Automatic classification method for breast tumor ultrasound images

Abstract

The invention relates to an automatic classification method for breast tumor ultrasound images, and belongs to the technical field of applications of artificial intelligence. According to the invention, quantitative features of the breast tumor ultrasound images are tightly combined, histogram features, color features, profile features, edge features and echo features in the breast tumor ultrasound images are quantified, a decision-making tree, a Naive Bayesian method and a random forest method are selected to serve as machine learning methods, and a decision-making tree, Naive Bayesian and random forest weighted fusion multi-dimensional classification method is proposed to perform recognition on the breast images. The automatic classification method can effectively improve the automatic classification accuracy of the breast tumor ultrasound images.

Description

technical field [0001] The invention relates to an automatic classification method for ultrasound images of breast tumors, belonging to the technical field of artificial intelligence applications. Background technique [0002] At present, the clinical analysis of medical images is mainly completed through the qualitative evaluation of images by doctors, and there is a lack of quantitative measurement of image features. Differences in people's visual perception, experience accumulation, and use of different characteristics and diagnostic criteria lead to differences in the diagnostic results of different doctors. Through computer methods, image features can be extracted and analyzed objectively and quantitatively to solve the limitations of human vision. Image-based computer-aided diagnosis was developed out of this need. [0003] For the automatic classification of breast ultrasound images, from the perspective of recognition methods, the image recognition methods mentione...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem of low automatic classification accuracy of ultrasound images of breast tumors, and closely combine the quantitative features of ultrasound images of breast tumors to quantify the histogram features, color features, contour features, boundary features, and echo features in ultrasound images of breast tumors , choose decision tree, naive Bayesian and random forest methods as machine learning methods, and propose a decision tree, naive Bayesian and random forest weighted fusion multidimensional classification method to recognize breast images

Images