Automatic recognizing method and system for ultrasonic radiofrequency metadata

Abstract

The invention provides an automatic recognizing method and system for ultrasonic radiofrequency metadata. The method comprises the following steps: acquiring ultrasonic echo signals, and synthesizing the ultrasonic echo signals into ultrasonic radiofrequency metadata signals; directly carrying out Hilbert unwrapping on the ultrasonic radiofrequency metadata signals to generate demodulated signals; selecting an area-of-interest, extracting feature signals of the demodulated signals in the area-of-interest, and carrying out feature description; inputting the feature signals as input vectors to at least two different classifiers to obtain respective AUC results; selecting one of the classifiers through the AUC result; and setting the recognition result as the final recognition result. Extracted features cover strength, texture and fractal, and features of characterization images can be represented comprehensively; and furthermore, a plurality of classifiers are adopted, the optimal classifier is used, and therefore, the boundedness of the classifiers is overcome.

Description

technical field [0001] The invention belongs to the field of ultrasonic diagnostic imaging, and relates to an automatic identification method and system for ultrasonic radio frequency metadata. Background technique [0002] With the development of technologies in related fields such as electronics, computers, and materials science, ultrasound imaging has become one of the most widely used means of auxiliary diagnosis in clinical practice due to its non-invasive, real-time, convenient operation, and low price. . During the ultrasonic imaging process, it is necessary to collect the original ultrasonic echo signal, and perform a series of processing on the ultrasonic echo signal to obtain the final desired result. [0003] In the prior art, ultrasonic imaging of different manufacturers often adopts different processing techniques, standards are different, and the final imaging results obtained are also different; among the commonly used processing methods, [0004] It usually...

AI Technical Summary

Problems solved by technology

Since the post-processing technology is still in the initial stage of development and the processing capability of the computer, in the prior art, the intermediate processing process adopts the method of dividing the echo signal into I\Q two-way signals, and correspondingly performs processing on the echo signal. Down-sampling and down-bit processing to match the processing power of the computer, so supporting the entire processing flow requires a lot of hardware support, especially the intermediate processing process, which usually requires a dedicated chip or digital signal processor to achieve, resulting in extremely complex processing links; use Orthogonal demodulation technology demodulates ultrasonic signals, which cannot be adaptively demodulated according to the signal frequency; at the same time, nearly 80% of the echo information discarded in the demodulation and down-sampling process of traditional ultrasound contains a large number of tissue microstructures. Information, resulting in the loss of imaging information, so that the quality of the final image is not high, which has an inevitable adverse effect on the statistical characteristics of scientific research; further, in the traditional ultrasound imaging process, usually only select a single classifier, automatically poor adaptability

Images