Processing method of CT cerebral hemorrhage image

Abstract

The invention discloses a treating method of CT cerebral hemorrhage image, comprising: automatically selecting gray level image, binary image of brain tissue or binary image of head of raw data based on nonsingular number and winkling the brain median sagittal plane based on singular number; robustly depicting the asymmetry of instant cerebral hemorrhage to the median sagittal plane based on general asymmetry of dotted pairs area; adaptively figuring out gray threshold of instant cerebral hemorrhage, threshold of general asymmetry, local contrast threshold and partial bulk effect threshold; determining threshold of instant cerebral hemorrhage near the fourth ventricle by searching the axial slice below the pertrous bone; obtaining instant cerebral hemorrhage symmetrical to the median sagittal plane from the obtained unsymmetric hemorrhage; determining darker instant cerebral hemorrhage from determined lighter (higher gray scale) instant cerebral hemorrhage; removing high signal of not instant cerebral hemorrhage; determining instant cerebral hemorrhage pixel due to partial bulk effect, therefore the final instant cerebral hemorrhage image is obtained.

Description

technical field [0001] The invention relates to the technical field of CT image processing, in particular to a processing method for CT cerebral hemorrhage images, which is used to accurately determine the location of acute cerebral hemorrhage regions. Background technique [0002] Acute intracerebral hemorrhage refers to recent hemorrhage in the brain, which is a very urgent and dangerous sign, and its accurate and rapid detection is the prerequisite for effective treatment and treatment. Acute intracerebral hemorrhage is well identified by well-trained radiologists, but can also be erroneous when the hemorrhage is minimal or obscured by normal tissue; well-trained radiologists usually calibrate and calculate manually Cerebral hemorrhage volume, which is not only time-consuming, but also difficult to control accuracy, and the obtained scattered two-dimensional pictures are not the overall three-dimensional information. To make matters worse, when patients with bleeding ent...

AI Technical Summary

Problems solved by technology

Methods that rely on more precise registration of brain atlas and data, where such registration is impossible to achieve precisely, for two reasons: First, due to the low spatial resolution of clinical CT data, it is not possible to precisely determine the Brain landmarks, second, brain tissue may shift or deform after hemorrhage, making it difficult to establish a spatial correspondence between normal brain atlas and abnormal brain tissue. not possible

Shang Bin and Xu Liangxian's "An Automatic Segmentation Method for CT Image Sequences of Cerebral Hemorrhage in Stroke Patients" (Computer Engineering 2004: 33 (Supplement): 356-357) used a method similar to that of Maldjian to first realize the matching of images and brain atlases. Then using the fuzzy C homogeneous clustering identification method, only very simple images can be processed

Images