Automatic geographic atrophy segmentation using optical attenuation in OCT scans with deep learning
Automatic geographic atrophy segmentation using optical attenuation in OCT scans with deep learning
复制标题
DOI：
10.1364/boe.449314
复制
发表时间：
2022-03-01
影响因子：
3.4
通讯作者：
Wang, Ruikang K.
中科院分区：
文献类型：
--
作者：
Chu, Zhongdi;Wang, Liang;Wang, Ruikang K.
开发了一种深度学习算法，用于基于从光学相干断层扫描（OCT）数据集计算的光学衰减系数（OAC）自动识别、分割和量化地图状萎缩（GA）。正常眼和继发于年龄相关性黄斑变性的GA眼使用6 x 6 mm扫描模式用扫频源OCT成像。根据OCT扫描计算的OAC用于生成定制的复合正面OAC图像。使用定制的正面视网膜下色素上皮（subRPE）OCT图像识别和测量GA病变。使用OAC图像和subRPE OCT图像训练具有相同U-Net架构的两个深度学习模型。使用DICE相似系数（DSC）评价模型性能。计算GA面积，并使用Pearson相关性和Bland-Altman图与手动分割进行比较。本研究共包括80只GA眼和60只正常眼，其中16只GA眼和12只正常眼用于测试模型。这两种模型在受试者水平上以100%的灵敏度和特异性鉴定了GA。对于GA眼睛，与使用subRPE OCT图像训练的模型相比，使用OAC图像训练的模型实现了显著更高的DSC，与手动结果的更强相关性和更小的平均偏差（0.940 +/- 0.032 vs 0.889 +/- 0.056，p = 0.03，配对t检验，r = 0.995 vs r = 0.959，平均偏倚= 0.011 mm vs平均偏倚= 0.117 mm）。总之，所提出的使用复合OAC图像的深度学习模型使用OCT扫描有效且准确地识别、分割和量化GA。(C)2022 Optica出版集团根据Optica开放获取出版协议的条款
A deep learning algorithm was developed to automatically identify, segment, and quantify geographic atrophy (GA) based on optical attenuation coefficients (OACs) calculated from optical coherence tomography (OCT) datasets. Normal eyes and eyes with GA secondary to age-related macular degeneration were imaged with swept-source OCT using 6 x 6 mm scanning patterns. OACs calculated from OCT scans were used to generate customized composite en face OAC images. GA lesions were identified and measured using customized en face sub-retinal pigment epithelium (subRPE) OCT images. Two deep learning models with the same U-Net architecture were trained using OAC images and subRPE OCT images. Model performance was evaluated using DICE similarity coefficients (DSCs). The GA areas were calculated and compared with manual segmentations using Pearson's correlation and Bland-Altman plots. In total, 80 GA eyes and 60 normal eyes were included in this study, out of which, 16 GA eyes and 12 normal eyes were used to test the models. Both models identified GA with 100% sensitivity and specificity on the subject level. With the GA eyes, the model trained with OAC images achieved significantly higher DSCs, stronger correlation to manual results and smaller mean bias than the model trained with subRPE OCT images (0.940 +/- 0.032 vs 0.889 +/- 0.056, p = 0.03, paired t-test, r = 0.995 vs r = 0.959, mean bias = 0.011 mm vs mean bias = 0.117 mm). In summary, the proposed deep learning model using composite OAC images effectively and accurately identified, segmented, and quantified GA using OCT scans. (C) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement