深度学习预测AMD进展的初步研究
该初步研究纳入71例确诊早期/中期AMD且对侧眼为湿性AMD的患者(共71眼),在2年内进行3次OCT成像,采用两种深度卷积神经网络基于基线OCT数据预测2年后是否转为晚期AMD。新架构AMDnet结合分割归一化预处理后,B扫描水平AUC为0.89、体积水平为0.91。
要点
- AMDnet结合预处理在B扫描水平AUC达0.89、体积水平达0.91。
- VGG16结合预处理B扫描AUC为0.82、体积为0.87,无预处理仅0.66/0.69。
- 分割归一化预处理可提升不同网络架构的预测性能。
核心结论
- 结合基于层分割预处理的卷积神经网络对早期/中期AMD进展为晚期AMD具有较强预测能力。
- 无论采用何种网络架构,使用该预处理均能改善预测性能。
研究设计与样本
- 回顾性分析71例确诊早期/中期AMD且对侧眼为湿性AMD患者的71眼,2年内行3次OCT成像(基线、第1年、第2年)。
- 按第2年是否转为湿性AMD分为未转化组(n=40)与转化组(n=31)。
- 采用两种深度卷积神经网络(VGG16微调与新型简化CNN架构AMDnet)基于基线OCT数据进行5折交叉验证。
主要发现
- AMDnet结合预处理在B扫描水平的AUC为0.89,体积水平为0.91。
- VGG16结合预处理B扫描AUC为0.82、体积为0.87,无预处理时分别为0.66与0.69。
关键数值与推荐
- AMDnet结合预处理:B扫描水平AUC 0.89,体积水平AUC 0.91。
- VGG16结合预处理:B扫描水平AUC 0.82,体积水平AUC 0.87;无预处理:B扫描0.66,体积0.69。
临床怎么用
- 提示基于基线OCT的深度学习模型可辅助识别早期/中期AMD中高进展风险者,分割归一化预处理值得在建模中采用。
- 本研究为初步探索,样本量有限,尚不能直接用于临床决策。
局限性
- 为初步研究,样本量仅71眼,需更大样本验证。
- 仅评估两种网络架构与基线OCT数据,未涉及其他影像模态或外部验证。
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: To develop and assess a method for predicting the likelihood of converting from early/intermediate to advanced wet age-related macular degeneration (AMD) using optical coherence tomography (OCT) imaging and methods of deep learning. METHODS: Seventy-one eyes of 71 patients with confirmed early/intermediate AMD with contralateral wet AMD were imaged with OCT three times over 2 years (baseline, year 1, year 2). These eyes were divided into two groups: eyes that had not converted to wet AMD (n = 40) at year 2 and those that had (n = 31). Two deep convolutional neural networks (CNN) were evaluated using 5-fold cross validation on the OCT data at baseline to attempt to predict which eyes would convert to advanced AMD at year 2: (1) VGG16, a popular CNN for image recognition was fine-tuned, and (2) a novel, simplified CNN architecture was trained from scratch. Preprocessing was added in the form of a segmentation-based normalization to reduce variance in the data and improve performance. RESULTS: Our new architecture, AMDnet, with preprocessing, achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.89 at the B-scan level and 0.91 for volumes. Results for VGG16, an established CNN architecture, with preprocessing were 0.82 for B-scans/0.87 for volumes versus 0.66 for B-scans/0.69 for volumes without preprocessing. CONCLUSIONS: A CNN with layer segmentation-based preprocessing shows strong predictive power for the progression of early/intermediate AMD to advanced AMD. Use of the preprocessing was shown to improve performance regardless of the network architecture.
引用
- Russakoff DB, Lamin A, Oakley JD, et al. Deep Learning for Prediction of AMD Progression: A Pilot Study. Invest Ophthalmol Vis Sci. 2019. PMID: 30786275. doi:10.1167/iovs.18-25325
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。