LAUSR

In this paper, we use convolutional neural networks to conduct in-depth research and analysis on the classification and recognition of bone and muscle anatomical imaging graphics of 3D magnetic resonance and design corresponding models for practical applications. A series of medical image segmentation models based on convolutional neural networks is proposed. In this paper, firstly, a separated attention mechanism is introduced in the model, which divides the input data into multiple paths, applies self-attention weights to adjacent data paths, and finally fuses the weighted values to form the basic convolutional block. This structure has multiple parallel data paths, which increases the width of the network and therefore improves the feature extraction capability of the model. Then, this paper proposes a bidirectional feature pyramid for medical image segmentation task, which has top-down and bottom-up data paths, and, together with jump connections, can fully interact with feature maps at different scales. After that, a new activation function Mish is introduced, and its advantages over other activation functions are experimentally demonstrated. Finally, for the situation that medical image annotations are not easy to obtain, a semisupervised learning method is introduced in the model training process, and the effectiveness of this method is experimentally demonstrated. The joint network first denoises the input image, then super-resolution mapping is performed on the noise-removed feature map, and finally, the super-resolution 3D-MR image is obtained. We update the network by combining the denoising loss and super-resolution loss during the joint network training process. The experimental results show that the joint network with denoising first and then super-resolution outperforms the joint network with other task order and outperforms the method that performs the two tasks separately and the proposed method in this paper has the optimal performance.