Image segmentation method and device, and method for judging image inversion and distinguishing front side and back side of sternum

Abstract

The invention discloses image segmentation method and device, and a method for judging image inversion and distinguishing the front side and the back side of a sternum. The image segmentation method comprises the following steps of: a. preprocessing the input image; b. searching the outline of the target area, and checking the search result of the outline, wherein the process for checking the search result of the outline comprises the following steps of: judging whether the shape abnormity index of the target area in the outline search process is less than or equal to a preset threshold value; if so, accepting the result of the search process; and if not, rejecting the result of the search process; and c. extracting the target area according to the check result. By increasing the check procedure, the invention can enable a user to reasonably distinguish the input image, thereby solving the problem that the image abnormity affects the segmentation.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to image segmentation processing and its application in computer-aided image processing of digital X-ray chest films. Background technique [0002] Image segmentation, especially the segmentation of chest X-ray lung images, is a necessary process for computer-aided diagnosis and image post-processing of digital chest X-rays. On the one hand, it extracts the region of interest in the lung, which can reduce the number of false positives in lung disease detection; on the other hand, it facilitates the realization of chest radiographic tissue balance; at the same time, it is also the basis for automatic calculation of lung parameters. [0003] There are many techniques for realizing lung segmentation. Currently, there are three commonly used techniques: [0004] One is the rule-based segmentation method, which mainly utilizes image characteristics and processes the image so th...

AI Technical Summary

Problems solved by technology

This method has a simple process and fewer rules, but it is time-consuming to implement because it often requires a large number of cyclic comparisons, and the results are usually presented in the form of probability, resulting in uneven edges of the segmentation results.

[0006]The third is the model-based method, which has a relatively strong anti-noise ability, and the result is relatively smooth and complete, but it is easy to fall into local extremum, and it is harmful to the lungs Extraction of images with structural abnormalities or serious diseases will also fail

In the classic ASM (Active Shape Model, ASM), the component change of the feature vector should be within a limited range. If the limited range is small, it will be difficult to iterate to approximate the real contour due to the endless real shape.

Under a reasonable limit, the iteration of ASM may have abnormal shapes, which makes the extraction results unsatisfactory. Classical ASM cannot automatically identify such errors. Once the above situation occurs, the existing segmentation method The above problems cannot be avoided

[0007] In addition, for frontal chest radiographs, the current segmentation methods are not compatible with upside-down or left-right upside-down images. Once such images appear, the result will be serious. mistake

Images