An aortic contour segmentation algorithm based on active shape model

Abstract

The invention discloses an aortic contour segmentation algorithm based on an active shape model, which mainly overcomes the blurring or discontinuity of the aortic edge caused by the traditional method through the shape constraint, avoids the interference of other tissues, and realizes the accurate segmentation of the aortic arch part and the descending aorta part contour. The realization processis as follows: (1) marking feature points of a training set sample and performing normalizing and registration treatment on the shape vectors to establish a point distribution model; (2) sampling thegray level along the normal direction of the contour boundary of the training sample set to construct the gray level texture model of the training set; (3) searching for the best matching point of each marker point iteratively, and then uniformly performing constraining by the active shape model until the aortic contour converges.

Description

technical field [0001] The invention belongs to the technical field of image processing and relates to an aortic contour segmentation algorithm based on an active shape model, which can be used for accurate segmentation and extraction of the thoracoabdominal aortic contour. Background technique [0002] Aortic dissection (AoD) is the blood in the aortic lumen entering the aortic media-adventitia or media-adventitia junction through the aortic intima tear, resulting in the aortic wall being torn into true lumen and false lumen A pathological state of aortic dissection, the patient may die due to aortic rupture in a short period of time; the disease is critical, with high morbidity and mortality, and the fatality rate of patients with aortic dissection without timely and effective treatment is nearly 50% within 48 hours of onset %; At present, endovascular exclusion is mainly used in the treatment of aortic dissection, and for the surgeon, it is necessary to obtain as much inf...

AI Technical Summary

Problems solved by technology

[0002] Aortic dissection (AoD) is the blood in the aortic lumen entering the aortic media-adventitia or media-adventitia junction through the aortic intima tear, resulting in the aortic wall being torn into true lumen and false lumen A pathological state of aortic dissection, the patient may die due to aortic rupture in a short period of time; the disease is critical, with high morbidity and mortality, and the fatality rate of patients with aortic dissection without timely and effective treatment is nearly 50% within 48 hours of onset %; At present, endovascular exclusion is mainly used in the treatment of aortic dissection, and for the surgeon, it is necessary to obtain as much information as possible about the spatial relationship between the lesion in the aortic vessel and the local adjacency during the operation, so as to achieve accurate diagnosis. Diagnosis, surgery and postoperative evaluation, especially the measurement and analysis of data related to the location, extent, breach and blood flow extrusion of abdominal aortic dissection are crucial; current computerized tomography (Computed Tomography, CT) It has advantages in preoperative diagnosis, postoperative review and prognosis evaluation of aortic dissection, so it has become the most important diagnostic method in aortic dissection surgery; however, each patient needs at least 500 or more two-dimensional CT The overall situation of the aorta is fully displayed; general cardiologists need to rely on personal experience to analyze CT images and reconstruct the three-dimensional model of the aorta in their own brains to realize the assessment of the disease. This work requires a lot of clinical experience and the error is too large. Therefore, the best timing for treatment is often delayed; therefore, it is necessary to use a computer to carry out three-dimensional reconstruction of aortic dissection to assist physicians to have a more three-dimensional and comprehensive understanding of the patient's aorta, and the most important thing in the reconstruction process is to accurately segment the aortic region ; At present, for medical image segmentation algorithms, there are mainly methods such as level set method, C-V model, and region growing; The C-V model is difficult to accurately locate the region of interest, and the obtained region boundary may contain many unnecessary regions; when the region grows for multiple similar regions, although the required region can be accurately positioned, the resulting boundary of the segmentation is not smooth enough. The accuracy is not high; therefore, it is difficult to develop an automatic segmentation algorithm that accurately locates the aortic region

Images