Abstract
Polarization-sensitive optical coherence tomography (PS-OCT) is a high-resolution label-free optical biomedical imaging modality that is sensitive to the microstructural architecture in tissue that gives rise to form birefringence, such as collagen or muscle fibers. To enable polarization sensitivity in an OCT system, however, requires additional hardware and complexity. We developed a deep-learning method to synthesize PS-OCT images by training a generative adversarial network (GAN) on OCT intensity and PS-OCT images. The synthesis accuracy was first evaluated by the structural similarity index (SSIM) between the synthetic and real PS-OCT images. Furthermore, the effectiveness of the computational PS-OCT images was validated by separately training two image classifiers using the real and synthetic PS-OCT images for cancer/normal classification. The similar classification results of the two trained classifiers demonstrate that the predicted PS-OCT images can be potentially used interchangeably in cancer diagnosis applications. In addition, we applied the trained GAN models on OCT images collected from a separate OCT imaging system, and the synthetic PS-OCT images correlate well with the real PS-OCT image collected from the same sample sites using the PS-OCT imaging system. This computational PS-OCT imaging method has the potential to reduce the cost, complexity, and need for hardware-based PS-OCT imaging systems.
Highlights
Polarization-sensitive OCT (PS-OCT)[1] has become an exceptionally useful imaging technique that complements the scattering intensity contrast in standard OCT systems and provides additional diagnostic information and guidance[2,3,4,5,6,7]
Two generative adversarial network (GAN) models were generated for the degree of polarization uniformity (DOPU) and phase retardation synthesis, two common image-based representations of polarization information in PS-OCT images
While conventional hardware-based PS-OCT requires at least two OCT images with different polarizations to obtain the DOPU and phase retardation contrasts, our method managed to extract the polarization-sensitive information from single-polarization intensity images from a standard OCT system
Summary
Polarization-sensitive OCT (PS-OCT)[1] has become an exceptionally useful imaging technique that complements the scattering intensity contrast in standard OCT systems and provides additional diagnostic information and guidance[2,3,4,5,6,7]. While the generator network is similar to the DNNs used in conventional feature segmentation like U-Net, the discriminator network scores the synthetic images to estimate how likely they come from the training dataset instead of the generator network With such a unique network structure, a GAN was used in various synthetic biomedical imaging applications, such as virtual histology[15], digital phase staining[17], and synthetic clinical imaging[20,25]. Based on these demonstrated results, we propose and demonstrate the use of a GAN as the deep-learning model to synthesize PS-OCT images
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.