Low-dose CT image noise artifact decomposition method based on convolutional sparse coding network

The invention discloses a low-dose CT image noise artifact decomposition method based on a convolutional sparse coding network, and belongs to the technical field of computed tomography. The method comprises the following steps: firstly, acquiring a plurality of groups of matched low-dose and conventional-dose CT images, subtracting to obtain noise artifact images, and forming a training data set; establishing a convolutional sparse coding network about the low-dose CT image and the noise artifact image, and obtaining noise artifact features in the low-dose CT image; training the constructed convolutional sparse coding network by using the training data set to obtain network model parameters; and finally, processing the low-dose CT image by using the trained network to realize the decomposition of noise artifacts in the low-dose CT image. According to the method, the noise artifacts in the low-dose CT image and the human anatomical tissue structure can be effectively distinguished, so that the quality of the