文献速递青光眼眼底病与葡萄膜炎神经眼科

一种对视盘光学相干断层扫描图像进行数字染色的深度学习方法

A Deep Learning Approach to Digitally Stain Optical Coherence Tomography Images of the Optic Nerve Head.
PubMed 文献 · Invest Ophthalmol Vis Sci · 2018-01-01

本研究开发了一种深度学习网络,对100名受试者(40名健康者与60名青光眼患者)单眼的视盘OCT水平B扫描图像(经自适应补偿增强)进行数字染色,以突出视盘六种组织层。算法在未参与训练的图像上数字染色各组织的平均戴斯系数为0.84±0.03,敏感度为0.92±0.03,特异度为0.99±0.00,交并比为0.89±0.03,准确率为0.94±0.02,且使用补偿图像训练时性能显著更优(P<0.001)。

要点

  • 深度学习网络可同时染色视盘的神经与结缔组织,在健康者和青光眼患者OCT图像上均表现良好。
  • 各组织平均戴斯系数0.84±0.03、敏感度0.92±0.03、特异度0.99±0.00、交并比0.89±0.03、准确率0.94±0.02。
  • 使用补偿图像训练时算法性能显著优于未补偿图像(P<0.001)。

核心结论

  • 该深度学习算法能同时染色视盘的神经与结缔组织,为自动测量视盘多项关键结构参数提供了框架,这些参数可能对改善青光眼管理至关重要。

研究设计与样本

  • 研究纳入100名受试者(40名健康者与60名青光眼患者),每名受试者取单眼,使用Spectralis OCT采集通过视盘中心的水平B扫描图像。
  • 所有图像经自适应补偿增强,并设计定制深度学习网络用补偿后图像训练,以数字染色视盘六种组织层。
  • 算法准确性对照人工分割,采用戴斯系数、敏感度、特异度、交并比和准确率评估,并分析补偿、训练图像数量及青光眼与健康受试者间性能比较的影响。

主要发现

  • 在未参与评估的图像上,算法能数字染色视网膜神经纤维层+前筛板、RPE、所有其他视网膜层、脉络膜以及视盘周围巩膜和筛板。
  • 所有组织的平均戴斯系数为0.84±0.03,敏感度为0.92±0.03,特异度为0.99±0.00,交并比为0.89±0.03,准确率为0.94±0.02。
  • 使用补偿图像训练时算法性能显著更好(P<0.001)。
  • 数字染色在青光眼和健康个体的OCT图像上均表现良好。

关键数值与推荐

  • 所有组织的平均戴斯系数为0.84±0.03,敏感度为0.92±0.03,特异度为0.99±0.00,交并比为0.89±0.03,准确率为0.94±0.02。
  • 使用补偿图像训练时算法性能显著更好(P<0.001)。

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 a deep learning approach to digitally stain optical coherence tomography (OCT) images of the optic nerve head (ONH). METHODS: A horizontal B-scan was acquired through the center of the ONH using OCT (Spectralis) for one eye of each of 100 subjects (40 healthy and 60 glaucoma). All images were enhanced using adaptive compensation. A custom deep learning network was then designed and trained with the compensated images to digitally stain (i.e., highlight) six tissue layers of the ONH. The accuracy of our algorithm was assessed (against manual segmentations) using the dice coefficient, sensitivity, specificity, intersection over union (IU), and accuracy. We studied the effect of compensation, number of training images, and performance comparison between glaucoma and healthy subjects. RESULTS: For images it had not yet assessed, our algorithm was able to digitally stain the retinal nerve fiber layer + prelamina, the RPE, all other retinal layers, the choroid, and the peripapillary sclera and lamina cribrosa. For all tissues, the dice coefficient, sensitivity, specificity, IU, and accuracy (mean) were 0.84 ± 0.03, 0.92 ± 0.03, 0.99 ± 0.00, 0.89 ± 0.03, and 0.94 ± 0.02, respectively. Our algorithm performed significantly better when compensated images were used for training (P < 0.001). Besides offering a good reliability, digital staining also performed well on OCT images of both glaucoma and healthy individuals. CONCLUSIONS: Our deep learning algorithm can simultaneously stain the neural and connective tissues of the ONH, offering a framework to automatically measure multiple key structural parameters of the ONH that may be critical to improve glaucoma management.

来源:Invest Ophthalmol Vis Sci,查看原文。版权归原作者所有。

引用

  1. Devalla SK, Chin KS, Mari JM, et al. A Deep Learning Approach to Digitally Stain Optical Coherence Tomography Images of the Optic Nerve Head. Invest Ophthalmol Vis Sci. 2018. PMID: 29313052. doi:10.1167/iovs.17-22617

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。