深度学习卷积神经网络自动检测早期早产儿视网膜病变
模型采用五折交叉验证,测试平均准确率92.23%±1.39,在区分无ROP与ROP、1期与无ROP及2期、2期与无ROP及1期时敏感度和特异度分别为96.14%±0.87和95.95%±0.48、91.82%±2.03和94.50%±0.71、89.81%±1.82和98.99%±0.40。结论认为该系统能准确区分ROP早期分期,有望辅助眼科医生早期分类。
要点
- 深度CNN在测试集区分无ROP与ROP的敏感度96.14%±0.87、特异度95.95%±0.48。
- 区分1期ROP与无ROP及2期时敏感度91.82%±2.03、特异度94.50%±0.71。
- 区分2期ROP与无ROP及1期时敏感度89.81%±1.82、特异度98.99%±0.40。
核心结论
- 所提出的系统能准确区分ROP早期分期,具有辅助眼科医生早期分类ROP的潜力。
研究设计与样本
- 回顾性横断面研究,在台湾一家转诊医学中心纳入无ROP、1期ROP或2期ROP的早产儿。
- 采用敏感度、特异度和受试者工作特征曲线下面积评估算法相对于参考标准诊断的性能。
主要发现
- 模型采用五折交叉验证训练,训练平均准确率99.93%±0.03,测试平均准确率92.23%±1.39。
- 预测无ROP与ROP时,敏感度96.14%±0.87、特异度95.95%±0.48。
- 预测1期ROP与无ROP及2期时,敏感度91.82%±2.03、特异度94.50%±0.71。
- 预测2期ROP与无ROP及1期时,敏感度89.81%±1.82、特异度98.99%±0.40。
临床怎么用
- 该CNN系统可用于辅助眼科医生对早产儿视网膜病变进行早期分期分类。
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/AIM: To automatically detect and classify the early stages of retinopathy of prematurity (ROP) using a deep convolutional neural network (CNN). METHODS: This retrospective cross-sectional study was conducted in a referral medical centre in Taiwan. Only premature infants with no ROP, stage 1 ROP or stage 2 ROP were enrolled. Overall, 11 372 retinal fundus images were compiled and split into 10 235 images (90%) for training, 1137 (10%) for validation and 244 for testing. A deep CNN was implemented to classify images according to the ROP stage. Data were collected from December 17, 2013 to May 24, 2019 and analysed from December 2018 to January 2020. The metrics of sensitivity, specificity and area under the receiver operating characteristic curve were adopted to evaluate the performance of the algorithm relative to the reference standard diagnosis. RESULTS: The model was trained using fivefold cross-validation, yielding an average accuracy of 99.93%±0.03 during training and 92.23%±1.39 during testing. The sensitivity and specificity scores of the model were 96.14%±0.87 and 95.95%±0.48, 91.82%±2.03 and 94.50%±0.71, and 89.81%±1.82 and 98.99%±0.40 when predicting no ROP versus ROP, stage 1 ROP versus no ROP and stage 2 ROP, and stage 2 ROP versus no ROP and stage 1 ROP, respectively. CONCLUSIONS: The proposed system can accurately differentiate among ROP early stages and has the potential to help ophthalmologists classify ROP at an early stage.
引用
- Huang YP, Basanta H, Kang EY, et al. Automated detection of early-stage ROP using a deep convolutional neural network. Br J Ophthalmol. 2020. PMID: 32830123. doi:10.1136/bjophthalmol-2020-316526
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。