Lens segmentation method and device and storage medium

Abstract

The embodiment of the invention provides a lens segmentation method and device and a storage medium. The method comprises the steps of extracting a lens image area from an original image; obtaining aninitial lens structure in the lens image area through a preset neural network model; and performing edge smoothing processing on the initial lens structure by adopting a shape template to obtain a segmented lens structure, the shape template being obtained by training a lens sample. By means of the preset neural network model and the shape template, the automatic segmentation of the lens structure can be achieved, so that the accuracy of lens structure segmentation is improved while the labor cost is reduced.

Description

technical field [0001] Embodiments of the present invention relate to the field of image analysis, and in particular, to a lens segmentation method, device and storage medium. Background technique [0002] As a common blinding eye disease, cataract is due to certain reasons that cause the lens to become cloudy, which affects retinal imaging and causes patients to be unable to see clearly. Among them, anterior segment optical coherence tomography (Anterior Segment Optical Coherence Tomography, referred to as: AS-OCT) can be used to assist in the diagnosis of various ophthalmic diseases including cataracts. Specifically, AS-OCT is a non-invasive and harmless diagnostic method that uses the density of different structures of the lens to measure the severity of ophthalmic diseases such as cataracts. [0003] At present, lens structure segmentation based on AS-OCT images is mostly performed manually. However, manual segmentation of the lens structure has the problem of low accu...

AI Technical Summary

Problems solved by technology

However, manual segmentation of the lens structure has the problem of low accuracy and high labor costs

Images