Breast image obtaining method and device and mammography system

Abstract

The invention provides a breast image obtaining method and device and a mammography system. The breast image obtaining method comprises the steps of segmenting a medical image to obtain a breast area; detecting a breast edge in the medical image according to the gray level change characteristics of the breast edge; determining a breast image based on the breast area and the breast edge. Breast images of medical images of different doses can be obtained with the technical solution; the precision of finally obtained breast images is relatively high and the quality of breast images is improved, so that the misdiagnosis rate is further reduced and the efficiency of diagnosis of doctors on foci of breast areas can be increased to a certain degree.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a breast image acquisition method and device, and a mammography system. Background technique [0002] With the development of computer science and information technology, medical imaging technology has also been developed rapidly, and various medical imaging systems are emerging. Full-field digital mammography (FFDM, full-field digital mammography) has been widely used in the screening and diagnosis of breast cancer. [0003] For medical images obtained by FFDM, the extraction of breast images is a key step in the computer-aided diagnosis based on FFDM. Extracting the breast image can limit the detection range of the lesion within the breast area, thereby reducing the interference of the background area. [0004] At present, the following three methods are usually used to segment breast images: [0005] The first one: Otsu method, which uses a threshold to segment the...

AI Technical Summary

Problems solved by technology

It is relatively simple to use the Otsu method to realize the segmentation of breast images, but the breast images obtained after segmentation are inaccurate and missing

[0006] The second type: the watershed algorithm. Compared with the Otsu method, the breast image obtained by using the watershed algorithm is more accurate than the breast image obtained by using the Otsu method. However, for medical images with high doses, the watershed algorithm obtained after segmentation Breast images are still imprecise

[0007] The third type: Snake algorithm, which uses the Snake algorithm to segment medical images. The breast images obtained by segmentation are more accurate, but the segmentation speed is slow, which is not suitable for actual products.

Images