To help clinicians better detect and track eye diseases like glaucoma and age-related macular degeneration, researchers have applied artificial intelligence (AI) deep learning techniques to develop a more precise and in-depth method for analyzing optical coherence tomography (OCT) images of the back of the eye. OCT imaging, frequently used in ophthalmology and optometry, captures high-resolution cross-sectional pictures of the eye that reveal the various tissue layers. These pictures have a 4 m width.
Clinicians can identify eye diseases by using OCT imaging scans to measure and track the thickness of the tissue layers in the eye.
In the study, researchers searched for a novel approach to image analysis. They extracted the retina and choroid, the two major tissue layers at the rear of the eye, with a focus on the choroid. The main blood arteries that carry nutrients and oxygen to the eye are found in the choroid, between the retina and the sclera.
According to researchers, although most clinical OCT instruments have software that analyzes choroidal tissue, standard OCT imaging processing methods do a good job of defining and analyzing the layers of retinal tissue. To precisely and automatically define the boundaries between the choroid and the retina, the study team trained a deep learning network to learn the essential characteristics of the images.
Related Content: High-Resolution OCT To Improve Retinal Imaging