Method, device, terminal and storage medium for segmenting mammography image

Abstract

The embodiment of the present invention discloses a segmentation method, device, terminal and storage medium of a mammogram image. The method includes: acquiring a mammogram image, and adjusting the contrast of the mammogram image according to the pixel values ​​of the mammogram image; Input the contrast-adjusted mammography image into the pre-trained image segmentation model to output the pre-segmented image of the breast region according to the image segmentation model; perform region filling and / or elimination processing on the pre-segmented image to obtain the target segmentation of the breast region image. By adjusting the contrast of the mammography image, the difference between the background area and the foreground area (breast area and non-breast tissue area) can be highlighted; the pre-segmentation of the breast area in the mammography image can be realized through the pre-trained image segmentation model; through Performing region filling and / or culling processing on pre-segmented images can improve the accuracy of breast segmentation, which is beneficial to front-end display and subsequent research on breast masses and calcifications.

Description

technical field [0001] Embodiments of the present invention relate to image segmentation technologies, and in particular to a segmentation method, device, terminal and storage medium for mammography images. Background technique [0002] At present, mammography examination, also known as molybdenum-palladium examination, uses low-dose X-rays to scan the breast, and obtains high-resolution mammography images through breast tissue absorbing X-rays to varying degrees. By performing breast segmentation on the mammography image, the information of the region of interest in the image can be determined, for example, the type of the region of interest is determined as calcification or mass. Compared with artificial breast examination, more complete and accurate breast information can be obtained through mammography, and the examination method is simple, reliable, non-invasive, reproducible, not limited by age and body shape, so it has been used as a routine breast examination means....

AI Technical Summary

Problems solved by technology

The shortcomings of the existing methods include at least: the binary image obtained by segmentation network segmentation is relatively rough, which is not conducive to front-end display and subsequent research on breast masses and calcifications

Images