Method for converting low-frequency ultrasonic image into high-frequency ultrasonic image

Abstract

The invention, which relates to the field of image processing, discloses a method for converting a low-frequency ultrasonic image into a high-frequency ultrasonic image. The method comprises: a three-dimensional low-frequency ultrasonic image is obtained, wherein the three-dimensional low-frequency ultrasonic image includes c layers of two-dimensional images, n image blocks are selected at the same position of each layer of two-dimensional image, and the c and n are positive integers; the n image blocks include a first image block and (n-1) other image blocks, wherein the first image block andthe (n-1) other image blocks have the same sizes, the first image block is one part of an original two-dimensional image, and the (n-1) other image blocks are obtained by down sampling on original two-dimensional images in a different larger range using the first image block as the center; and the selected c*n image blocks are inputted into a trained c*n-channel neural network to output a high-frequency ultrasonic image. Therefore, the low-frequency ultrasonic image can be converted into the high-frequency ultrasonic image to obtain an image with reduced noises, large depth, and fast imagingspeed.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for converting a low-frequency ultrasonic image into a high-frequency ultrasonic image. Background technique [0002] The low-frequency ultrasonic images in the prior art are noisy, have the advantages of fast imaging speed, large penetration depth, and low resolution in the depth direction, but have the disadvantage of large noise; and the advantages of high-frequency ultrasonic images produced by high-frequency ultrasonic systems are It has less noise and high resolution in the depth direction, but has the disadvantages of small penetration depth and slow imaging speed. [0003] At present, there are simple ultrasonic noise removal methods such as median filter and Optimized Bayesian Non-Local Mean (OBNLM) in the industry, but these methods cannot improve the resolution of the original image and improve the image quality. [0004] Therefore, it is necessary to provide ...

AI Technical Summary

Problems solved by technology

[0002] The low-frequency ultrasonic images in the prior art are noisy, have the advantages of fast imaging speed, large penetration depth, and low resolution in the depth direction, but have the disadvantage of large noise; and the advantages of high-frequency ultrasonic images produced by high-frequency ultrasonic systems are Less noise, high resolution in the depth direction, but has the disadvantages of small penetration depth and slow imaging speed

[0003] At present, there are simple ultrasonic noise removal methods such as median filter and Optimized Bayesian Non-Local Mean (OBNLM) in the industry, but these methods cannot improve the resolution of the original image and improve the image quality.

Images