Calculation Method of Color Pixel Density in Doppler Ultrasound

Abstract

The invention discloses a Doppler ultrasound color pixel density computing method. The method comprises the steps of 1 selecting a zone to be processed; 2 resolving R, G and B channel planes of the selected zone and respectively calculating four characteristic planes by adopting the method; 3 utilizing an OTSU method to respectively perform threshold segmentation and restoration on four characteristic planes to obtain a color pixel segmentation result and performing color pixel statistics. The Doppler ultrasound color pixel density computing method can automatically and quickly perform color pixel density statistics, improve the result accuracy, accordingly lay a sound technical basis for lesion recognition and computer-aided diagnosis and providing convenience for doctors.

Description

technical field [0001] The invention relates to the field of biomedical image processing, in particular to the segmentation of Doppler color blood flow images and the statistical method of color pixel density. Background technique [0002] Doppler ultrasound adds pseudo-color coding to ordinary black and white ultrasound, so that we can dynamically observe and study the distribution of blood flow, flow velocity and other characteristics. However, the size of the area occupied by the blood flow cannot be quantitatively analyzed. The color pixel density, that is, the ratio of the area of ​​the colored blood flow to the area of ​​the tumor, is a feature that is of great reference and research value for judging benign or malignant breast tumors. The current method of calculating blood flow area and tumor area is generally to manually mark and then calculate the area by other graphics software, such as Photoshop. But such an approach is inefficient and error-prone. [0003] In...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a method for quickly and accurately calculating the color pixel density of a tumor, which can solve the problem that the segmentation target part and the background of the blood flow map are different from each other, but there are also differences between the segmentation target parts. The big difference is the problem that the effect of the maximum inter-class variance method for the R, G, and B three channels caused by the red class, the blue class and the yellow-green class respectively is not ideal. The specific steps include the following steps:

Images