Method and system for hemorrhage area segmentation in brain CT images based on semi-supervised learning

Abstract

The invention discloses a hemorrhage area segmentation method and system of a cerebral CT image based on semi-supervised learning. The method comprises a semi-supervised model training phase and a semi-supervised model based hemorrhage area segmentation phase; a semi-supervised model is trained in the semi-supervised model training phase; and in the semi-supervised model based hemorrhage area segmentation phase, format conversion is carried out on a 2D CT image sequence which needs intracranial hemorrhage area segmentation, 2D CT images are reconstructed into a 3D space, a super-voxel algorithm is used to divide each 3D image into super voxels in similar sizes, each super voxel serves as a sample extraction feature, and the super voxels are divided into foreground and background portions according to the features by utilizing the trained semi-supervised model. According to the invention, the semi-supervised learning algorithm is introduced and super voxels replace pixels to improve the accuracy of hemorrhage area detection effectively.

Description

technical field [0001] The present invention relates to the fields of machine learning and image processing, in particular to a method and system for segmenting hemorrhage areas in brain CT images based on semi-supervised learning. 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 ind...

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 ble...

Images