An ultrasonic breast tumor morphological quantitative feature extraction method based on a shape histogram

Abstract

The invention discloses an ultrasonic breast tumor morphological quantitative feature extraction method based on a shape histogram. Aiming at defects that in a computer-aided diagnosis system, the traditional ultrasonic breast tumor benign and malignant quantitative feature description is inaccurate. Based on the contour of a breast tumor, a shape histogram of the breast tumor is constructed, andthree morphological quantization characteristics are designed on the basis of the shape histogram, namely the maximum curvature sum, the maximum curvature peak value sum and the maximum curvature standard deviation sum, so as to effectively represent the local benign and malignant difference of the ultrasonic breast tumor; The three morphological quantitative characteristics provided by the invention are applied to the classifier, and the obtained benign and malignant recognition rate of the ultrasonic breast tumor is obviously improved compared with the recognition rate of the traditional morphological quantitative characteristics, so that the practical value is realized. The method can effectively reduce the influence of subjective factors of doctors, is helpful for improving the diagnosis accuracy of the doctors, can be suitable for diagnosis of benign and malignant tumors of other tumors, and has a good application prospect.

Description

technical field [0001] The invention relates to the technical field of computer-aided medical diagnosis, in particular to a method for extracting features of ultrasonic breast tumor morphology quantization based on shape histograms. Background technique [0002] At present, breast cancer is a malignant tumor disease that is often suffered by women all over the world. It has extremely high morbidity and mortality. Showed a rising trend. Ultrasound imaging has become an important means of early detection and diagnosis of breast tumors due to its advantages of no radiation trauma, low cost, real-time portability and other advantages. Ultrasound doctors rely on experience to distinguish between benign and malignant breast tumor images collected by ultrasound. This is a subjective judgment process. The diagnosis result is limited by the doctor's experience, knowledge level, and fatigue. , the diagnostic results may be completely different, and even the same doctor may have diff...

AI Technical Summary

Problems solved by technology

It can be seen that none of them consider the local morphological changes of breast tumors, and the extracted benign and malignant features of breast tumors are not accurate

Images