COMPARISON OF THE CHOROIDAL VASCULARITY INDEX MEASUREMENTS OF IMAGES ACQUIRED WITH DIFFERENT OPTICAL COHERENCE TOMOGRAPHY SCAN SCALE TYPES.

PURPOSE: To evaluate the differences in choroidal vascularity index (CVI) measurements between images acquired at the 1:1 pixel scale and at the 1:1 µ m scale of the Heidelberg optical coherence tomography device. METHODS: Forty-five healthy eyes of 45 healthy subjects were included for this study. Fovea-centered scans were obtained with an enhanced-depth imaging mode with a high-speed protocol scan. Each scan was exported in 3 different types: 1) 1:1 pixel scale type; 2) 1:1 µ m scale type (MST); and 3) 4×-magnified MST (4×MST; 400%-magnified 1:1 µ m images exported via screenshot). A comparison between CVI measurements based on the different scale types of optical coherence tomography images was conducted using the Bland-Altman analysis and intraclass correlation coefficient. RESULTS: The image with the worst clarity was acquired via the MST, and the CVI was found to be higher in MST images (69.05 ± 3.21) compared with the other groups. The intraclass correlation coefficient between the CVI values of the 4×MST and pixel scale type images was 0.92, between those of the 4×MST and MST images was 0.33, and between those of the pixel scale type and MST images was 0.44. CONCLUSION: The optical coherence tomography scale and export method type significantly influence the image resolution, CVI, and choroidal area measurements.

Quantitative analysis of deep learning-based denoising model efficacy on optical coherence tomography images with different noise levels.

BACKGROUND: 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. METHODS: 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). RESULTS: 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. CONCLUSIONS: 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.