Department of Biomedical Engineering, Duke University, Durham, North Carolina.
Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina.
Retina. 2022 Jul 1;42(7):1347-1355. doi: 10.1097/IAE.0000000000003448.
To assess the generalizability of a deep learning-based algorithm to segment the ellipsoid zone (EZ).
The dataset consisted of 127 spectral-domain optical coherence tomography volumes from eyes of participants with USH2A-related retinal degeneration enrolled in the RUSH2A clinical trial (NCT03146078). The EZ was segmented manually by trained readers and automatically by deep OCT atrophy detection, a deep learning-based algorithm originally developed for macular telangiectasia Type 2. Performance was evaluated using the Dice similarity coefficient between the segmentations, and the absolute difference and Pearson's correlation of measurements of interest obtained from the segmentations.
With deep OCT atrophy detection, the average (mean ± SD, median) Dice similarity coefficient was 0.79 ± 0.27, 0.90. The average absolute difference in total EZ area was 0.62 ± 1.41, 0.22 mm2 with a correlation of 0.97. The average absolute difference in the maximum EZ length was 222 ± 288, 126 µm with a correlation of 0.97.
Deep OCT atrophy detection segmented EZ in USH2A-related retinal degeneration with good performance. The algorithm is potentially generalizable to other diseases and other biomarkers of interest as well, which is an important aspect of clinical applicability.
评估基于深度学习的算法在分割椭圆体区（EZ）方面的泛化能力。
该数据集包含了 127 份来自 RUSH2A 临床试验（NCT03146078）中 USH2A 相关视网膜变性患者的光谱域光学相干断层扫描体积。EZ 由经过训练的读者手动分割和深度 OCT 萎缩检测自动分割，后者是一种基于深度学习的算法，最初用于治疗 2 型黄斑毛细血管扩张症。通过分割的 Dice 相似系数、分割得到的感兴趣测量值的绝对差异和 Pearson 相关系数来评估性能。
使用深度 OCT 萎缩检测，平均（平均值 ± 标准差，中位数）Dice 相似系数为 0.79 ± 0.27，0.90。总 EZ 面积的平均绝对差异为 0.62 ± 1.41，0.22mm2，相关性为 0.97。最大 EZ 长度的平均绝对差异为 222 ± 288，126µm，相关性为 0.97。
深度 OCT 萎缩检测在 USH2A 相关视网膜变性中对 EZ 进行了分割，性能良好。该算法具有潜在的泛化能力，可以应用于其他疾病和其他感兴趣的生物标志物，这是临床应用的一个重要方面。
