Abstract
Background: To investigate the effects of deep learning denoising on quantitative vascular measurements and the quality of optical coherence tomography angiography (OCTA) images. Methods: U-Net-based deep learning denoising with an averaged OCTA data set as teacher data was used in this study. One hundred and thirteen patients with various retinal diseases were examined. An OCT HS-100 (Canon inc., Tokyo, Japan) performed a 3 × 3 mm2 superficial capillary plexus layer slab scan centered on the fovea 10 times. A single-shot image was defined as the original image and the 10-frame averaged image and denoised image generated from the original image using deep learning denoising for the analyses were obtained. The main parameters measured were the OCTA image acquisition time, contrast-to-noise ratio (CNR), peak signal-to-noise ratio (PSNR), vessel density (VD), vessel length density (VLD), vessel diameter index (VDI), and fractal dimension (FD) of the original, averaged, and denoised images. Results: One hundred and twelve eyes of 108 patients were studied. Deep learning denoising removed the background noise and smoothed the rough vessel surface. The image acquisition times for the original, averaged, and denoised images were 16.6 ± 2.4, 285 ± 38, and 22.1 ± 2.4 s, respectively (P < 0.0001). The CNR and PSNR of the denoised image were significantly higher than those of the original image (P < 0.0001). There were significant differences in the VLD, VDI, and FD (P < 0.0001) after deep learning denoising. Conclusions: The deep learning denoising method achieved high speed and high quality OCTA imaging. This method may be a viable alternative to the multiple image averaging technique.
Highlights
Optical coherence tomography angiography (OCTA) is a non-invasive imaging method that images the three-dimensional retinal microvasculature by detecting the motion contrast of blood flow in the retina without intravenous dye injections [1]
The impact of deep learning denoising on optical coherence tomography angiography (OCTA) quantitative parameters and en face OCTA image acquisition times were evaluated and the results were compared with those obtained using the averaging technique
There was a significant improvement in the quality in both the denoised and averaged images, deep learning denoising yielded a significantly shorter OCTA image acquisition time than the averaging technique
Summary
Optical coherence tomography angiography (OCTA) is a non-invasive imaging method that images the three-dimensional retinal microvasculature by detecting the motion contrast of blood flow in the retina without intravenous dye injections [1]. The high contrast and resolution in OCTA images make it possible to evaluate the retinal microvasculature quantitatively, including vessel density and nonperfusion areas, more effectively than in FA images [3,4]. Since deep learning has the potential to generate a high-quality OCTA image from a single shot image without multiple image acquisition, the application of deep learning to en face OCTA imaging is expected to provide high-quality retinal microvasculature images in a short time. We developed a novel deep learning-based algorithm for noise reduction (denoising) in en face OCTA imaging and evaluated the effects of deep learning denoising on the image quality and image acquisition time
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
