利用深度学习和基线与纵向结构测量预测视野进展
该研究纳入3,079只眼(1,765例患者),利用基线与系列视盘照片及视网膜神经纤维层厚度构建深度学习模型预测视野进展,基线模型AUC为0.813,加入第二、三次视盘照片后AUC分别升至0.860和0.894,在另一OCT设备数据集上AUC为0.893。
要点
- 基线视盘照片联合RNFL厚度预测视野进展的AUC为0.813(95%CI 0.757-0.869)。
- 加入第二、三次视盘照片后AUC分别升至0.860和0.894(p<0.027)。
- 预测快速进展(MD年变化率<1.0 dB/年)时AUC最高,达0.911。
核心结论
- 深度学习模型利用基线RNFL厚度和系列视盘照片能以临床相关准确度预测视野进展,进一步验证后可作为临床工具实施。
研究设计与样本
- 开发预测视野进展的深度学习算法,纳入来自三级学术中心的3,079只眼(1,765例患者),涵盖各类青光眼,要求≥5次视野检查且随访≥3年。
- 以线性回归估算系列视野平均偏差(MD)变化率,视野进展定义为MD斜率为负且p<0.05。
- 采用以ResNet-152为骨干、经ImageNet预训练的孪生神经网络,利用系列视盘照片和基线RNFL厚度预测视野进展。
- 在另一数据集(427只眼)上测试模型,该数据集RNFL数据来自不同OCT设备。
- 主要结局指标为ROC曲线下面积(AUC)。
主要发现
- 基线平均(SD)MD为3.4(4.9)dB,900只眼(29%)检测到视野进展。
- 纳入基线视盘照片和RNFL厚度的模型AUC(95%CI)为0.813(0.757-0.869)。
- 加入第二和第三次视盘照片后,AUC分别增至0.860和0.894(p<0.027)。
- 该模型预测快速进展(MD年变化率<1.0 dB/年)的AUC最高,为0.911。
- 应用于使用另一OCT设备RNFL数据的第二数据集时,模型性能相似,AUC=0.893(95%CI 0.837-0.948)。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
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: Identifying glaucoma patients at high risk of progression based on widely available structural data is an unmet task in clinical practice. We test the hypothesis that baseline or serial structural measures can predict visual field (VF) progression with deep learning (DL). DESIGN: Development of a DL algorithm to predict VF progression. METHODS: 3,079 eyes (1,765 patients) with various types of glaucoma and ≥5 VFs, and ≥3 years of follow-up from a tertiary academic center were included. Serial VF mean deviation (MD) rates of change were estimated with linear-regression. VF progression was defined as negative MD slope with p<0.05. A Siamese Neural Network with ResNet-152 backbone pre-trained on ImageNet was designed to predict VF progression using serial optic-disc photographs (ODP), and baseline retinal nerve fiber layer (RNFL) thickness. We tested the model on a separate dataset (427 eyes) with RNFL data from different OCT. The Main Outcome Measure was Area under ROC curve (AUC). RESULTS: Baseline average (SD) MD was 3.4 (4.9)dB. VF progression was detected in 900 eyes (29%). AUC (95% CI) for model incorporating baseline ODP and RNFL thickness was 0.813 (0.757-0.869). After adding the second and third ODPs, AUC increased to 0.860 and 0.894, respectively (p<0.027). This model also had highest AUC (0.911) for predicting fast progression (MD rate <1.0 dB/year). Model's performance was similar when applied to second dataset using RNFL data from another OCT device (AUC=0.893; 0.837-0.948). CONCLUSIONS: DL model predicted VF progression with clinically relevant accuracy using baseline RNFL thickness and serial ODPs and can be implemented as a clinical tool after further validation.
引用
- Mohammadzadeh V, Wu S, Besharati S, et al. Prediction of Visual Field Progression with Baseline and Longitudinal Structural Measurements Using Deep Learning. Am J Ophthalmol. 2024. PMID: 38354971. doi:10.1016/j.ajo.2024.02.007
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。