深度学习与迁移学习基于黄斑OCT图像准确诊断早期青光眼
本研究构建并评估深度学习模型,利用谱域OCT黄斑区视网膜神经纤维层和神经节细胞复合层厚度诊断早期开角型青光眼。多机构数据经预训练和二次训练后,测试集诊断准确率AROC达93.7%,显著优于随机森林(82.0%)和支持向量机(67.4%),且预训练过程对性能至关重要。
要点
- 深度学习模型基于黄斑OCT厚度图诊断早期青光眼,AROC达93.7%。
- 去除预训练后AROC显著降至76.6%–78.8%,预训练提升性能。
- 模型性能优于随机森林(82.0%)和支持向量机(67.4%)。
核心结论
- 深度学习模型利用谱域OCT黄斑厚度图诊断早期青光眼,诊断性能显著提升。
研究设计与样本
- 多机构人工智能诊断工具开发、评估与比较研究。
- 预训练数据含4316张OCT图像(RS3000),来自1371只开角型青光眼眼和193只正常眼。
- 训练数据含94例早期开角型青光眼患者(平均偏差>-5.0 dB)的94只眼和84例正常人的84只眼。
- 测试数据含114例早期开角型青光眼患者(平均偏差>-5.0 dB)的114只眼和82例正常人的82只眼。
- 深度学习(卷积神经网络)分类器先经预训练数据集训练,再用独立训练数据集进行第二轮训练。
主要发现
- 深度学习模型的AROC为93.7%。
- 无预训练过程时,AROC显著降至76.6%至78.8%之间。
- 随机森林模型AROC为82.0%,支持向量机模型AROC为67.4%,均显著低于深度学习模型。
临床怎么用
- 基于黄斑OCT厚度图的深度学习模型可用于辅助诊断早期开角型青光眼。
- 预训练是提升模型诊断性能的关键步骤,临床部署时应保留。
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: We sought to construct and evaluate a deep learning (DL) model to diagnose early glaucoma from spectral-domain optical coherence tomography (OCT) images. DESIGN: Artificial intelligence diagnostic tool development, evaluation, and comparison. METHODS: This multi-institution study included pretraining data of 4316 OCT images (RS3000) from 1371 eyes with open angle glaucoma (OAG) regardless of the stage of glaucoma and 193 normal eyes. Training data included OCT-1000/2000 images from 94 eyes of 94 patients with early OAG (mean deviation > -5.0 dB) and 84 eyes of 84 normal subjects. Testing data included OCT-1000/2000 from 114 eyes of 114 patients with early OAG (mean deviation > -5.0 dB) and 82 eyes of 82 normal subjects. A DL (convolutional neural network) classifier was trained using a pretraining dataset, followed by a second round of training using an independent training dataset. The DL model input features were the 8 × 8 grid macular retinal nerve fiber layer thickness and ganglion cell complex layer thickness from spectral-domain OCT. Diagnostic accuracy was investigated in the testing dataset. For comparison, diagnostic accuracy was also evaluated using the random forests and support vector machine models. The primary outcome measure was the area under the receiver operating characteristic curve (AROC). RESULTS: The AROC with the DL model was 93.7%. The AROC significantly decreased to between 76.6% and 78.8% without the pretraining process. Significantly smaller AROCs were obtained with random forests and support vector machine models (82.0% and 67.4%, respectively). CONCLUSION: A DL model for glaucoma using spectral-domain OCT offers a substantive increase in diagnostic performance.
引用
- Asaoka R, Murata H, Hirasawa K, et al. Using Deep Learning and Transfer Learning to Accurately Diagnose Early-Onset Glaucoma From Macular Optical Coherence Tomography Images. Am J Ophthalmol. 2018. PMID: 30316669. doi:10.1016/j.ajo.2018.10.007
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。