Intracranial hemorrhage area three-dimensional segmentation method based on local entropy and level set algorithm

Abstract

The invention relates to an intracranial hemorrhage area three-dimensional segmentation method based on local entropy and a level set algorithm, and belongs to the technical field of image processing.The method comprises the following steps: S1, inputting multiple frames of MRI images; s2, initializing a level set function, and setting a parameter penalty term coefficient and the size of a Gaussian kernel function; s3, calculating a local entropy and an adaptive length term coefficient, and iteratively calculating a mean value of global and local terms according to a derivation formula; s4, using the calculated local entropy as an adaptive weight model to adjust the weights of the global item and the local item, and using the calculated adaptive length item coefficient to change the curved surface evolution speed; and S5, evolving the level set function by using a gradient descent method, and performing three-dimensional segmentation on the image. Compared with a traditional image segmentation method, the method is easy to implement, and does not need to spend a lot of time in extracting image features and adjusting system parameters; and three-dimensional segmentation of multipleframes of intracranial hemorrhage MRI images is also ensured.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a three-dimensional segmentation method for intracranial hemorrhage area based on local entropy and level set algorithm. Background technique [0002] Medical image segmentation is a complex and critical step in the field of medical image processing and analysis. Medical practitioners make a more accurate diagnosis. Although there are certain research results in the use of MRI images to segment intracranial hemorrhage regions, there is a lack of algorithms that effectively consider and balance the characteristics of the above segmentation problems. The gray similarity between the hemorrhage area and the surrounding tissue in the MRI image increases the difficulty of hemorrhage area segmentation. MRI scans provide three-dimensional data in the form of two-dimensional slices, and the correlation between each tomographic image makes three-dimensional segmentation possible. ...

AI Technical Summary

Problems solved by technology

[0003] In view of this, the object of the present invention is to provide a three-dimensional segmentation method of intracranial hemorrhage area based on local entropy and level set algorithm, which solves the failure of image segmentation with uneven gray scale in the prior art, and the gray scale of the bleeding area is similar to that of surrounding tissues Increase the difficulty of segmentation, weak robustness to noise, etc., and can greatly reduce the time for extracting image features and adjusting system parameters

Images