Automatic segmentation of anterior segment of an eye in optical coherence tomography images

An imaging system comprising:

• a memory comprising computer-executable instructions;
• a processor configured to execute the computer-executable instructions and cause the imaging system to:
• generate, based on scan data of an eye, an optical coherence tomography (OCT) image of the eye;
• crop, based on one or more structures of the eye in the OCT image, the OCT image of the eye into one or more sub-images corresponding to the one or more structures, wherein the processor is configured to crop the OCT image of the eye into one or more sub-images by:
• identifying an iris of the eye in the OCT image;
• selecting, based on the iris of the eye, a set of cropping algorithms;
• and
• applying the set of cropping algorithms to crop the OCT image of the eye into the one or more sub-images;
• for each of the one or more sub-images of the OCT image of the eye:
• generate a background seed of the sub-image;
• generate a foreground seed of the sub-image;
• generate, based on both the background and the foreground seeds, and an image segmentation model, a mask for a structure of the one or more structures of the eye included in the sub-image;
• generate, based on the mask for the structure, one or more contours of the structure included in the sub-image;
• and
• display the one or more contours on the sub-image.

A system comprising:

• a memory comprising computer-executable instructions;
• a processor configured to execute the computer-executable instructions and cause the system to:
• receive scan data of an eye from an OCT imaging system;
• generate, based on the scan data, an OCT image of the eye;
• crop, based on one or more structures of the eye in the OCT image, the OCT image of the eye into one or more sub-images corresponding to the one or more structures, wherein cropping the OCT image of the eye into one or more sub-images, further comprises:
• identifying an iris of the eye in the OCT image;
• selecting, based on the iris of the eye, a set of cropping algorithms;
• and
• applying the set of cropping algorithms to crop the OCT image of the eye into the one or more sub-images;
• for each of the one or more sub-images of the OCT image of the eye:
• generate a background seed of the sub-image;
• generate a foreground seed of the sub-image;
• generate, based on both the background and the foreground seeds, and an image segmentation model, a mask for a structure of the one or more structures of the eye included in the sub-image;
• generate, based on the mask for the structure, one or more contours of the structure included in the sub-image;
• generate an enhanced sub-image by displaying one or more virtual markers on the sub-image, wherein the virtual markers correspond to the one or more contours of the structure;
• and
• transmit the enhanced sub-image to the OCT imaging system.