Department of Ophthalmology, Faculty of Medicine, Bezmialem Vakif University, Adnan Menderes (Vatan) Avenue, Fatih, Istanbul 34093, Turkiye.
Department of Ophthalmology, Faculty of Medicine, Bezmialem Vakif University, Adnan Menderes (Vatan) Avenue, Fatih, Istanbul 34093, Turkiye.
Photodiagnosis Photodyn Ther. 2024 Feb;45:103891. doi: 10.1016/j.pdpdt.2023.103891. Epub 2023 Nov 9.
To quantitatively evaluate the effectiveness of the Noise2Noise (N2N) model, a deep learning (DL)-based noise reduction algorithm, on enhanced depth imaging-optical coherence tomography (EDI-OCT) images with different noise levels.
The study included 30 subfoveal EDI-OCT images averaged with 100 frames from 30 healthy participants. Artificial Gaussian noise at 25.00, 50.00, and 75.00 standard deviations were added to the averaged (original) images, and the images were grouped as 25N, 50N, and 75N. Afterward, noise-added images were denoised with the N2N model and grouped as 25dN, 50dN, and 75dN, according to previous noise levels. The choroidal vascularity index (CVI) and deep choroidal contrast-to-noise ratio (CNR) were calculated for all images, and noise-added and denoised images were compared with the original images. The structural similarity of the noise-added and denoised images to the original images was assessed by the Multi-Scale Structural Similarity Index (MS-SSI).
The CVI and CNR parameters of the original images (68.08 ± 2.47 %, and 9.71 ± 2.80) did not differ from the only 25dN images (67.97 ± 2.34 % and 8.50 ± 2.43) (p:1.000, and p:0.062, respectively). Noise reduction improved the MS-SSI at each noise level (p < 0.001). However, the highest MS-SSI was achieved in 25dN images.
The DL-based N2N denoising model can be used effectively for images with low noise levels, but at increasing noise levels, this model may be insufficient to provide both the original structural features of the choroid and structural similarity to the original image.
为了定量评估基于深度学习的降噪算法 Noise2Noise（N2N）在不同噪声水平下增强深度成像光学相干断层扫描（EDI-OCT）图像的效果。
本研究纳入了 30 名健康参与者的 30 个中心凹下 EDI-OCT 平均 100 帧图像。在平均（原始）图像中加入人工高斯噪声，标准差分别为 25.00、50.00 和 75.00，图像分为 25N、50N 和 75N。随后，用 N2N 模型对加噪图像进行去噪，并根据之前的噪声水平将其分为 25dN、50dN 和 75dN。计算所有图像的脉络膜血管指数（CVI）和深层脉络膜对比噪声比（CNR），并将加噪和去噪图像与原始图像进行比较。用多尺度结构相似性指数（MS-SSI）评估加噪和去噪图像与原始图像的结构相似性。
原始图像的 CVI 和 CNR 参数（68.08±2.47%和 9.71±2.80）与仅 25dN 图像（67.97±2.34%和 8.50±2.43）无差异（p：1.000，p：0.062）。降噪提高了每个噪声水平的 MS-SSI（p<0.001）。然而，最高的 MS-SSI 是在 25dN 图像中获得的。
基于深度学习的 N2N 去噪模型可有效用于低噪声水平的图像，但随着噪声水平的增加，该模型可能不足以提供脉络膜的原始结构特征和与原始图像的结构相似性。
