进展还是衰老?一种深度学习区分青光眼进展与OCT扫描中年龄相关变化的方法
在特异性均衡至95%时,深度学习模型的命中率为0.498,高于最小二乘回归的0.284(P < .001)。
要点
- 深度学习模型利用OCT B扫描序列识别青光眼性结构进展,并校正年龄相关变化。
- 特异性95%时,深度学习命中率0.498,最小二乘回归命中率0.284,差异有统计学意义(P < .001)。
- 研究纳入3253只眼(1859名受试者),平均随访3.5±1.6年。
核心结论
- 深度学习模型能够利用替代参考标准识别OCT B扫描中的纵向青光眼性结构变化。
研究设计与样本
- 回顾性队列研究,纳入具有≥5次可靠视盘周围OCT(Spectralis,Heidelberg Engineering)环形扫描的青光眼眼与健康眼。
- 开发了弱监督时间序列学习模型噪声正-未标记(Noise-PU)深度学习,采用两种学习方案:一种通过区分青光眼与健康眼的测试序列识别年龄相关变化,另一种基于青光眼眼打乱OCT识别重测变异性。
- 两种模型均以卷积神经网络(CNN)和长短期记忆(LSTM)网络为基础,组合成CNN-LSTM模型,特征联合训练以识别青光眼进展并考虑年龄相关损失。
主要发现
- 在测试样本中,当特异性均衡至95%时,深度学习方法的命中率为0.498(95%CI:0.470-0.526),普通最小二乘(OLS)回归的命中率为0.284(95%CI:0.258-0.309),差异有统计学意义(P < .001)。
- 命中率被用作敏感性的替代指标。
关键数值与推荐
- 深度学习模型命中率0.498(95%CI:0.470-0.526) vs OLS回归命中率0.284(95%CI:0.258-0.309),特异性均衡至95%,P < .001。
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: To develop deep learning (DL) algorithm to detect glaucoma progression using optical coherence tomography (OCT) images, in the absence of a reference standard. DESIGN: Retrospective cohort study. METHODS: Glaucomatous and healthy eyes with ≥5 reliable peripapillary OCT (Spectralis, Heidelberg Engineering) circle scans were included. A weakly supervised time-series learning model, called noise positive-unlabeled (Noise-PU) DL was developed to classify whether sequences of OCT B-scans showed glaucoma progression. The model used 2 learning schemes, one to identify age-related changes by differentiating test sequences from glaucoma vs healthy eyes, and the other to identify test-retest variability based on scrambled OCTs of glaucoma eyes. Both models' bases were convolutional neural networks (CNN) and long short-term memory (LSTM) networks which were combined to form a CNN-LSTM model. Model features were combined and jointly trained to identify glaucoma progression, accounting for age-related loss. The DL model's outcomes were compared with ordinary least squares (OLS) regression of retinal nerve fiber layer (RNFL) thickness over time, matched for specificity. The hit ratio was used as a proxy for sensitivity. RESULTS: Eight thousand seven hundred eighty-five follow-up sequences of 5 consecutive OCT tests from 3253 eyes (1859 subjects) were included in the study. The mean follow-up time was 3.5 ± 1.6 years. In the test sample, the hit ratios of the DL and OLS methods were 0.498 (95%CI: 0.470-0.526) and 0.284 (95%CI: 0.258-0.309) respectively (P < .001) when the specificities were equalized to 95%. CONCLUSION: A DL model was able to identify longitudinal glaucomatous structural changes in OCT B-scans using a surrogate reference standard for progression.
引用
- Mandal S, Jammal AA, Malek D, et al. Progression or Aging? A Deep Learning Approach for Distinguishing Glaucoma Progression From Age-Related Changes in OCT Scans. Am J Ophthalmol. 2024. PMID: 38703802. doi:10.1016/j.ajo.2024.04.030
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。