Glaucoma Division, Stein Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California.
Department of Computer Science, California State University Los Angeles, Los Angeles, California.
Ophthalmol Glaucoma. 2023 Jan-Feb;6(1):68-77. doi: 10.1016/j.ogla.2022.06.006. Epub 2022 Jun 21.
To investigate the confounding effect of nonexudative age-related macular degeneration (AMD), specifically drusen and outer retinal atrophy, on the architecture and automated segmentation of the inner retinal layers as measured with OCT.
Observational cross-sectional study.
Two hundred sixty-three consecutive eyes with nonexudative AMD were identified through a retrospective chart review. Exclusion criteria were a diagnosis of glaucoma or glaucoma suspect, other retinal pathology affecting the macula, axial length > 26.5 mm or spherical equivalent less than -6 diopters, any other optic nerve or neurologic disorders, or poor image quality.
Drusen were automatically segmented on macular OCT B-scans with a publicly available and validated deep learning approach. Automated segmentation of the inner plexiform layer (IPL)/inner nuclear layer (INL) boundary was carried out with the device's proprietary software.
Quality of segmentation of the IPL/INL boundary as a function of drusen size and presence of inner retinal layer displacement in the area of macular pathology (drusen or atrophy).
One hundred twenty-five eyes (65 patients) met the inclusion criteria. Drusen size varied between 16 and 272 μm (mean, 118 μm). Automated segmentation had a 22% chance of failure if the drusen height was between 145 and 185 μm and was most likely to fail with drusen heights above 185 μm. When drusen height was normalized by total retinal thickness, segmentation failed 36% of the time when the drusen to total retinal thickness ratio was 0.45 or above. Images were likely to show displacement of inner retinal layers with drusen heights above 176 μm and a normalized drusen height ratio of 0.5 or higher. Eighty-seven percent of images with outer retinal atrophy displayed incorrect segmentation.
Outer retinal diseases can alter the retinal topography and affect the segmentation accuracy of the inner retinal layers. Large drusen may cause segmentation error and compression of the inner macular layers. Geographic atrophy confounds automated segmentation in a high proportion of eyes. Clinicians should be cognizant of the effects of outer retinal disease on the inner retinal layer measurements when interpreting the results of macular OCT imaging in patients with glaucoma.
研究非渗出性年龄相关性黄斑变性（AMD），特别是玻璃膜疣和外层视网膜萎缩，对 OCT 测量的内视网膜层结构和自动分割的混杂影响。
观察性横断面研究。
通过回顾性图表审查，确定了 263 只连续患有非渗出性 AMD 的眼睛。排除标准包括青光眼或疑似青光眼的诊断、影响黄斑的其他视网膜病变、眼轴长度>26.5mm 或等效球镜度数小于-6 屈光度、任何其他视神经或神经障碍、或图像质量差。
使用公开的、经过验证的深度学习方法，对黄斑 OCT B 扫描中的玻璃膜疣进行自动分割。使用设备的专有软件对内丛状层（IPL）/内核层（INL）边界进行自动分割。
作为玻璃膜疣大小和黄斑病变区域（玻璃膜疣或萎缩）内视网膜层移位存在的函数，IPL/INL 边界分割的质量。
125 只眼睛（65 名患者）符合纳入标准。玻璃膜疣大小在 16 至 272μm 之间（平均 118μm）。如果玻璃膜疣高度在 145 至 185μm 之间，自动分割的失败概率为 22%，而当玻璃膜疣高度超过 185μm 时，最有可能失败。当玻璃膜疣高度按总视网膜厚度进行归一化时，当玻璃膜疣与总视网膜厚度的比值为 0.45 或更高时，图像的分割失败率为 36%。当玻璃膜疣高度超过 176μm 且归一化玻璃膜疣高度比为 0.5 或更高时，内视网膜层很可能发生移位。87%的外层视网膜萎缩图像显示出不正确的分割。
外层视网膜疾病会改变视网膜的形态，并影响内视网膜层的分割准确性。大玻璃膜疣可能导致分割错误和内黄斑层的压缩。地理萎缩在很大比例的眼睛中混淆了自动分割。临床医生在解释青光眼患者的黄斑 OCT 成像结果时，应意识到外层视网膜疾病对内视网膜层测量的影响。
