文献速递眼底病与葡萄膜炎

双模态深度卷积神经网络自动诊断年龄相关性黄斑变性与息肉状脉络膜血管病变

Automated diagnoses of age-related macular degeneration and polypoidal choroidal vasculopathy using bi-modal deep convolutional neural networks.
PubMed 文献 · Br J Ophthalmol · 2020-06-04

本研究基于北京协和医院患者的彩色眼底图像与OCT图像,构建双模态深度卷积神经网络(DCNN)框架,将图像分为正常、干性AMD、湿性AMD与PCV四类,并与三位视网膜专家独立诊断进行比较。在80只眼(每组20只眼)共143对图像的测试集上,双模态DCNN准确率87.4%、敏感度88.8%、特异度95.6%,与诊断金标准一致性Cohen's κ为0.828,略高于最佳专家(κ 0.810),识别PCV的表现亦优于最佳专家。

要点

  • 双模态DCNN在测试集上诊断AMD与PCV的准确率为87.4%、敏感度88.8%、特异度95.6%。
  • 模型与诊断金标准一致性Cohen's κ 0.828,略高于最佳专家(κ 0.810)。
  • 识别PCV时模型表现优于最佳专家,提示其在筛查与辅助诊断中的潜力。

核心结论

  • 双模态DCNN用于AMD与PCV的自动分类准确,在公共卫生领域具有应用前景。

研究设计与样本

  • 回顾性横断面研究,纳入就诊于北京协和医院的AMD或PCV患者,诊断由两位视网膜专家依据AMD与PCV诊断金标准确认。
  • 排除合并视网膜血管疾病的患者,采集散瞳后彩色眼底图像与频域OCT图像并匿名化处理。
  • 图像预标注为正常、干性AMD、湿性AMD或PCV,以ResNet-50为骨干网络,并构建随机森林分类器等替代机器学习模型作比较。
  • 同一参与者的所有图像仅出现在单一数据划分子集中;人机比较由三位视网膜专家在同一测试数据集上独立诊断。

主要发现

  • 测试集包含来自80只眼的143对眼底与OCT图像,每组20只眼。
  • 双模态DCNN表现最佳,准确率87.4%、敏感度88.8%、特异度95.6%。
  • 模型与诊断金标准一致性Cohen's κ 0.828,略高于最佳专家(Human1,κ 0.810)。
  • 识别PCV时,模型表现同样优于最佳专家。

关键数值与推荐

  • 测试集规模:143对眼底与OCT图像,来自80只眼,每组20只眼。
  • 双模态DCNN:准确率87.4%、敏感度88.8%、特异度95.6%。
  • 与诊断金标准一致性:Cohen's κ 0.828;最佳专家Cohen's κ 0.810。

临床怎么用

  • 该双模态DCNN可基于彩色眼底与OCT图像自动区分正常、干性AMD、湿性AMD与PCV,可作为辅助诊断与筛查工具参考。

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

AIMS: To investigate the efficacy of a bi-modality deep convolutional neural network (DCNN) framework to categorise age-related macular degeneration (AMD) and polypoidal choroidal vasculopathy (PCV) from colour fundus images and optical coherence tomography (OCT) images. METHODS: A retrospective cross-sectional study was proposed of patients with AMD or PCV who came to Peking Union Medical College Hospital. Diagnoses of all patients were confirmed by two retinal experts based on diagnostic gold standard for AMD and PCV. Patients with concurrent retinal vascular diseases were excluded. Colour fundus images and spectral domain OCT images were taken from dilated eyes of patients and healthy controls, and anonymised. All images were pre-labelled into normal, dry or wet AMD or PCV. ResNet-50 models were used as the backbone and alternate machine learning models including random forest classifiers were constructed for further comparison. For human-machine comparison, the same testing data set was diagnosed by three retinal experts independently. All images from the same participant were presented only within a single partition subset. RESULTS: On a test set of 143 fundus and OCT image pairs from 80 eyes (20 eyes per-group), the bi-modal DCNN demonstrated the best performance, with accuracy 87.4%, sensitivity 88.8% and specificity 95.6%, and a perfect agreement with diagnostic gold standard (Cohen's κ 0.828), exceeds slightly over the best expert (Human1, Cohen's κ 0.810). For recognising PCV, the model outperformed the best expert as well. CONCLUSION: A bi-modal DCNN for automated classification of AMD and PCV is accurate and promising in the realm of public health.

来源:Br J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Xu Z, Wang W, Yang J, et al. Automated diagnoses of age-related macular degeneration and polypoidal choroidal vasculopathy using bi-modal deep convolutional neural networks. Br J Ophthalmol. 2020. PMID: 32499330. doi:10.1136/bjophthalmol-2020-315817

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。