A method and system for automatic detection of breast lumps

Abstract

An embodiment of the present invention provides a method and device for automatically detecting a breast mass, the method comprising: acquiring a breast image to be detected, and acquiring a candidate mass image from the breast image; the candidate mass image is a part of the breast image A sub-image: using the candidate mass image as an input of a pre-built mass recognition model to obtain a detection result of whether a mass appears in the breast position corresponding to the candidate mass image. The method can more accurately complete the segmentation of breast images to be detected, and at the same time use a neural network recognition model pre-built based on a large number of sample data to identify the segmented images and obtain breast masses. This method has strong adaptability and accurate detection Beneficial effect.

Description

technical field [0001] The invention relates to the technical field of image information processing, and more specifically, to a method and system for automatic detection of breast masses. Background technique [0002] With the continuous improvement of the medical level, people will have various image data to assist in the diagnosis of diseases during the medical treatment process. Relevant statistics indicate that imaging data accounts for 90% of hospital data and is increasing at a rate of 30% per year, while radiologists are only increasing at a rate of about 4%. It can be seen that the review of a large amount of imaging data Bring great workload to the doctor. In addition, if doctors review image data for a long time, they are prone to fatigue, which may lead to possible errors in diagnosis. [0003] Breast lesions are a common disease that threatens women's health. In particular, the incidence of breast cancer has jumped to the top of the incidence of female maligna...

AI Technical Summary

Problems solved by technology

Although mammography has many of the above advantages, it still has some unavoidable defects. In particular, only a small part of the information of mammography images can be recognized by human eyes, and it is difficult for experienced doctors to find mammography in time. Tiny calcifications in early-stage breast cancer on X-ray images, delaying treatment for patients

Images