Provided herein are techniques for automatically segmenting anterior segment of an eye in an optical coherence tomography (OCT) image. A method includes receiving an OCT image of an eye; cropping, 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; for each of the one or more sub-images of the OCT image of the eye: generating a background seed and a foreground seed of the sub-image; generating, based on 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; generating, based on the mask for the structure, one or more contours of the structure included in the sub-image; and displaying the one or more contours on the sub-image.