Method and device for detecting tissue boundaries by use of ultrasonic images

Abstract

The invention discloses a method and a device for detecting tissue boundaries by use of ultrasonic images. The method comprises a search step and a detection step, wherein the search step is used for searching an ultrasonic image of a detection target for an initial center point of a target region and determining an initial region boundary curve according to the initial center point; the detection step takes the initial center point as a pole, starts searching for the position of a target region boundary along a polar line passing the pole from an initial region boundary, and calculates the energy functional of gray-scale distribution in different positions, wherein a position corresponding to the minimum value of the energy functional of gray-scale distribution is the boundary of the target region. As the invention first detects the center point and then rapidly detects the boundaries along the polar line, the invention is simpler and rapider in detection. Region segmentation functional adopted in the invention can effectively avoid the influence of ultrasonic image noise and effectively detects weak boundaries. In addition, grey scale correction along the polar line can eliminate the influence of non-uniform fields of image gray-scale distribution.

Description

technical field [0001] The invention relates to an ultrasonic image analysis technology, in particular to a method and device for detecting tissue boundaries using an ultrasonic image. Background technique [0002] Ultrasonography has become an important and non-invasive detection method for displaying the structure and motor function of human organs, and further quantitative analysis of the structure and function of these organs first needs to determine the boundary information of these organs. For example, the quantitative analysis of cardiac function requires the measurement of shape parameters such as the area of ​​the cardiac chamber section and its changes during the cardiac cycle, which requires a clear endocardial boundary. At the same time, border delineation can also be used to track the lesion. In addition, the 3D reconstruction of human organ images also needs to outline the boundaries of the organs as a basis. [0003] As the most commonly used field of human ...

AI Technical Summary

Problems solved by technology

Although this method can remove the influence of noise well, it cannot meet the real-time requirements, and the echocardiographic image cannot simply be regarded as an image containing only the foreground and background, that is, the image of the blood region of the left ventricle and the two tissues of the myocardium. , there are also many areas of blood outside the myocardium of the left ventricle, such as the blood in the right ventricle and atrium

Therefore, directly applying the dual-area gray distribution functional cannot get ideal results

Images