深度学习对糖尿病视网膜病变患者眼底荧光血管造影图像的自动解读与临床评估
本研究收集845例糖尿病视网膜病变患者的1558只眼共15599张眼底荧光血管造影(FFA)图像,训练三种卷积神经网络模型用于图像质量、位置、眼别、分期及五种病变的分类,ResNet18表现最佳,预诊断评估准确率80.79%-93.34%,病变检测准确率63.67%-88.88%,人机对比显示其准确率与低年资眼科医师相似。
要点
- ResNet18在预诊断评估中准确率达80.79%-93.34%,在病变检测中达63.67%-88.88%。
- 人机对比显示卷积神经网络准确率与低年资眼科医师相似。
- 假阳性与假阴性分析为模型改进提供了方向。
核心结论
- 作者认为该模型可应用于临床实践,并将对FFA图像的智能诊断发展做出贡献。
研究设计与样本
- 研究收集并标注了845例糖尿病视网膜病变患者的1558只眼共15599张FFA图像。
- 训练三种卷积神经网络模型以生成图像质量、位置、眼别、分期及五种病变的标签。
- 采用准确率、F-1分数、曲线下面积及人机对比评估模型性能,并对假阳性与假阴性结果进行详细分析。
主要发现
- 与LeNet-5和VGG16相比,ResNet18取得最佳结果,预诊断评估准确率达80.79%-93.34%,病变检测准确率达63.67%-88.88%。
- 人机对比显示卷积神经网络的准确率与低年资眼科医师相似。
- 假阳性与假阴性分析指出了改进方向。
临床怎么用
- 原文结论认为该模型可应用于临床实践,但未给出具体推荐条款。
局限性
- 原文未报告局限性。
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: Fundus fluorescein angiography (FFA) is an important technique to evaluate diabetic retinopathy (DR) and other retinal diseases. The interpretation of FFA images is complex and time-consuming, and the ability of diagnosis is uneven among different ophthalmologists. The aim of the study is to develop a clinically usable multilevel classification deep learning model for FFA images, including prediagnosis assessment and lesion classification. METHODS: A total of 15 599 FFA images of 1558 eyes from 845 patients diagnosed with DR were collected and annotated. Three convolutional neural network (CNN) models were trained to generate the label of image quality, location, laterality of eye, phase and five lesions. Performance of the models was evaluated by accuracy, F-1 score, the area under the curve and human-machine comparison. The images with false positive and false negative results were analysed in detail. RESULTS: Compared with LeNet-5 and VGG16, ResNet18 got the best result, achieving an accuracy of 80.79%-93.34% for prediagnosis assessment and an accuracy of 63.67%-88.88% for lesion detection. The human-machine comparison showed that the CNN had similar accuracy with junior ophthalmologists. The false positive and false negative analysis indicated a direction of improvement. CONCLUSION: This is the first study to do automated standardised labelling on FFA images. Our model is able to be applied in clinical practice, and will make great contributions to the development of intelligent diagnosis of FFA images.
引用
- Gao Z, Pan X, Shao J, et al. Automatic interpretation and clinical evaluation for fundus fluorescein angiography images of diabetic retinopathy patients by deep learning. Br J Ophthalmol. 2023. PMID: 36171054. doi:10.1136/bjo-2022-321472
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。