OCT image edema region boundary extraction method and system based on biological inspiration

Abstract

The invention belongs to the technical field of edema region boundary extraction, and discloses an OCT image edema region boundary extraction method and system based on biological inspiration, and themethod comprises the steps: carrying out the denoising and smooth preprocessing of an OCT image based on biological inspiration; and carrying out edema region boundary extraction on the OCT image byutilizing the improved SBGFRLS model. According to the method, denoising and smoothing preprocessing of the OCT image are realized based on a structure preserving and guiding retina image filtering method; according to the SGRIF method, the image quality is improved, meanwhile, the structure of the retina image is protected, and a foundation is laid for high-precision extraction of the edema region boundary; based on edema region boundary extraction of the improved level set, the level set evolution curve is converged into the edema region by improving the symbolic pressure function in the binarized Gaussian filtering level set, and high-precision extraction of the edema region boundary of the DME is achieved.

Description

technical field [0001] The invention belongs to the technical field of edema region boundary extraction, and in particular relates to a biologically inspired OCT image edema region boundary extraction method and system. Background technique [0002] Currently, the closest prior art: [0003] Diabetic retinopathy (DR) is one of the most common complications of diabetes, and the prevalence of DR in diabetic patients worldwide is about 25%. Diabetic patients develop diabetic macular edema (DME) due to diabetes. DME is considered to be the main cause of central vision loss. Therefore, early detection and detection of DME has a great guiding effect on the early treatment of DR. Coherence tomography (OCT) is a noninvasive imaging modality that provides information on morphological organization including the retina, and is a method for visualizing edematous regions, which has been widely used for edge detection in DME regions. Affected by OCT image quality, edema region boundary ...

AI Technical Summary

Problems solved by technology

[0006] Affected by OCT image quality, edema area boundary fuzziness and shape diversification, the existing OCT image edema area boundary extraction has the following problems: (1) Affected by image quality such as noise, the existing methods still cannot extract the edema area boundary. There are phenomena such as mis-extraction and over-extraction; (2) Affected by the ambiguity of the boundary of the edema area, the existing method has the problem of high calculation time when searching for the boundary of the edema area; (3) Affected by the shape diversity of the edema area, the existing method The accuracy of the results of the edema area boundary extraction needs to be improved

[0008] (1) Affected by noise and other image quality, the existing methods still have mis-extraction and over-extraction when extracting the boundary of the edema area

[0009] (2) Affected by the ambiguity of the boundary of the edema area, the existing methods have problems such as high computational time consumption when searching for the boundary of the edema area

[0010] (3) Affected by the diversification of the shape of the edema area, the accuracy of the results of the boundary extraction of the edema area of ​​the existing method needs to be improved

[0012] Affected by the image acquisition equipment, there are often problems such as noise or uneven brightness in the acquired image, which leads to mis-extraction and over-extraction during boundary extraction.

[0013] The boundary of the edema area of ​​the OCT image is similar to the gray value of the surrounding ROI area, and the color boundary is not obvious, so it is difficult to accurately extract

[0014] The shape of the edema area is diverse, so that the extraction accuracy of the edema boundary is not high

Images