Unsupervised medical image registration method and system based on multiple channels and residual attention mechanism

The invention relates to the technical field of medical image registration, in particular to an unsupervised medical image registration method and system based on multiple channels and a residual attention mechanism, and the method comprises the steps: obtaining a to-be-registered medical image, carrying out the registration of the medical image through a preset image registration model, and obtaining a medical image registration result, the medical image to be registered comprises a moving image and a fixed image; wherein the image registration model is a neural network model obtained by performing unsupervised training based on a similarity loss function by using a medical sample; the neural network model comprises an encoder part used for performing feature extraction on an input medical image, a decoder part used for decoding the extracted features and a spatial transformation network used for obtaining a registration image according to a moving image, and the encoder part extracts image features based on