Breast tumor diagnosis system based on magnetic resonance spectrum imaging

Abstract

The invention provides a breast tumor diagnosis system based on magnetic resonance spectrum imaging, comprising a superconduction MR (Magneto Resistance) scanner and a computer system. Through a computer auxiliary detection measure, the breast tumor diagnosis system realizes the early identification diagnosis of a breast tumor and the further diagnosis of breast cancer. Mammary gland magnetic resonance spectrum data are studied by adopting a distinctive manifold study method and projected to a low dimension embedding space, thus not only a low dimension manifold structure hidden in a high dimension magnetic resonance spectrum space can be revealed, but also the identification information in the mammary gland magnetic resonance spectrum data can be efficiently kept; then optimization clustering is carried out on the low dimension identification characteristic by utilizing a clustering method so that data points without the similar identification characteristic are separated to the maximum; and further a cost sensitive mechanism is introduced to achieve misclassification total cost minimization and realize optimization diagnosis of the breast cancer.

Description

technical field [0001] The invention belongs to the field of medical technology, in particular to a breast tumor diagnosis system based on magnetic resonance imaging. Background technique [0002] Breast cancer is one of the common diseases and frequently-occurring diseases of women. In recent years, the morbidity and mortality of breast cancer caused by breast tumors in the female population has been increasing year by year, and it has leapt to the first place in the incidence and mortality of female malignant tumors in my country. Early detection, early diagnosis, and early treatment are the key to reducing the incidence and mortality of breast tumors. At present, the imaging examination methods used for breast mainly include B-ultrasound, mammography and magnetic resonance examination, and magnetic resonance examination is obviously superior to the other two examination methods in terms of showing the location, shape and nature of the lesion. [0003] Nuclear magnetic r...

AI Technical Summary

Problems solved by technology

[0007] The combination of PCA and Support Vector Machine (SVM) has been applied to brain MRS data for brain tissue classification. PCA takes the maximum variance as the criterion and can optimally express the data in the sense of the smallest mean square error, but it cannot Efficiently preserves discriminative information in MRS data, thus not suitable for classification

[0008] LDA is based on the criterion of maximizing the ratio of the inter-class dispersion matrix to the intra-class dispersion matrix, and obtains the projection matrix by solving the generalized Rayleigh quotient problem, which can perform data dimension reduction and classification; but LDA also has defects: it can only Extracting features that are less than the number of marked categories does not consider the difference in category variance, and the small sample problem will cause the algorithm to fail; and the performance of its support vector machine mainly depends on the parameters it chooses. If the parameters are not selected properly, the support vector machine will fail. There may be over-learning or under-learning, and the effect of machine learning is not ideal

This means that the traditional linear feature extraction method cannot effectively discover the intrinsic manifold structure in the magnetic resonance spectroscopy data, so that it cannot effectively realize the dimensionality reduction of the magnetic resonance spectroscopy data; at the same time, the useful features of the data in reality are often not necessarily linear combination of features, linear methods are not suitable for such occasions

Images