Adaptive optics optical coherence tomography (AOOCT) requires a dense sampling of the retina to visualize individual cones in the living human eye. This in turn increases the acquisition time and introduces susceptibility to eye motion artifacts. Here, we present hybrid transformer generative adversarial network (HT-GAN), an artificial intelligence technique that can improve the pixel resolution of images to better reveal cones from sparsely sampled AOOCT volumes. The method can potentially increase the speed of acquisition by four-fold while maintaining the visibility of individual cones despite a lower than ideal pixel sampling.
High-resolution imaging is essential for understanding retinal diseases. Adaptive optics scanning light ophthalmoscopy (AOSLO) achieves cellular-level resolution through correction of the optical aberrations of the eye. However, the resolution of AOSLO is still limited by the diffraction of light. Here, we combine annular pupil illumination with sub-Airy disk confocal pinhole detection to surpass the diffraction limit. With the improved resolution, both rod photoreceptor and foveal cone mosaics were more readily identifiable in the living human eye.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.