Hamilton Glaucoma Center, Shiley Eye Institute, The Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, CA, USA.
School of Medicine, University of Alabama-Birmingham, Birmingham, AL, USA.
Transl Vis Sci Technol. 2021 Jul 1;10(8):19. doi: 10.1167/tvst.10.8.19.
To compare change over time in eye-specific optical coherence tomography (OCT) retinal nerve fiber layer (RNFL)-based region-of-interest (ROI) maps developed using unsupervised deep-learning auto-encoders (DL-AE) to circumpapillary RNFL (cpRNFL) thickness for the detection of glaucomatous progression.
Forty-four progressing glaucoma eyes (by stereophotograph assessment), 189 nonprogressing glaucoma eyes (by stereophotograph assessment), and 109 healthy eyes were followed for ≥3 years with ≥4 visits using OCT. The San Diego Automated Layer Segmentation Algorithm was used to automatically segment the RNFL layer from raw three-dimensional OCT images. For each longitudinal series, DL-AEs were used to generate individualized eye-based ROI maps by identifying RNFL regions of likely progression and no change. Sensitivities and specificities for detecting change over time and rates of change over time were compared for the DL-AE ROI and global cpRNFL thickness measurements derived from a 2.22-mm to 3.45-mm annulus centered on the optic disc.
The sensitivity for detecting change in progressing eyes was greater for DL-AE ROIs than for global cpRNFL annulus thicknesses (0.90 and 0.63, respectively). The specificity for detecting not likely progression in nonprogressing eyes was similar (0.92 and 0.93, respectively). The mean rates of change in DL-AE ROI were significantly faster than for cpRNFL annulus thickness in progressing eyes (-1.28 µm/y vs. -0.83 µm/y) and nonprogressing eyes (-1.03 µm/y vs. -0.78 µm/y).
Eye-specific ROIs identified using DL-AE analysis of OCT images show promise for improving assessment of glaucomatous progression.
The detection and monitoring of structural glaucomatous progression can be improved by considering eye-specific regions of likely progression identified using deep learning.
比较使用无监督深度学习自动编码器（DL-AE）开发的基于眼部特定光学相干断层扫描（OCT）视网膜神经纤维层（RNFL）的感兴趣区域（ROI）图的随时间变化，与检测青光眼进展的周边 RNFL（cpRNFL）厚度。
对 44 只进展性青光眼眼（通过立体照片评估）、189 只非进展性青光眼眼（通过立体照片评估）和 109 只健康眼进行了≥3 年的随访，随访时间≥4 次，每次均使用 OCT。使用 San Diego 自动分层算法从原始三维 OCT 图像中自动分割 RNFL 层。对于每个纵向系列，使用 DL-AE 通过识别可能进展和无变化的 RNFL 区域来生成个体化的眼部 ROI 图。比较了 DL-AE ROI 和以视盘为中心的 2.22-3.45mm 环的全局 cpRNFL 厚度测量值随时间变化的检测敏感性和特异性以及随时间变化的速率。
在进展性眼中，检测变化的敏感性 DL-AE ROI 高于全局 cpRNFL 环厚度（分别为 0.90 和 0.63）。在非进展性眼中，检测不太可能进展的特异性相似（分别为 0.92 和 0.93）。进展性眼和非进展性眼中，DL-AE ROI 的平均变化率明显快于 cpRNFL 环厚度（分别为-1.28µm/y 和-0.83µm/y）。
使用 OCT 图像的 DL-AE 分析识别的眼部特异性 ROI 有望改善青光眼进展的评估。
赵桂秋
