An automatic detection method of vascular adventitia based on intravascular ultrasound images

Abstract

The invention discloses an intravascular ultrasound image based automatic adventitia detection method. The method includes processes: transforming an intravascular ultrasound image from rectangular coordinates to polar coordinates; determining seed points needed by a Fast Marching algorithm; determining marching speed of each pixel needed by the Fast Marching algorithm according to image grayscale and gradient; automatically detecting the adventitia by the aid of the Fast Marching algorithm. The seed points, a termination point and a valid marching speed function are detected automatically, so that automaticity in the detection process is guaranteed; by the Fast Marching algorithm based processing method, simpleness and effectiveness of the detection method are guaranteed, and complexity of an existing algorithm model and dependence on imaging conditions are avoided.

Description

technical field [0001] The present invention relates to the field of medical image processing, in particular to a Fast Marching algorithm and an automatic detection method for intima and intima of blood vessels applied to intravascular ultrasound (IVUS: Intravascular ultrasound) images. Background technique [0002] Intravascular Ultrasound (IVUS: Intravascular Ultrasound) images have very important clinical application value for the diagnosis and treatment of cardiovascular diseases such as atherosclerosis. Diagnosis of atherosclerosis based on IVUS images requires quantitative indicators of atherosclerotic image features such as vessel lumen area and plaque area. The accurate extraction of these quantitative indicators depends on effective vessel edge detection. Manual detection means that doctors manually outline the lumen and adventitia boundaries of blood vessels, which is not only time-consuming and laborious, but also limited by the subjectivity of doctors' experience...

AI Technical Summary

Problems solved by technology

At present, there are three main types of computer automatic detection (segmentation) algorithms for blood vessel edges based on IVUS images: the first type is statistical methods (G. Mendizabal-Ruiz, M. Rivera, et al., “Aprobabilistic segmentation method for the identification of luminal borders in intravascular ultrasound images", IEEE Conference on Computer Vision and Pattern Recognition, pp.1-8, 2008.), statistical modeling of the gray distribution of the image to achieve IVUS image segmentation, so as to detect the edge of the blood vessel, but in the IVUS image Complex image features such as artifacts and calcifications will greatly reduce the accuracy of statistical modeling; the second category is machine learning methods (1.E. G. Bovenkamp, ​​J. Dijkstra, J. G.Bosch, et al., “Multi-agent segmentation of IVUS images”, Patten Recognition, Vol.37, No.4, pp.647-663, 2004; 2. G. Unal, S. Bucher, S. Carlier, et al., “Shape-driven segmentation of the arterial wall in intravascular ultrasoundimages", IEEE Trans. On information technology in biomedicine, Vol.12, No.3, pp.335-346, 2008.), this type of method model is complicated, and it is subject to many restrictions in practical application; the third type is Method based on active contour model (1. Zhang Qi, Wang Yuanyuan, etc., "Active Contour Model and Contourlet Multi-resolution Analysis to Segment Intravascular Ultrasound Images", Optical Precision Engineering, Vol.16, No.11, pp.2301- 311, 2008; 2. X. Zhu, P.Zhang, J. Shao, et al., “A snake-based method for segmentation of intravascular ultrasound images and its in vivo validation”, Ultrasonics, Vol.51, pp.181-189, 2011.), this type of method is simple and easy to implement, but it often needs to give an initial contour line, and the detection results are easily affected by complex image features such as noise

Images