Deep learning-based adaptive ultrasound image enhancement method

Abstract

The invention provides a deep learning-based adaptive ultrasound image enhancement method. The method is carried out according to the following steps: training a deep neural network; reading ultrasound image data; dividing the image data into blocks and inputting the blocks into the trained deep neural network, and classifying the deep neural network into a uniform formation region and a structure region; carrying out corresponding data processing on ultrasound block images respectively; and carrying out fusion and whole outputting on the corresponding parts. The step of training the deep neural network also comprises the following steps: collecting picture data, and carrying out grouping pretreatment on the picture data; building a RBM model, and determining the number of layers and the training mode of the model; extracting features, and feeding a group of pictures in the grouped pictures into the RBM to calculate and extract image features; building the neural network, building a deep neural network model by the image features extracted in the previous step; and adopting specific image enhancement and speckle suppression according to classification and identification results, so that the imaging effect of the ultrasound images is effectively improved.

Description

technical field [0001] The invention relates to an image enhancement method, specifically an adaptive ultrasound image enhancement method based on deep learning, and belongs to the technical field of ultrasound image processing. Background technique [0002] Ultrasound medical imaging is widely used in clinic because of its advantages of intuition, convenience, safety, and speed. However, due to the physical characteristics of ultrasound imaging and the related properties of ultrasound probes, ultrasound images often show irregularities while reflecting the contours of human organs. Speckle and artifacts, which greatly affect the image quality and identification of lesions. In response to this situation, the current main ultrasound image enhancement algorithms include anisotropic diffusion, wavelet transform, median filter, etc., but these methods act on the entire image, and it is inevitable that the boundary will be blurred while filtering the noise, or the boundary will b...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the problem of inaccurate image analysis in the process of ultrasonic image processing, the present invention discloses an adaptive ultrasonic image enhancement method capable of self-identifying and processing ultrasonic images with deep learning

Images