基于深度学习的眼底疾病筛查诊断系统的初步研究

A preliminary study of a deep learning assisted diagnostic system with an artificial intelligence for detection of retina disease

摘要:

目的：评估基于深度学习的眼底疾病筛查人工智能诊断系统的应用价值。

方法：收集2018-07/12在我院就诊的患者1 345例2 690眼，通过分析比较眼科专家诊断及基于多层深度卷积神经网络学习的人工智能诊断系统的一致性，确定人工智能诊断系统的准确率、特异性和敏感性。

结果：人工智能诊断系统的准确率为62.82%，所纳入患者的诊断结果有1～5(1.38±0.67)个诊断，其中1个诊断的准确率为56.09%，2个诊断的准确率为77.96%，3个诊断的准确率为84.61%，4个诊断的准确率为86.95%，5个诊断的准确率为60.00%； 无明显异常及豹纹状眼底的一致性Kappa值分别为0.044、0.169， 敏感性分别为3.00%、99.6%，特异性分别为99.7%、14.2%，其余诊断的一致性Kappa值高达0.57～1.00，敏感性高达65.1%～100%，特异性高达93.0%～100%。

结论：基于多层深度卷积神经网络学习的人工智能诊断系统能较好地诊断眼底疾病，有望成为基层医疗的有效筛查工具。

Abstract:

AIM:To evaluate the application value of artificial intelligence diagnosis system for fundus disease screening based on deep learning.

METHODS:A total of 1 345 patients(2 690 eyes)in our hospital were recruited from July 2018 to December 2018. The accuracy, specificity, consistency and sensitivity of the artificial intelligence diagnosis system were determined by comparison with ophthalmologist diagnosis and artificial intelligence diagnosis system which based on multi-layer deep convolution neural network learning.

RESULTS:The accuracy of artificial intelligence diagnosis system is 62.82%. There are 1-5(1.38±0.67)diagnoses among the patients, among which the accuracy of one diagnosis is 56.09%, the accuracy of two diagnosis is 77.96%, the accuracy of three diagnosis is 84.61%, the accuracy of four diagnosis is 86.95%, and the accuracy of five diagnosis is 60.00%; The consistency kappa value without obvious abnormality and leopard pattern fundus was 0.044 and 0.169 respectively. The sensitivity was 3.00% and 99.6% respectively, the specificity was 99.7% and 14.2% respectively. The consistency Kappa value of other diagnosis was as high as 0.57-1.00, the sensitivity was as high as 65.1%-100%, and the specificity was as high as 93.0%-100%.

CONCLUSION:This study shows that the artificial intelligence diagnosis system based on multi-layer deep convolution neural network learning is a reliable alternative to diagnose retina diseases, and it is expected to become an effective screening tool for primary medical treatment.