Abstract
The presence of artifacts, including conjugate, DC, and auto-correlation artifacts, is a critical limitation of Fourier-domain optical coherence tomography (FD-OCT). Many methods have been proposed to resolve this problem to obtain high-quality images. Furthermore, the development of deep learning has resulted in many prospective advancements in the medical field; image-to-image translation by using generative adversarial networks (GANs) is one such advancement. In this study, we propose applying the Pix2Pix GAN to eliminate artifacts from FD-OCT images. The first experiment results showed that the proposed framework could translate conventional FD-OCT depth profiles into artifact-free FD-OCT depth profiles. In addition, the FD-OCT depth profile and optical distance of translated images matched those of ground truth images. Second experiment verified that the proposed GAN-based FD-OCT can be applied to generate artifact-free FD-OCT image with different parameters of sample refractive index, the front surface of the sample toward the zero-delay position, and the physical thickness of the sample. Third experiment proved that the proposed model could translated the conventional FD-OCT depth profiles with additional Gaussian noises source image into artifacts-free FD-OCT and successfully relieved the noise.
Highlights
Optical coherence tomography (OCT) is an optical imaging modality used to obtain high-resolution cross-sectional tomographic images of the internal microstructures of materials and biological systems
AND DISCUSSION we present the experimental results of the proposed Pix2Pix generative adversarial networks (GANs)-based Fourier-domain OCT (FD-OCT) model
First experiment aims to prove the feasibility of the Pix2Pix GAN-based FD-OCT
Summary
Optical coherence tomography (OCT) is an optical imaging modality used to obtain high-resolution cross-sectional tomographic images of the internal microstructures of materials and biological systems. We proposed another method for artifact suppression that utilized orthogonal polarized light for phase shifting to improve the speed of image scanning and remove unwanted components [4], [5]. A previous study [10] proposed an achromatic phase-shifting method in which a linear polarizer and a quarter-wave plate were used to generate circularly polarized light in the reference arm This method could produce fringe-free OCT images in a single shot. Another study proposed an FD-OCT design with two phase-shifted interference fringes that were simultaneously obtained from two orthogonally polarized lights and processed using the image reconstruction algorithm [11]. In a previous study [23], a GAN was implemented with conditional adversarial networks, known as cGAN, to obtain a general-purpose solution This model can be used to solve various image translation problems. By using (2), the value of axial resolution can be calculated as approximately 52.86 μm
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
