Qiu Bin, Huang Zhiyu, Liu Xi, Meng Xiangxi, You Yunfei, Liu Gangjun, Yang Kun, Maier Andreas, Ren Qiushi, Lu Yanye
Department of Biomedical Engineering, College of Engineering, Peking University, No. 5 Yihe Yuan Road, Haidian District, Beijing 100871, China.
Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Department of Nuclear Medicine, Peking University Cancer Hospital & Institute, Beijing 100142, China.
Biomed Opt Express. 2020 Jan 14;11(2):817-830. doi: 10.1364/BOE.379551. eCollection 2020 Feb 1.
Optical coherence tomography (OCT) is susceptible to the coherent noise, which is the speckle noise that deteriorates contrast and the detail structural information of OCT images, thus imposing significant limitations on the diagnostic capability of OCT. In this paper, we propose a novel OCT image denoising method by using an end-to-end deep learning network with a perceptually-sensitive loss function. The method has been validated on OCT images acquired from healthy volunteers' eyes. The label images for training and evaluating OCT denoising deep learning models are images generated by averaging 50 frames of respective registered B-scans acquired from a region with scans occurring in one direction. The results showed that the new approach can outperform other related denoising methods on the aspects of preserving detail structure information of retinal layers and improving the perceptual metrics in the human visual perception.
光学相干断层扫描（OCT）易受相干噪声影响，这种相干噪声即散斑噪声，会降低OCT图像的对比度和细节结构信息，从而对OCT的诊断能力造成重大限制。在本文中，我们提出了一种新颖的OCT图像去噪方法，该方法使用具有感知敏感损失函数的端到端深度学习网络。该方法已在从健康志愿者眼睛获取的OCT图像上得到验证。用于训练和评估OCT去噪深度学习模型的标签图像是通过对从一个方向进行扫描的区域获取的50帧各自配准的B扫描图像进行平均而生成的。结果表明，新方法在保留视网膜层细节结构信息和改善人类视觉感知中的感知指标方面优于其他相关去噪方法。
