Medical ultrasonic image super-resolution reconstruction method based on multi-image fusion

The invention discloses a medical ultrasonic image super-resolution reconstruction method based on multi-image fusion. The method comprises the following steps: preprocessing a collected medical ultrasonic image data set; fusing a plurality of similar medical ultrasonic images of the same case by adopting a contrast-based wavelet image fusion algorithm; extracting texture features of the fused image based on a Gaussian Markov random field model; selecting a low-resolution image pair and a high-resolution image pair for supervised learning according to an automatic image definition evaluation method based on a discrete cosine transform coefficient; constructing a generative adversarial network (GAN) architecture based on a convolutional neural network model CNN to train the training data set; the trained model is used for super-resolution reconstruction of the medical ultrasonic image. According to the method, image fusion, a traditional detail extraction algorithm and a CNN-based generative adversarial networ