Method and system for automatically extracting inner contour of blood vessel wall based on OCT image

Abstract

The invention discloses a blood vessel wall inner contour automatic extraction method and system based on an OCT image. The method comprises the following steps: acquiring an original OCT blood vessel image; performing pretreatment; carrying out binarization on the preprocessed OCT blood vessel image, carrying out opening operation and closing operation in mathematical morphology, scanning each A-line of the preprocessed OCT blood vessel image, taking the initial position of the longest area as a blood vessel wall inner contour point, and extracting an initial blood vessel wall inner contour; correcting the initial inner contour of the blood vessel wall; and converting the inner contour line of the blood vessel wall to Cartesian coordinates to obtain a final inner contour of the blood vessel wall. According to the method, the OCT blood vessel image is binarized and then is subjected to opening operation and closing operation in mathematical morphology, the blood vessel wall inner contour is extracted according to the A-line numerical value of the OCT blood vessel image after blood vessel tissue segmentation is realized, the influence of image noise on blood vessel contour extraction is reduced, the operation frequency is reduced, and the robustness of an algorithm is improved.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method and system for automatically extracting the inner contour of a blood vessel wall based on an OCT image. Background technique [0002] Globally, cardiovascular and cerebrovascular diseases have become one of the major diseases that threaten human health, and coronary atherosclerosis is the main cause of cardiovascular and cerebrovascular diseases. Optical coherence tomography (OCT) is the latest intravascular imaging technique for the diagnosis of cardiovascular and cerebrovascular diseases. [0003] OCT utilizes near-infrared light and is a high-resolution imaging technique that can probe micron-scale structures in biological tissues. It has an axial resolution of about 10µm, a lateral resolution of about 20µm, and a detection depth of about 2mm. For the coronary artery wall, OCT can provide more subtle and clear information. [0004] The diagnosis of...

AI Technical Summary

Problems solved by technology

The first type is the method based on the active contour model (Snake model), which often needs to give the initial contour line, which is sensitive to noise, and the efficiency of the algorithm is not high, and the time cost is large

The second category is a method based on machine learning, which needs to extract features and obtain a large amount of data for calibration and training, which is subject to many limitations in practical applications

The third type is a statistical method, which mainly uses the gray information of the image for statistical modeling, but for complex OCT images containing artifacts or plaques, the accuracy of statistical modeling will be greatly reduced

For complex blood vessel images, the extraction effect of the inner contour of the blood vessel wall is not ideal

Images