Brain tumor automatic extraction method based on symmetrically structured subtraction

Abstract

The invention provides a brain tumor automatic extraction method based on symmetrically structured subtraction, which can accurately separate out a tumor area and avoid human intervention, so as to improve the separation efficiency. The method comprises the following steps: firstly, brain tumor image symmetry analysis; secondly, optimization of a sagittal plane and a middle sagittal line in a symmetrical image, wherein the symmetric model obtained in the first step is applied to the tumor image, and the maximum mutual information between an original image and a mirror image thereof is taken as an optimized condition to calculate the optimized middle sagittal line; thirdly, the calculation of the reduction of the mirror image based on the middle sagittal line, wherein both the original image and the reduction of the mirror image based on the middle sagittal line are calculated; fourthly, relaxation iterative based tumor initial area tracking, wherein a relaxation iterative method is utilized to track the initializing boundary of the tumor area; and fifthly, accurate tumor separation utilizing an automatic seed point and window width based mean shift method, wherein an original seed point and wind width are calculated according to the initializing boundary of the tumor area obtained in the fourth step, and a mean drift algorithm is adopted to separate the original brain tumor image.

Description

technical field [0001] The invention is an automatic extraction method of brain tumor images, which can be applied to important decisions such as clinical diagnosis and treatment plan. Background technique [0002] Digital medical images are mainly obtained through X-ray, CT, PET, MRI and other technologies, among which MRI, that is, magnetic resonance imaging is a kind of tomography, which is characterized by the ability to obtain tomographic images of organisms in any direction, three-dimensional volume data, and even A 4D image of the spatial-spectral distribution can be obtained. MRI can be imaged without injecting radioactive isotopes, which is safer than PET and SPET. [0003] The most commonly used nucleus for MRI is the hydrogen nucleus proton (1H), because it has the strongest signal and is widely present in human tissue. The grayscale characteristic of MRI images is that the stronger the MRI signal, the greater the brightness; the weaker the MRI signal, the lower...

AI Technical Summary

Problems solved by technology

So far, there is no general-purpose, fully automatic segmentation algorithm with good segmentation effect, and different segmentation methods must be studied for tumor images with different manifestations

Images