Hierarchical segmentation method for OCT (Optical Coherent Tomography) image of optic disc region based on spatial continuity constraints

Abstract

The invention discloses a hierarchical segmentation method for an OCT (Optical Coherent Tomography) image of an optic disc region based on spatial continuity constraints. The method comprises the steps of firstly removing speckle noise in the OCT image by using a BM3D algorithm; then mutually separating multiple high-reflection regions in the image by using an ROI (Region of Interest) segmentationmethod based on the fuzzy C-means and active contour; then positioning the vascular shadow by using an ROI region image; sequentially segmenting the ROI by using an A-scan segmentation algorithm, correcting an initial segmentation result of each image by using a vascular shadow region; and finally optimizing the corrected segmentation results by using the spatial continuity constraints to obtainsegmentation boundaries of an ILM (Internal Limiting Membrane), an IS-OS (Inner segment-Outer segment) and a BM (Bruch membrane). Disclosed by the invention is an effective hierarchical segmentation method for the OCT image of the optic disc region, is high in segmentation accuracy and has certain robustness for the speckle noise and vascular shadow.

Description

technical field [0001] The invention belongs to the technical field of medical image processing and image segmentation, and in particular relates to a hierarchical segmentation method of OCT images in an optic disc region based on spatial continuity constraints. Background technique [0002] Since the introduction of Spectial-Domain Optical Coherence Tomography (SD-OCT) imaging technology, it has been widely used in modern ophthalmic medical imaging diagnosis due to its non-invasive characteristics in the imaging process. Compared with traditional medical imaging technologies such as fundus cameras and ultrasound, SD-OCT can obtain more abundant three-dimensional structural information of physiological tissues, and provide more comprehensive assistance for doctors' clinical diagnosis. [0003] Common eye diseases, such as glaucoma and age-related macular degeneration (Age-related Macular Degeneration, AMD), etc., are mostly retinal diseases. When these ophthalmic diseases o...

AI Technical Summary

Problems solved by technology

However, compared with other types of algorithms, most algorithms based on graph theory have higher time complexity, and at the same time, the segmentation accuracy rate decreases when there are many vascular shadows.

Images