文献速递眼底病与葡萄膜炎

利用超广角眼底照相和深度学习自动检测玻璃体炎

AUTOMATED DETECTION OF VITRITIS USING ULTRAWIDE-FIELD FUNDUS PHOTOGRAPHS AND DEEP LEARNING.
PubMed 文献 · Retina · 2024-01-01

横断面非干预研究使用超广角眼底照相和DenseNet121卷积神经网络检测玻璃体炎,模型检测敏感性91%、特异性89%、准确率0.90、AUC 0.97;外部验证检测准确率0.78;六分类分级准确率有限(0.61),归为三类后提升至0.75。

要点

  • 模型检测玻璃体炎敏感性91%、特异性89%、准确率0.90、AUC 0.97。
  • 外部图像集检测玻璃体炎准确率0.78。
  • 六分类分级准确率0.61,归为三类后0.75,接受一个等级误差时六分类提升至0.90。

核心结论

  • 基于超广角眼底成像的深度学习模型为玻璃体炎检测提供了有效工具。
  • 模型对玻璃体炎按严重程度分为三类的分级性能可接受。
  • 模型对玻璃体炎六分类分级的性能有限,但可能通过更大图像集改善。

研究设计与样本

  • 横断面非干预研究,使用葡萄膜炎患者的超广角眼底视网膜照相。
  • 玻璃体混浊按标准化葡萄膜炎命名法六步分级定义。
  • 采用TensorFlow深度学习框架和DenseNet121卷积神经网络进行分类任务,最佳拟合模型在验证研究中测试。

主要发现

  • 模型检测玻璃体炎的敏感性为91%,特异性为89%,准确率为0.90,受试者操作特征曲线下面积为0.97。
  • 在外部图像集上,检测玻璃体炎的准确率为0.78。
  • 将玻璃体炎按标准化葡萄膜炎命名法分为六类时,分级准确率有限(0.61);归为三类后提升至0.75。
  • 接受一个等级误差时,六分类分级准确率提升至0.90,提示需要更大样本以改善模型性能。

局限性

  • 六分类分级准确率有限(0.61)。
  • 接受一个等级误差时六分类准确率提升至0.90,提示需要更大样本以改善模型性能。
  • 模型性能可能通过更大图像集改善。

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/PURPOSE: Evaluate the performance of a deep learning algorithm for the automated detection and grading of vitritis on ultrawide-field imaging. METHODS: Cross-sectional noninterventional study. Ultrawide-field fundus retinophotographs of uveitis patients were used. Vitreous haze was defined according to the six steps of the Standardization of Uveitis Nomenclature classification. The deep learning framework TensorFlow and the DenseNet121 convolutional neural network were used to perform the classification task. The best fitted model was tested in a validation study. RESULTS: One thousand one hundred eighty-one images were included. The performance of the model for the detection of vitritis was good with a sensitivity of 91%, a specificity of 89%, an accuracy of 0.90, and an area under the receiver operating characteristics curve of 0.97. When used on an external set of images, the accuracy for the detection of vitritis was 0.78. The accuracy to classify vitritis in one of the six Standardization of Uveitis Nomenclature grades was limited (0.61) but improved to 0.75 when the grades were grouped into three categories. When accepting an error of one grade, the accuracy for the six-class classification increased to 0.90, suggesting the need for a larger sample to improve the model performances. CONCLUSION: A new deep learning model based on ultrawide-field fundus imaging that produces an efficient tool for the detection of vitritis was described. The performance of the model for the grading into three categories of increasing vitritis severity was acceptable. The performance for the six-class grading of vitritis was limited but can probably be improved with a larger set of images.

来源:Retina,查看原文。版权归原作者所有。

引用

  1. Mhibik B, Kouadio D, Jung C, et al. AUTOMATED DETECTION OF VITRITIS USING ULTRAWIDE-FIELD FUNDUS PHOTOGRAPHS AND DEEP LEARNING. Retina. 2024. PMID: 38261816. doi:10.1097/IAE.0000000000004049

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。