文献速递眼底病与葡萄膜炎

条件生成对抗网络预测新生血管性年龄相关性黄斑变性治疗后OCT图像

POST-TREATMENT PREDICTION OF OPTICAL COHERENCE TOMOGRAPHY USING A CONDITIONAL GENERATIVE ADVERSARIAL NETWORK IN AGE-RELATED MACULAR DEGENERATION.
PubMed 文献 · Retina · 2021-01-01

结果显示预测图像对四种病变的准确度、特异度和阴性预测值范围分别为77.0-91.9%、94.1-95.1%和54.7-96.5%,联合FA和ICGA后分别提升至80.7-96.3%、97.3-99.0%和59.0-98.3%。

要点

  • 条件生成对抗网络可基于基线OCT生成治疗后OCT图像。
  • 联合FA和ICGA图像可提升预测准确度、特异度和阴性预测值。
  • 预测图像对IRF、SRF、PED和SHRM四种病变具有可接受的准确性。

核心结论

  • 条件生成对抗网络能够基于基线OCT、FA和ICGA图像生成治疗后OCT图像。

研究设计与样本

  • 使用来自241例患者723次扫描的15,183张增强配对OCT B扫描图像训练网络,图像为基线和抗VEGF治疗3次负荷剂量后1个月。
  • 网络还使用基线FA或ICGA图像联合基线OCT图像进行训练。
  • 测试集为50只眼的150张图像,评估预测视网膜内液、视网膜下液、PED和视网膜下高反射物质存在的能力。

主要发现

  • 基于基线OCT预测的图像对四种病变的准确度、特异度和阴性预测值范围分别为77.0-91.9%、94.1-95.1%和54.7-96.5%。
  • 联合FA和ICGA图像后,准确度、特异度和阴性预测值范围分别提升至80.7-96.3%、97.3-99.0%和59.0-98.3%。

关键数值与推荐

  • 预测图像对四种病变的准确度范围为77.0-91.9%(仅OCT)和80.7-96.3%(联合FA和ICGA)。
  • 特异度范围为94.1-95.1%(仅OCT)和97.3-99.0%(联合FA和ICGA)。
  • 阴性预测值范围为54.7-96.5%(仅OCT)和59.0-98.3%(联合FA和ICGA)。

临床怎么用

  • 该模型可辅助预测新生血管性年龄相关性黄斑变性患者抗VEGF治疗后的OCT表现。
  • 联合FA和ICGA图像可能提高预测准确性。

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 a deep learning model to generate posttreatment optical coherence tomography (OCT) images of neovascular age-related macular degeneration. METHODS: Two hundred ninety-eight patients with neovascular age-related macular degeneration were included. The conditional generative adversarial network was trained using 15,183 augmented paired OCT B-scan images obtained from 723 scans of 241 patients at baseline and 1 month after 3 loading doses of an anti-vascular endothelial growth factor treatment. The network was also trained using baseline fluorescein angiography (FA) or indocyanine green angiography (ICGA) images together with baseline OCT images. A test set of 150 images of 50 eyes was used to evaluate its ability to predict the presence of intraretinal fluid, subretinal fluid, PED, and subretinal hyperreflective material. Posttreatment OCT images were compared with images generated from baseline OCT with or without FA and indocyanine green angiography images. RESULTS: The predicted images inferred from baseline OCT images achieved an acceptable accuracy, specificity, and negative predictive value for four lesions (range: 77.0-91.9, 94.1-95.1, and 54.7-96.5%, respectively). The addition of both FA and indocyanine green angiography images improved the accuracy, specificity, and negative predictive value (range: 80.7-96.3, 97.3-99.0, and 59.0-98.3%, respectively). CONCLUSION: A conditional generative adversarial network is able to generate posttreatment OCT images from baseline OCT, FA, and indocyanine green angiography images.

来源:Retina,查看原文。版权归原作者所有。

引用

  1. Lee H, Kim S, Kim MA, et al. POST-TREATMENT PREDICTION OF OPTICAL COHERENCE TOMOGRAPHY USING A CONDITIONAL GENERATIVE ADVERSARIAL NETWORK IN AGE-RELATED MACULAR DEGENERATION. Retina. 2021. PMID: 32568984. doi:10.1097/IAE.0000000000002898

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。