Method and device for detecting breast skin lines

Abstract

The invention provides a method and a device for detecting breast skin lines. The method comprises the following steps: inputting an original three-dimensional sequence image of breast tissues, and determining regions of interest of the left and right breasts according to the feature points and feature positions of the breast tissues in the image; according to the statistical distribution of skinline features, strengthening breast skin lines in the regions of interest of the left and right breasts on the image; according to intermediate layer images of the regions of interest of the left andright breasts, respectively determining skin lines on the intermediate layer images of the regions of interest of the left and right breasts via a dynamic planning method; and based on the skin lineson the intermediate layer images of the regions of interest of the left and right breasts, respectively and sequentially determining skin lines on layer images in the regions of interest of the left and right breasts besides the intermediate layers. The technical solution can accurately and effectively realize automatic detection of the breast skin lines.

Description

[0001] This application is a division of a Chinese patent application filed with the Chinese Patent Office on March 11, 2014, with the application number 201410088614.X and the invention title "A method and device for detecting breast skin lines". Technical field [0002] The invention relates to the field of image processing, in particular to a method and device for detecting breast skin lines. Background technique [0003] In clinical practice, breast dynamic contrast-enhanced magnetic resonance images usually contain several magnetic resonance image scan sequences to meet the different needs of radiologists. In order to facilitate the comparison and observation of the enhancement of the breast tissue in the magnetic resonance image before and after the contrast agent is injected, the magnetic resonance image scan sequence usually adopts a T1-weighted fat pressure image sequence. Compared with other types of image sequences, T1-weighted liposuction image sequence has higher nois...

AI Technical Summary

Problems solved by technology

Since T1-weighted fat-suppressed image sequences have higher noise levels, stronger artifact interference, and lower image gray-scale contrast than non-fat-suppressed image sequences, the existing methods on non-fat-suppressed image sequences are not suitable. Suitable for liposuction image sequences

Due to the diversity of the gray scale and gradient distribution of breast skin lines in different scan slices and the same scan slice, the thinner breast skin lines of some patients have lower contrast after liposuction, and the glandular fibrous tissue in the images It is close to the position of the skin line, so the threshold-based detection method or the gradient-based detection method is not enough to accurately extract the breast skin line

Model-based detection methods require a large number of training samples to train the model to obtain more accurate detection results, and the acquisition of these accurate training samples is a more difficult and complicated task

Images