“Deep Learning Based System Generation Of Visible Light For Retinal Images Captured Scanning Laser Ophthalmoscopy”

Abstract: ABSTRACT GENERATING A VISIBLE LIGHT IMAGE FROM A SCANNING LASER OPHTHALMOSCOPE IMAGE Approaches for generating a visible light image from a scanning laser ophthalmoscope (SLO) image are described. In an 5 example, an input SLO image of a retina is obtained and processed using an image generation model. This model is trained on paired datasets of SLO images and corresponding visible light images, along with detailed retinal feature data. The model extracts retinal features from the input SLO image, including 10 information about various retinal layers, structures, and characteristics. Based on these extracted features, the model generates a visible light image that closely resembles what would be captured by a traditional visible light retinal camera. The image generation model utilizes a generative adversarial network (GAN) architecture, comprising a generator and 15 discriminator, to produce highly realistic synthetic images.

Patent Information

Applicants

Inventors

Specification

Documents

Application Documents