An Improved CT image aorta segmentation method based on an active shape model

Abstract

The invention discloses an improved CT image aorta segmentation method based on an active shape model. A segmentation and extraction method combining a Support vector machine (SVM) and an active shapemodel (ASM) are used to segment and extract the aortic region from the CT images of patients with aortic dissection accurately, which solves the problem of error caused by the large difference between the model and the actual segmentation target in the existing algorithm. The process is as follows: (1) selecting samples from aortic patient CT images to construct a training set and marking the characteristic points of an aortic region in the training set; (2) constructing a shape vector from the feature points of the sample marks and performing normalized registration; (3) reducing the dimension of the vector to determine the main sample components and constructing a statistical shape model; (4) performing gray-scale sampling ofa square matrix centered on feature points to establish a texture model; (5) constructing a support vector machine classifier in the training process of the model; (6) calculating the probability of the marked point set to the contour of the target, and findingthe best matching position.

Description

technical field [0001] The invention belongs to the technical field of medical image processing and relates to an improved active shape model-based CT image aorta segmentation and extraction method, which can be used for automatic segmentation and extraction of the aorta region in the CT scan image of the human chest and abdominal cavity. Background technique [0002] Aortic dissection is a relatively dangerous type of cardiovascular disease at present. The main reason is the rupture of the aortic wall intima caused by high blood pressure. The wall is ruptured, and rescue is very difficult, and the risk is much higher than that of high-risk conditions such as cerebral infarction, myocardial infarction, and malignant tumors; currently, computerized tomography (Computed Tomography, CT) has become the most important diagnostic method in aortic dissection surgery, but due to every A patient with aortic dissection has many CT scan images, usually 500 to 1000. Generally, cardiolog...

AI Technical Summary

Problems solved by technology

[0002] Aortic dissection is a relatively dangerous type of cardiovascular disease at present. The main reason is the rupture of the aortic wall intima caused by high blood pressure. The wall is ruptured, and rescue is very difficult, and the risk is much higher than that of high-risk conditions such as cerebral infarction, myocardial infarction, and malignant tumors; currently, computerized tomography (Computed Tomography, CT) has become the most important diagnostic method in aortic dissection surgery, but due to every A patient with aortic dissection has many CT scan images, usually 500 to 1000. Generally, cardiologists need to analyze the patient’s CT scan image information one by one. The optimal timing of treatment is missed; therefore, domestic and foreign medical diagnostic equipment developers usually use CT scan image sequences of the thoracoabdominal cavity of patients with aortic dissection, and use image processing methods to perform three-dimensional reconstruction of the outer contour of the aorta to assist physicians in understanding the three-dimensional structure of the patient's aorta. Have a relatively three-dimensional and comprehensive understanding of the location and size of the hematoma in detail. The most important thing in the reconstruction process is to accurately segment the aortic region; because the location and shape of the aorta vary greatly among different individuals, and there are other The interference of organs and tissues makes it difficult to accurately segment and extract the aortic region in CT images; currently, the segmentation algorithms for medical CT images mainly include methods based on regions, boundaries and shape models; the main advantages of region-based segmentation methods It is simple and efficient, but it is difficult to obtain satisfactory segmentation results for images with insignificant grayscale differences between different target regions; the boundary-based method is better for image segmentation with obvious edges and low noise, but it is sensitive to noise. Images with complex edges are prone to false edges or discontinuous edges; the advantage of the algorithm based on the active shape model is that it does not need to select the region of interest, and can directly input the entire CT image to achieve segmentation and extraction, which is widely used in practical applications, but when the target segmentation When there is a large difference between some regions and the trained aorta model, there is a certain error; therefore, it is difficult to develop an automatic and accurate extraction algorithm for various aortic region structures in human thoracoabdominal CT images

Images