文献速递青光眼眼底病与葡萄膜炎

深度学习辅助智能手机眼底照相诊断青光眼

Deep learning-assisted (automatic) diagnosis of glaucoma using a smartphone.
PubMed 文献 · Br J Ophthalmol · 2021-07-14

本研究验证了一种深度学习算法利用智能手机拍摄的眼底照片诊断青光眼的能力。训练集包括1364张有青光眼指征和1768张无青光眼特征的彩色眼底照片(普通眼底相机拍摄)。测试集为73例青光眼患者和89例正常对照者的眼底照片,分别用普通眼底相机和智能手机拍摄。普通相机AROC为98.9%,智能手机为84.2%;在晚期青光眼亚组(平均偏差<-12 dB,N=26)中分别为99.3%和90.0%,不同相机间AROC差异显著。

要点

  • 深度学习算法基于智能手机眼底照片筛查青光眼具有较高诊断能力。
  • 普通眼底相机AROC为98.9%,智能手机为84.2%,两者差异显著。
  • 晚期青光眼亚组中智能手机AROC达90.0%,诊断能力更优。

核心结论

  • 深度学习算法从智能手机眼底照片自动筛查青光眼的有用性得到验证。
  • 算法诊断能力相当高,尤其在晚期青光眼眼中。

研究设计与样本

  • 训练集由普通眼底相机拍摄的1364张有青光眼指征和1768张无青光眼特征的彩色眼底照片构成。
  • 测试集包括73例青光眼患者的73只眼和89例正常对照者的89只眼,分别用普通眼底相机和智能手机拍摄眼底照片。
  • 开发深度学习算法诊断青光眼,通过测试集预测结果评估诊断准确性,采用受试者工作特征曲线下面积(AROC)评估。

主要发现

  • 普通眼底相机AROC为98.9%,智能手机AROC为84.2%。
  • 仅晚期青光眼眼(平均偏差值<-12 dB,N=26)中,普通相机AROC为99.3%,智能手机为90.0%。
  • 不同相机获得的AROC值之间存在显著差异。

关键数值与推荐

  • 训练集:1364张有青光眼指征和1768张无青光眼特征的彩色眼底照片。
  • 测试集:73例青光眼患者和89例正常对照者。
  • 晚期青光眼定义:平均偏差值<-12 dB,N=26。
  • 诊断准确性指标:普通相机AROC 98.9%,智能手机AROC 84.2%;晚期亚组分别为99.3%和90.0%。

临床怎么用

  • 深度学习算法可用于智能手机眼底照片的青光眼自动筛查。
  • 在晚期青光眼眼中诊断能力更高,适合资源有限场景的初步筛查。

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/AIMS: To validate a deep learning algorithm to diagnose glaucoma from fundus photography obtained with a smartphone. METHODS: A training dataset consisting of 1364 colour fundus photographs with glaucomatous indications and 1768 colour fundus photographs without glaucomatous features was obtained using an ordinary fundus camera. The testing dataset consisted of 73 eyes of 73 patients with glaucoma and 89 eyes of 89 normative subjects. In the testing dataset, fundus photographs were acquired using an ordinary fundus camera and a smartphone. A deep learning algorithm was developed to diagnose glaucoma using a training dataset. The trained neural network was evaluated by prediction result of the diagnostic of glaucoma or normal over the test datasets, using images from both an ordinary fundus camera and a smartphone. Diagnostic accuracy was assessed using the area under the receiver operating characteristic curve (AROC). RESULTS: The AROC with a fundus camera was 98.9% and 84.2% with a smartphone. When validated only in eyes with advanced glaucoma (mean deviation value < -12 dB, N=26), the AROC with a fundus camera was 99.3% and 90.0% with a smartphone. There were significant differences between these AROC values using different cameras. CONCLUSION: The usefulness of a deep learning algorithm to automatically screen for glaucoma from smartphone-based fundus photographs was validated. The algorithm had a considerable high diagnostic ability, particularly in eyes with advanced glaucoma.

来源:Br J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Nakahara K, Asaoka R, Tanito M, et al. Deep learning-assisted (automatic) diagnosis of glaucoma using a smartphone. Br J Ophthalmol. 2021. PMID: 34261663. doi:10.1136/bjophthalmol-2020-318107

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。