文献速递青光眼

深度学习图像分析光学相干断层扫描血管成像测量的血管密度改善健康眼与青光眼的分类

Deep Learning Image Analysis of Optical Coherence Tomography Angiography Measured Vessel Density Improves Classification of Healthy and Glaucoma Eyes.
PubMed 文献 · Am J Ophthalmol · 2021-11-13

本研究比较卷积神经网络(CNN)分析en face血管密度图像与梯度提升分类器(GBC)分析OCTA血管密度及OCT视网膜神经纤维层厚度对健康眼与青光眼的分类性能,共纳入80名健康者130眼和185例青光眼患者275眼。CNN的调整AUPRC为0.97,显著优于各GBC模型(P≤0.01)。

要点

  • CNN分析en face血管密度图像的调整AUPRC为0.97(95%CI 0.95,0.99)。
  • GBC基于OCTA血管密度的调整AUPRC为0.89~0.91,基于RNFL厚度的为0.93。
  • CNN分类性能显著优于所有GBC模型(P≤0.01)。

核心结论

  • 深度学习en face图像分析在健康眼与青光眼分类上优于基于特征的GBC模型。

研究设计与样本

  • 研究纳入80名健康者130眼和185例青光眼患者275眼,均行视神经乳头OCTA和OCT成像。
  • 采用VGG16 CNN在完整的en face 4.5×4.5-mm径向视乳头周围毛细血管OCTA视神经乳头图像上训练和测试。
  • 另分别训练和测试基于OCTA及OCT测量值的GBC模型,采用五折交叉验证评估预测。
  • 计算精确率-召回率曲线下面积(AUPRC)以控制训练/测试集大小不均衡,并进行比较。

主要发现

  • 全图像血管密度GBC的调整AUPRC为0.89(95%CI 0.82,0.92)。
  • 全图像毛细血管密度GBC的调整AUPRC为0.89(95%CI 0.83,0.92)。
  • 全图像血管密度联合全图像毛细血管密度GBC的调整AUPRC为0.91(95%CI 0.88,0.93)。
  • RNFL厚度GBC的调整AUPRC为0.93(95%CI 0.91,0.95)。
  • CNN分析en face血管密度图像的调整AUPRC为0.97(95%CI 0.95,0.99),显著优于所有GBC比较(P≤0.01)。

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 compare convolutional neural network (CNN) analysis of en face vessel density images to gradient boosting classifier (GBC) analysis of instrument-provided, feature-based optical coherence tomography angiography (OCTA) vessel density measurements and OCT retinal nerve fiber layer (RNFL) thickness measurements for classifying healthy and glaucomatous eyes. DESIGN: Comparison of diagnostic approaches. METHODS: A total of 130 eyes of 80 healthy individuals and 275 eyes of 185 glaucoma patients with optic nerve head (ONH) OCTA and OCT imaging were included. Classification performance of a VGG16 CNN trained and tested on entire en face 4.5 × 4.5-mm radial peripapillary capillary OCTA ONH images was compared to the performance of separate GBC models trained and tested on standard OCTA and OCT measurements. Five-fold cross-validation was used to test predictions for CNNs and GBCs. Areas under the precision recall curves (AUPRC) were calculated to control for training/test set size imbalance and were compared. RESULTS: Adjusted AUPRCs for GBC models were 0.89 (95% CI = 0.82, 0.92) for whole image vessel density GBC, 0.89 (0.83, 0.92) for whole image capillary density GBC, 0.91 (0.88, 0.93) for combined whole image vessel and whole image capillary density GBC, and 0.93 (0.91, 095) for RNFL thickness GBC. The adjusted AUPRC using CNN analysis of en face vessel density images was 0.97 (0.95, 0.99) resulting in significantly improved classification compared to GBC OCTA-based results and GBC OCT-based results (P ≤ 0.01 for all comparisons). CONCLUSION: Deep learning en face image analysis improves on feature-based GBC models for classifying healthy and glaucoma eyes.

来源:Am J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Bowd C, Belghith A, Zangwill LM, et al. Deep Learning Image Analysis of Optical Coherence Tomography Angiography Measured Vessel Density Improves Classification of Healthy and Glaucoma Eyes. Am J Ophthalmol. 2021. PMID: 34780803. doi:10.1016/j.ajo.2021.11.008

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。