使用光学相干断层扫描测量青光眼视网膜神经纤维层厚度时自动分割的错误
这项横断面研究纳入213名青光眼或疑似青光眼患者的412只眼共3490次扫描,比较仅自动分割与手动修正后视网膜神经纤维层厚度及青光眼分类的差异。结果显示仅自动分割使整体视网膜神经纤维层厚度薄1.6微米(P<.001),并高估青光眼分类,8.5%扫描的分类发生改变。作者建议在青光眼管理中应检查和手动修正光学相干断层扫描的视网膜层分割。
要点
- 仅自动分割较手动修正使整体视网膜神经纤维层厚度薄1.6微米(P<.001)。
- 手动修正使3486次扫描中298次(8.5%)的整体青光眼分类发生改变。
- 617次临界分类中146次(23.7%)经手动修正变为正常。
核心结论
- 不进行手动修正的自动分割导致整体视网膜神经纤维层厚度降低并高估青光眼分类。
- 视网膜神经纤维层较薄、年龄较大和扫描质量下降时差异增大。
- 作者建议在青光眼管理中评估视网膜神经纤维层厚度时,操作者应检查和手动修正光学相干断层扫描的视网膜层分割。
研究设计与样本
- 横断面研究,设置于青光眼临床实践。
- 数据集包括213名诊断为青光眼或疑似青光眼个体的412只眼的3490次扫描。
- 使用谱域光学相干断层扫描(Spectralis)在6度视乳头周围圆周测量视网膜神经纤维层厚度,导出仅自动分割结果及手动修正后的结果。
主要发现
- 仅自动分割较手动修正使整体视网膜神经纤维层厚度薄1.6微米(P<.001)。
- 按操作者调整后,多变量模型显示差异随视网膜神经纤维层厚度降低(P<.001)、扫描质量下降(P<.001)和年龄增加(P<.03)而增大。
- 手动修正使3486次扫描中298次(8.5%)的整体青光眼分类发生改变,其中617次临界分类中146次(23.7%)变为正常。
- 上方和下方颞侧时钟小时的差异最大。
关键数值与推荐
- 整体视网膜神经纤维层厚度差异:仅自动分割较手动修正薄1.6微米(P<.001)。
- 整体青光眼分类改变:3486次扫描中298次(8.5%)。
- 临界分类转为正常:617次中146次(23.7%)。
临床怎么用
- 作者建议在青光眼管理中评估视网膜神经纤维层厚度时,操作者应检查和手动修正光学相干断层扫描的视网膜层分割。
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 characterize the error of optical coherence tomography (OCT) measurements of retinal nerve fiber layer (RNFL) thickness when using automated retinal layer segmentation algorithms without manual refinement. DESIGN: Cross-sectional study. METHODS: This study was set in a glaucoma clinical practice, and the dataset included 3490 scans from 412 eyes of 213 individuals with a diagnosis of glaucoma or glaucoma suspect. We used spectral domain OCT (Spectralis) to measure RNFL thickness in a 6-degree peripapillary circle, and exported the native "automated segmentation only" results. In addition, we exported the results after "manual refinement" to correct errors in the automated segmentation of the anterior (internal limiting membrane) and the posterior boundary of the RNFL. Our outcome measures included differences in RNFL thickness and glaucoma classification (i.e., normal, borderline, or outside normal limits) between scans with automated segmentation only and scans using manual refinement. RESULTS: Automated segmentation only resulted in a thinner global RNFL thickness (1.6 μm thinner, P < .001) when compared to manual refinement. When adjusted by operator, a multivariate model showed increased differences with decreasing RNFL thickness (P < .001), decreasing scan quality (P < .001), and increasing age (P < .03). Manual refinement changed 298 of 3486 (8.5%) of scans to a different global glaucoma classification, wherein 146 of 617 (23.7%) of borderline classifications became normal. Superior and inferior temporal clock hours had the largest differences. CONCLUSIONS: Automated segmentation without manual refinement resulted in reduced global RNFL thickness and overestimated the classification of glaucoma. Differences increased in eyes with a thinner RNFL thickness, older age, and decreased scan quality. Operators should inspect and manually refine OCT retinal layer segmentation when assessing RNFL thickness in the management of patients with glaucoma.
引用
- Mansberger SL, Menda SA, Fortune BA, et al. Automated Segmentation Errors When Using Optical Coherence Tomography to Measure Retinal Nerve Fiber Layer Thickness in Glaucoma. Am J Ophthalmol. 2016. PMID: 27818206. doi:10.1016/j.ajo.2016.10.020
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。