无监督机器学习识别SS-OCT视网膜神经纤维层特征可预测青光眼进展
研究对28名健康者(56眼)和93名青光眼患者(179眼)每3个月进行广角SS-OCT、SD-OCT视盘周围RNFL环扫、SAP和FDT检查,持续2年。采用主成分分析的无监督机器学习从RNFL厚度图提取结构特征,其检测青光眼的AUC为0.95,预测进展的准确性显著高于SAP MD、FDT MD和平均cpRNFLt。
要点
- RNFL PCA特征与SAP MD(R2=0.49)、FDT MD(R2=0.48)和平均cpRNFLt(R2=0.58)显著相关。
- 检测青光眼AUC:RNFL PCA 0.95 vs 平均cpRNFLt 0.90(P=0.09)、SAP MD 0.86(P=0.034)、FDT MD 0.83(P=0.021)。
- 预测进展准确性RNFL PCA显著高于SAP MD(P=0.046)、FDT MD(P=0.007)和平均cpRNFLt(P=0.044)。
核心结论
- 计算方法可识别改善青光眼检测和进展预测的结构特征。
研究设计与样本
- 队列纳入28名健康参与者(56眼)和93名青光眼参与者(179眼),每3个月完成广角SS-OCT、SD-OCT cpRNFL环扫、SAP和FDT,持续2年。
- 从分割的SS-OCT图像提取RNFL厚度图,采用基于主成分分析的无监督机器学习识别新结构特征。
主要发现
- RNFL PCA特征与SAP MD(R2=0.49,P<0.0001)、FDT MD(R2=0.48,P<0.0001)和SD-OCT平均cpRNFLt(R2=0.58,P<0.0001)显著相关。
- 检测青光眼AUC:RNFL PCA 0.95 vs 平均cpRNFLt 0.90(P=0.09)、SAP MD 0.86(P=0.034)、FDT MD 0.83(P=0.021)。
- 预测进展准确性RNFL PCA显著高于SAP MD(P=0.046)、FDT MD(P=0.007)和平均cpRNFLt(P=0.044)。
关键数值与推荐
- RNFL PCA检测青光眼AUC为0.95,平均cpRNFLt为0.90,SAP MD为0.86,FDT MD为0.83。
- RNFL PCA预测进展准确性较SAP MD(P=0.046)、FDT MD(P=0.007)和平均cpRNFLt(P=0.044)显著更高。
临床怎么用
- 基于广角SS-OCT的无监督机器学习RNFL特征可能有助于青光眼检测和进展预测。
局限性
- 原文未述局限性
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 apply computational techniques to wide-angle swept-source optical coherence tomography (SS-OCT) images to identify novel, glaucoma-related structural features and improve detection of glaucoma and prediction of future glaucomatous progression. METHODS: Wide-angle SS-OCT, OCT circumpapillary retinal nerve fiber layer (cpRNFL) circle scans spectral-domain (SD)-OCT, standard automated perimetry (SAP), and frequency doubling technology (FDT) visual field tests were completed every 3 months for 2 years from a cohort of 28 healthy participants (56 eyes) and 93 glaucoma participants (179 eyes). RNFL thickness maps were extracted from segmented SS-OCT images and an unsupervised machine learning approach based on principal component analysis (PCA) was used to identify novel structural features. Area under the receiver operating characteristic curve (AUC) was used to assess diagnostic accuracy of RNFL PCA for detecting glaucoma and progression compared to SAP, FDT, and cpRNFL measures. RESULTS: The RNFL PCA features were significantly associated with mean deviation (MD) in both SAP (R2 = 0.49, P < 0.0001) and FDT visual field testing (R2 = 0.48, P < 0.0001), and with mean circumpapillary RNFL thickness (cpRNFLt) from SD-OCT (R2 = 0.58, P < 0.0001). The identified features outperformed each of these measures in detecting glaucoma with an AUC of 0.95 for RNFL PCA compared to an 0.90 for mean cpRNFLt (P = 0.09), 0.86 for SAP MD (P = 0.034), and 0.83 for FDT MD (P = 0.021). Accuracy in predicting progression was also significantly higher for RNFL PCA compared to SAP MD, FDT MD, and mean cpRNFLt (P = 0.046, P = 0.007, and P = 0.044, respectively). CONCLUSIONS: A computational approach can identify structural features that improve glaucoma detection and progression prediction.
引用
- Christopher M, Belghith A, Weinreb RN, et al. Retinal Nerve Fiber Layer Features Identified by Unsupervised Machine Learning on Optical Coherence Tomography Scans Predict Glaucoma Progression. Invest Ophthalmol Vis Sci. 2018. PMID: 29860461. doi:10.1167/iovs.17-23387
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。