MRF-Snake segmentation-based breast cancer diagnosis system and method

Abstract

An MRF-Snake segmentation-based breast cancer diagnosis system disclosed in the invention comprises an image preprocessing unit, an image segmenting unit, a segmentation result visualization unit, a feature extraction unit and a classification diagnostic unit, wherein the image preprocessing unit is used for preprocessing an original mammary gland MRI image sequence, the image segmenting unit is used for segmenting suspected lesions of each image in the preprocessed image sequence, the segmentation result visualization unit is used for visually displaying each image in a segmented image sequence and extracting edge of lesions in each visualized image, the feature extraction unit is used for compressing a grayscale of each image in the segmented image sequence, a compressed image sequence is obtained, and a characteristic value of each compressed image is extracted; the classification diagnostic unit is used for inputting the extracted characteristic value into a classifier for data training, and whether the lesions are benign or malignant is assessed. According to a breast cancer diagnosis method disclosed in the invention, an MRF and Snake combination-based segmentation method is adopted for accurately segmenting breast cancer lesions, and accurate diagnosis of mammary gland diseases can be effectively assisted.

Description

technical field [0001] The invention belongs to the technical field of post-processing of medical images, and in particular relates to a breast cancer diagnosis system and method based on MRF-Snak segmentation. Background technique [0002] At present, breast cancer screening is an important means to achieve early diagnosis and treatment of breast cancer, which can reduce the mortality rate by 30%. Breast MRI images are an important basis for the early detection and diagnosis of breast cancer. The different manifestations of lesions in breast images have become the only standard for early diagnosis of breast cancer, but its diagnosis is more difficult. Computer-aided diagnosis technology can be used to diagnose breast cancer Segmentation, detection and classification of suspected tumors with specific characteristics. Up to now, computer-aided diagnosis technology has been relatively mature, but there are still defects in diagnostic performance, mainly in the low diagnostic ...

AI Technical Summary

Problems solved by technology

Up to now, computer-aided diagnosis technology has been relatively mature, but there are still defects in diagnostic performance, mainly in the low diagnostic performance. The main reason is the segmentation of suspected tumors, that is, the useful information of lesion images content of

Images