Nipple positioning method and device, and storage medium

Abstract

The embodiment of the invention, which belongs to the field of image processing, discloses a nipple positioning method and device, and a storage medium. The method comprises: a grayscale image of a target image is obtained; a target region image is obtained based on the grayscale image; a first image region located at the outer side of a curve in the target region image is determined; and whethera connection region with the area greater than a preset area exists in the first image region is detected to determine a nipple image and a nipple location is determined based on the nipple type. According to the embodiment of the invention, the nipple types are classified into a convex nipple and an invagination nipple; and nipple positioning is carried out by combining the morphological characteristics of the breast tissue region and the nipple type. Therefore, no searching is needed; the computing complexity caused by determining a searching direction and traversing lots of irrelevant pixels during the searching process is reduced; and the computing efficiency is improved. Moreover, with consideration of the morphological characteristics of the breast tissue region, the positioning accuracy is enhanced.

Description

technical field [0001] Embodiments of the present invention relate to the field of image processing, in particular to a nipple positioning method, device and storage medium. Background technique [0002] Digital imaging technology is currently the main way to detect breast cancer. It can digitally photograph target users under the control of a computer to generate breast tissue images. Breast tissue images are widely used in breast cancer detection, and nipple positioning is a key step in the detection process. Only when the nipple position is accurately positioned can the subsequent detection process be carried out. [0003] see figure 1 In the related art, breast DR (Digital Radiography, digital X imaging) technology is usually used to shoot breast DR images, and an image segmentation algorithm is used to segment the foreground area and background area of ​​the breast DR image, and determine the edge direction of the pectoralis muscle, and divide the edge of the pectorali...

AI Technical Summary

Problems solved by technology

[0004] In the process of implementing the embodiments of the present invention, the inventors found that the above-mentioned related technologies have at least the following problems: First, the search process needs to traverse a large number of irrelevant pixels, which increases the computational complexity and leads to low computational efficiency

Second, it is difficult to accurately determine the direction of the edge of the pectoral muscle in practical applications, so it is also difficult to accurately determine the search direction, and it is not considered that the position of the farthest pixel searched in some abnormal situations does not represent the position of the nipple, resulting in accurate positioning sex is not guaranteed

Images