Lymph Node Ultrasound Image Segmentation Algorithm Based on Multimodal Image Fusion and DMA-UNet

Lymph nodes are important peripheral immune organs in the human immune system, and a variety of systemic and restrictive diseases can attack lymph nodes, leading to changes in their morphology and structure. Accurate identification of lymph nodes is of great value for the diagnosis, treatment and subsequent evaluation of lymph node diseases. The article firstly proposes a multimodal image fusion method for image preprocessing based on the characteristics of lymph node ultrasound images, and then proposes DMA-UNet based on the UNet network model, which uses residual convolution blocks and multiscale dilated convolution blocks instead of the original single $\mathbf{3} \ast\mathbf{3}$ convolution in the codec structure, enabling the nodes of different sizes to be treated during feature extraction. Meanwhile, a hybrid attention mechanism is used in the jump-long connection path of the UNet network model, which solves the problem that the decoding layer will introduce useless noise and other information besides the detailed features of lymph nodes, and achieves better nodal segmentation results.