RPD in eyes with intermediate to late AMD using FAF images (FAF model). Using label transfer from FAF to CFP images, a deep learning model was trained to detect RPD from CFP (CFP model). Performance was compared with 4 ophthalmologists using a random subset from the full test set. MAIN OUTCOME MEASURES: Area under the receiver operating characteristic curve (AUC), κ value, accuracy, and F1 score. RESULTS: The FAF model had an AUC of 0.939 (95% confidence interval [CI], 0.927-0.950), a κ value of 0.718 (95% CI, 0.685-0.751), and accuracy of 0.899 (95% CI, 0.887-0.911). The CFP model showed equivalent values of 0.832 (95% CI, 0.812-0.851), 0.470 (95% CI, 0.426-0.511), and 0.809 (95% CI, 0.793-0.825), respectively. The FAF model demonstrated superior performance to 4 ophthalmologists, showing a higher κ value of 0.789 (95% CI, 0.675-0.875) versus a range of 0.367 to 0.756 and higher accuracy of 0.937 (95% CI, 0.907-0.963) versus a range of 0.696 to 0.933. The CFP model demonstrated substantially superior performance to 4 ophthalmologists, showing a higher κ value of 0.471 (95% CI, 0.330-0.606) versus a range of 0.105 to 0.180 and higher accuracy of 0.844 (95% CI, 0.798-0.886) versus a range of 0.717 to 0.814. CONCLUSIONS: Deep learning-enabled automated detection of RPD presence from FAF images achieved a high level of accuracy, equal or superior to that of ophthalmologists. Automated RPD detection using CFP achieved a lower accuracy that still surpassed that of ophthalmologists. Deep learning models can assist, and even augment, the detection of this clinically important AMD-associated lesion.

来源:Ophthalmology,查看原文。版权归原作者所有。

引用

  1. Keenan TDL, Chen Q, Peng Y, et al. Deep Learning Automated Detection of Reticular Pseudodrusen from Fundus Autofluorescence Images or Color Fundus Photographs in AREDS2. Ophthalmology. 2020. PMID: 32447042. doi:10.1016/j.ophtha.2020.05.036

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。