文献速递角膜与眼表疾病白内障与屈光手术

卷积神经网络对角膜地形图原始数据的分类研究

Corneal Topography Raw Data Classification Using a Convolutional Neural Network.
PubMed 文献 · Am J Ophthalmol · 2020-06-10

该回顾性机器学习实验研究采用3000例Orbscan检查(正常、圆锥角膜、屈光手术史各1000例)训练卷积神经网络,利用四张原始数据图堆叠为四通道输入。验证集(n=300)总体分类准确率达99.3%(98.3%-100%),圆锥角膜灵敏度与特异度均为100%,正常眼灵敏度100%、特异度99%(94.9%-100%),屈光手术史眼灵敏度98%(97.4%-100%)、特异度100%。

要点

  • 卷积神经网络结合角膜地形图原始数据可高效分类正常、圆锥角膜与屈光手术史。
  • 验证集总体准确率99.3%,圆锥角膜识别灵敏度与特异度均达100%。
  • 该方法或可用于屈光手术筛查等角膜地形图常规任务。

核心结论

  • 结合角膜地形图原始数据与卷积神经网络是分类检查的有效方法,可能是自动分析角膜地形图最全面的方式。

研究设计与样本

  • 回顾性机器学习实验研究,共纳入本机构不同患者的3000例Orbscan检查(正常、圆锥角膜、屈光手术史各1000例)用于模型训练与验证。
  • 每类随机分配100例检查进入测试集。
  • 使用前表面最佳拟合球面(BFS)高程、后表面BFS高程、轴向前表面曲率和角膜测厚四张图的原始数值数据,每张图为2500个值的方阵,四图堆叠作为单图像的四通道输入。
  • 构建卷积神经网络并在训练集上训练,在验证集上计算分类准确率及各类别灵敏度和特异度。

主要发现

  • 验证集(n=300)总体分类准确率为99.3%(98.3%-100%)。
  • 圆锥角膜的灵敏度和特异度均为100%。
  • 正常检查的灵敏度为100%,特异度为99%(94.9%-100%)。
  • 屈光手术史检查的灵敏度为98%(97.4%-100%),特异度为100%。

临床怎么用

  • 该卷积神经网络方法可用于角膜地形图检查的自动分类,辅助区分正常、圆锥角膜与屈光手术史。
  • 研究提示该方法可考虑用于屈光手术筛查等角膜地形图常规任务。

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: We investigated the efficiency of a convolutional neural network applied to corneal topography raw data to classify examinations of 3 categories: normal, keratoconus (KC), and history of refractive surgery (RS). DESIGN: Retrospective machine-learning experimental study. METHODS: A total of 3,000 Orbscan examinations (1,000 of each class) of different patients of our institution were selected for model training and validation. One hundred examinations of each class were randomly assigned to the test set. For each examination, the raw numerical data from "elevation against the anterior best fit sphere (BFS)," "elevation against the posterior BFS" "axial anterior curvature," and "pachymetry" maps were used. Each map was a square matrix of 2,500 values. The 4 maps were stacked and used as if they were 4 channels of a single image.A convolutional neural network was built and trained on the training set. Classification accuracy and class wise sensitivity and specificity were calculated for the validation set. RESULTS: Overall classification accuracy of the validation set (n = 300) was 99.3% (98.3%-100%). Sensitivity and specificity were, respectively, 100% and 100% for KC, 100% and 99% (94.9%-100%) for normal examinations, and 98% (97.4%-100%) and 100% for RS examinations. CONCLUSION: Using combined corneal topography raw data with a convolutional neural network is an effective way to classify examinations and probably the most thorough way to automatically analyze corneal topography. It should be considered for other routine tasks performed on corneal topography, such as refractive surgery screening.

来源:Am J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Zéboulon P, Debellemanière G, Bouvet M, et al. Corneal Topography Raw Data Classification Using a Convolutional Neural Network. Am J Ophthalmol. 2020. PMID: 32533948. doi:10.1016/j.ajo.2020.06.005

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。