Deep Learning for Prediction of AMD Progression: A Pilot Study
Deep Learning for Prediction of AMD Progression: A Pilot Study
复制标题
DOI：
10.1167/iovs.18-25325
复制
发表时间：
2019-02-01
影响因子：
4.4
通讯作者：
Sivaprasad, Sobha
中科院分区：
文献类型：
--
作者：
Russakoff, Daniel B.;Lamin, Ali;Sivaprasad, Sobha
目的.开发和评估一种使用光学相干断层扫描（OCT）成像和深度学习方法预测早期/中期至晚期湿性年龄相关性黄斑变性（AMD）转化可能性的方法。71例确诊为早期/中期AMD伴对侧湿性AMD的患者的71只眼睛在2年内（基线、第1年、第2年）接受了3次OCT成像。这些眼睛被分为两组：在第2年未转化为湿性AMD的眼睛（n = 40）和已转化为湿性AMD的眼睛（n = 31）。使用基线OCT数据的5倍交叉验证评估了两个深度卷积神经网络（CNN），以尝试预测哪些眼睛将在第2年转化为晚期AMD：（1）VGG 16，一种用于图像识别的流行CNN被微调，以及（2）从头开始训练一种新的简化CNN架构。预处理以基于分割的标准化的形式添加，以减少数据的方差并提高性能。我们的新架构，AMDnet，与预处理，实现了0.89的受试者工作特征（ROC）曲线（AUC）下的面积在B扫描水平和0.91卷。VGG 16是一种已建立的CNN架构，具有预处理的结果为B扫描0.82/体积0.87，而B扫描0.66/体积0.69。具有基于层分割的预处理的CNN对早期/中期AMD向晚期AMD的进展显示出强大的预测能力。使用的预处理，以提高性能，无论网络架构。
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.