A method and system for segmentation of intracranial hemorrhage based on three-dimensional supervoxel

Abstract

The invention discloses a method and system for intracranial hemorrhage region segmentation based on three-dimensional supervoxels. The method includes a CT image preprocessing stage and a bleeding region segmentation stage based on three-dimensional supervoxels; the CT image preprocessing stage is a two-dimensional Transform the format of the CT image sequence, extract the skull structure, and find out the intracranial region; the bleeding region segmentation stage includes reconstructing the 2D partial CT image into a 3D space, and then using the supervoxel algorithm to divide the 3D image into supervoxels of similar size , and finally segment the supervoxels into foreground and background parts by the graph cut algorithm. The invention effectively improves the accuracy of hemorrhage area detection by preprocessing and extracting the intracranial structure, gradually refining and segmenting, and replacing pixels with supervoxels for calculation. The method and the system of the invention can effectively detect bleeding areas of different causes, different positions, and different sizes, and play an important role in promoting the clinical application of computer-aided medical treatment.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a three-dimensional supervoxel-based intracranial hemorrhage region segmentation method and system. Background technique [0002] Intracranial hemorrhage (ICH) is one of the most serious acute cerebrovascular diseases, and it is also an important cause of acute neurological disorders such as hemiplegia. Therefore, for clinical treatment, early diagnosis of intracranial hemorrhage is of great significance. Compared with clinical manifestations, computed tomography (CT) scan and magnetic resonance imaging (MRI) scan, which can be detected without trauma, can more directly and accurately reflect the severity and evolution trend of intracranial hemorrhage. At the same time, because the cost of CT detection is much less than that of MRI detection, most patients will choose CT detection. Fresh hematomas usually appear as hyperluminous areas with indistinct borders on CT images...

AI Technical Summary

Problems solved by technology

First, most of these methods use very simple segmentation algorithms, such as clustering and thresholding, etc., and while these methods may perform well in natural image processing, they do not perform well in complex situations, such as bleeding regions overlapping brain tissue. These methods do not work well when the edges of the bleed or bleed are not sufficiently discriminative

Second, most of the existing algorithms are only suitable for processing two-dimensional images

However, CT imaging is a three-dimensional process, so a series of parallel scanning image frames will be generated, while the 2D segmentation algorithm will ignore some important inter-frame information

Images