Portable ultrasonic video optimization reconstruction method of multi-channel generative adversarial network

Abstract

A portable ultrasonic video optimization reconstruction method based on an ultrasonic sensing dynamic information integration multi-channel generative adversarial network comprises the following steps: firstly, performing ultrasonic sensing dynamic information integration decomposition on an ultrasonic B-mode image collected by a portable ultrasonic instrument to generate a low-rank part and a sparse part so as to effectively decompose the low-rank part and the sparse part in the image; and through multi-channel generative adversarial networks located on an original image sub-channel, a low-rank sub-channel and a sparse sub-channel respectively, learning an ultrasonic B-mode image collected by a portable ultrasonic instrument through a dynamic/static information cascade transfer learning strategy, obtaining a low-rank part and a sparse part through decomposition, and finally obtaining a reconstruction result after averaging is conducted through an over-fusion layer. According to the method, dynamic information is captured through a cascade transfer learning strategy, a coarse-to-fine learning process is realized, and the reconstruction effect is remarkably improved.

Description

technical field [0001] The invention relates to a technology in the field of image processing, in particular to a portable ultrasonic video optimization reconstruction method based on the integration of ultrasonic perception dynamic information and multi-path generative confrontation network. Background technique [0002] As a new type of ultrasonic imaging equipment, portable ultrasound equipment has great application prospects in many fields such as community medical care, township medical care, and telemedicine. Portable ultrasound equipment has the advantages of simple operation, fast imaging, cheap price and light equipment. However, portable ultrasound equipment is limited by its own size, with low imaging resolution and strong artifact noise. The problem of low imaging quality seriously reduces the diagnostic reliability of portable ultrasound equipment, while the improvement of traditional post-processing methods based on gray distribution is restricted by limited i...

AI Technical Summary

Problems solved by technology

However, the portable ultrasound instrument is limited by its own size, low imaging resolution and strong artifact noise

The problem of low imaging quality seriously reduces the diagnostic reliability of portable ultrasound equipment, while the improvement of traditional post-processing methods based on gray distribution is limited by the limited information collected and cannot break through the limitations of hardware

Images