Research of volume measuring method for CT (Computer Tomography) image intracranial hematoma

Abstract

The invention relates to a research of a volume measuring method for CT (Computer Tomography) image intracranial hematoma. Aiming at the characteristics of an intracranial hematoma CT image, Nonlinear anisotropic diffuse filtration is adopted on the preprocessing of the image for effectively removing noises and artifacts and meeting the practical requirement of medical image processing; two-step image segmentation processing is adopted on the image for skillfully removing the skull and non-brain tissue outside the skull without the operations of image registration, and the like; and the concept of entropy is introduced into image segmentation for realizing the two-dimensional entropy threshold, and pixel grayscale and neighborhood grayscale are used as parameters for segmenting an image, which not only reflects the grayscale information distribution, but also reflects the relevant information of a neighborhood space of an image pixel, thereby effectively inhibiting noises and suppressing interferences and unnecessary fine structures; all operators of a genetic algorithm are improved, and a self-adaptive large mutation operator is adopted particularly for solving the problem of prematurity existing in the genetic algorithm, i.e. the algorithm is prematurely converged into a non-global optimal point; and finally, an optimal threshold value is searched by an improved delamination genetic algorithm.

Description

technical field [0001] The research on the volume measurement method of intracranial hematoma in CT image of the present invention is to transform the clinical requirement of volume measurement of intracranial hematoma into the hematoma segmentation problem of CT image, and propose a new segmentation algorithm, which belongs to the field of clinical application software. Background technique [0002] Brain injury leads to intracranial hemorrhage, and when blood accumulates in the brain to a certain volume, an intracranial hematoma is formed. Usually, a supratenorial hematoma of more than 20ml and an infratentorial blood volume of more than 10ml can cause symptoms of acute craniocerebral compression, which can be life-threatening. Hypertensive cerebral hemorrhage of more than 30ml is a disease with a high morbidity and disability rate in middle-aged and elderly people. Generally, the hematoma on the tentorium is more than 30ml, and the hematoma on the infratentorial is more t...

AI Technical Summary

Problems solved by technology

However, due to the complexity of medical images and the differences between different individuals, at present, no segmentation algorithm can produce satisfactory segmentation results for all images, and at the same time, there is no specific type of image that can make all algorithms can obtain equally good segmentation results