Dong Yanling, Li Dongfang, Guo Zhen, Liu Yang, Lin Ping, Lv Bin, Lv Chuanfeng, Xie Guotong, Xie Lixin
Qingdao Eye Hospital of Shandong First Medical University, Qingdao, China.
State Key Laboratory Cultivation Base, Shandong Provincial Key Laboratory of Ophthalmology, Eye Institute of Shandong First Medical University, Qingdao, China.
Front Neurosci. 2022 Jan 31;15:804273. doi: 10.3389/fnins.2021.804273. eCollection 2021.
To characterize the corneal and epithelial thickness at different stages of keratoconus (KC), using a deep learning based corneal segmentation algorithm for anterior segment optical coherence tomography (AS-OCT).
An AS-OCT dataset was constructed in this study with 1,430 images from 715 eyes, which included 118 normal eyes, 134 mild KC, 239 moderate KC, 153 severe KC, and 71 scarring KC. A deep learning based corneal segmentation algorithm was applied to isolate the epithelial and corneal tissues from the background. Based on the segmentation results, the thickness of epithelial and corneal tissues was automatically measured in the center 6 mm area. One-way ANOVA and linear regression were performed in 20 equally divided zones to explore the trend of the thickness changes at different locations with the KC progression. The 95% confidence intervals (CI) of epithelial thickness and corneal thickness in a specific zone were calculated to reveal the difference of thickness distribution among different groups.
Our data showed that the deep learning based corneal segmentation algorithm can achieve accurate tissue segmentation and the error range of measured thickness was less than 4 μm between our method and the results from clinical experts, which is approximately one image pixel. Statistical analyses revealed significant corneal thickness differences in all the divided zones ( < 0.05). The entire corneal thickness grew gradually thinner with the progression of the KC, and their trends were more pronounced around the pupil center with a slight shift toward the temporal and inferior side. Especially the epithelial thicknesses were thinner gradually from a normal eye to severe KC. Due to the formation of the corneal scarring, epithelial thickness had irregular fluctuations in the scarring KC.
Our study demonstrates that our deep learning method based on AS-OCT images could accurately delineate the corneal tissues and further successfully characterize the epithelial and corneal thickness changes at different stages of the KC progression.
使用基于深度学习的前段光学相干断层扫描（AS-OCT）角膜分割算法，描述圆锥角膜（KC）不同阶段的角膜厚度和上皮厚度。
本研究构建了一个AS-OCT数据集，包含来自715只眼睛的1430张图像，其中包括118只正常眼睛、134只轻度KC、239只中度KC、153只重度KC和71只瘢痕化KC。应用基于深度学习的角膜分割算法将上皮组织和角膜组织与背景分离。根据分割结果，在中心6mm区域自动测量上皮组织和角膜组织的厚度。在20个等分区中进行单因素方差分析和线性回归，以探讨不同位置的厚度变化随KC进展的趋势。计算特定区域上皮厚度和角膜厚度的95%置信区间（CI），以揭示不同组之间厚度分布的差异。
我们的数据表明，基于深度学习的角膜分割算法能够实现准确的组织分割，我们的方法与临床专家的测量结果之间的厚度误差范围小于4μm，约为一个图像像素。统计分析显示，所有分区的角膜厚度均存在显著差异（<0.05）。随着KC的进展，整个角膜厚度逐渐变薄，在瞳孔中心周围趋势更为明显，并略有向颞侧和下方偏移。尤其是从正常眼睛到重度KC，上皮厚度逐渐变薄。由于角膜瘢痕的形成，瘢痕化KC中的上皮厚度出现不规则波动。
我们的研究表明，基于AS-OCT图像的深度学习方法能够准确描绘角膜组织，并进一步成功描述KC进展不同阶段的上皮和角膜厚度变化。
