Mammary gland calcification detection method and device

Abstract

The invention discloses a mammary gland calcification detection method and device. The method comprises: acquiring a mammary gland image; inputting the mammary gland image into N calcification detection models, and determining the confidence coefficient of the mammary gland image in each calcification type determined by the N calcification detection models, wherein the N calcification detection models are respectively trained according to each pre-classified calcification type, and the N is a positive integer; and determining a calcification detection result in the mammary gland image according to the confidence coefficient of each calcification type determined by the mammary gland image in the N calcification detection models and a merging rule of each calcification type.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of machine learning, and in particular to a method and device for detecting breast calcification. Background technique [0002] At present, low-dose X-rays are used to examine human breasts to obtain breast images. Through the recognition of breast images, various breast tumors, cysts and other lesions can be detected, which is helpful for early detection of breast cancer and reduces its mortality. The diagnosis of breast imaging is an effective detection method, which can be used to diagnose a variety of female breast-related diseases. Of course, the most important use is still in the screening of breast cancer, especially early breast cancer. Therefore, if we can effectively detect various early manifestations of breast cancer on mammography, it will be of great help to doctors. Generally speaking, the diagnosis of lesions on breast imaging is often based on the detection of les...

AI Technical Summary

Problems solved by technology

For the same lesion, these signs may exist at the same time, making the diagnosis very difficult

Images