文献速递青光眼眼底病与葡萄膜炎

从机器到机器:用OCT训练的深度学习算法在眼底照片上客观量化青光眼性损伤

From Machine to Machine: An OCT-Trained Deep Learning Algorithm for Objective Quantification of Glaucomatous Damage in Fundus Photographs.
PubMed 文献 · Ophthalmology · 2018-12-20

本研究提出一种新方法,利用定量SD OCT数据训练深度学习算法,在视盘照片上量化青光眼性结构损伤,无需人工标注参考训练集。测试集显示预测与实测RNFL厚度强相关,区分青光眼与健康眼的能力与OCT相当。

要点

  • 用SD OCT平均RNFL厚度训练深度学习算法,在视盘照片上预测RNFL厚度。
  • 测试集预测与实测RNFL厚度强相关(r=0.832),平均绝对误差7.39 μm。
  • 深度学习预测区分青光眼与健康眼的AUC为0.944,与OCT的0.940相当。

核心结论

  • 提出一种深度学习新方法,在眼底照片上提供神经损伤的定量信息,可用于青光眼诊断与分期。
  • 训练神经网络客观预测SD OCT数据,可克服人工标注的局限性,并可能用于眼科其他领域。

研究设计与样本

  • 样本按患者水平随机分为训练加验证集(80%)和测试集(20%)。
  • 训练深度学习卷积神经网络评估视盘照片并预测SD OCT平均RNFL厚度。

主要发现

  • 测试集6292张视盘照片预测平均RNFL厚度为83.3±14.5 μm,对应SD OCT实测为82.5±16.8 μm(P=0.164)。
  • 预测与实测RNFL厚度强相关(Pearson r=0.832;R2=69.3%;P<0.001),平均绝对误差7.39 μm。
  • 深度学习预测与OCT实测区分青光眼与健康眼的AUC分别为0.944(95%CI 0.912-0.966)和0.940(95%CI 0.902-0.966)(P=0.724)。

临床怎么用

  • 可利用OCT训练深度学习算法,在视盘照片上客观量化青光眼性结构损伤,辅助诊断与分期。
  • 该方法无需人工标注参考训练集,可推广至其他需要客观量化的眼科领域。

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: Previous approaches using deep learning (DL) algorithms to classify glaucomatous damage on fundus photographs have been limited by the requirement for human labeling of a reference training set. We propose a new approach using quantitative spectral-domain (SD) OCT data to train a DL algorithm to quantify glaucomatous structural damage on optic disc photographs. DESIGN: Cross-sectional study. PARTICIPANTS: A total of 32 820 pairs of optic disc photographs and SD OCT retinal nerve fiber layer (RNFL) scans from 2312 eyes of 1198 participants. METHODS: The sample was divided randomly into validation plus training (80%) and test (20%) sets, with randomization performed at the patient level. A DL convolutional neural network was trained to assess optic disc photographs and predict SD OCT average RNFL thickness. MAIN OUTCOME MEASURES: The DL algorithm performance was evaluated in the test sample by evaluating correlation and agreement between the predictions and actual SD OCT measurements. We also assessed the ability to discriminate eyes with glaucomatous visual field loss from healthy eyes with area under the receiver operating characteristic (ROC) curves. RESULTS: The mean prediction of average RNFL thickness from all 6292 optic disc photographs in the test set was 83.3±14.5 μm, whereas the mean average RNFL thickness from all corresponding SD OCT scans was 82.5±16.8 μm (P = 0.164). There was a very strong correlation between predicted and observed RNFL thickness values (Pearson r = 0.832; R2 = 69.3%; P < 0.001), with mean absolute error of the predictions of 7.39 μm. The area under the ROC curves for discriminating glaucomatous from healthy eyes with the DL predictions and actual SD OCT average RNFL thickness measurements were 0.944 (95% confidence interval [CI], 0.912-0.966) and 0.940 (95% CI, 0.902-0.966), respectively (P = 0.724). CONCLUSIONS: We introduced a novel DL approach to assess fundus photographs and provide quantitative information about the amount of neural damage that can be used to diagnose and stage glaucoma. In addition, training neural networks to predict SD OCT data objectively represents a new approach that overcomes limitations of human labeling and could be useful in other areas of ophthalmology.

来源:Ophthalmology,查看原文。版权归原作者所有。

引用

  1. Medeiros FA, Jammal AA, Thompson AC, et al. From Machine to Machine: An OCT-Trained Deep Learning Algorithm for Objective Quantification of Glaucomatous Damage in Fundus Photographs. Ophthalmology. 2018. PMID: 30578810. doi:10.1016/j.ophtha.2018.12.033

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。