Abstract: Accurate extraction of the therapeutic target region in the monitoring ultrasonic image is necessary for high intensity focused ultrasound(HIFU)therapy.However,due to the interference of complex background and large amount of noise in the ultrasonic image,traditional image segmentation algorithms have limitations on the target region segmentation of ultrasonic image.In order to extract the target region in ultrasonic image,a semantic segmentation method combining improved DeepLabv3+network and improved loss function is proposed.On the basis of DeepLabv3+network,dense atrous spatial pyramid pooling(DenseASPP)enhanced by attention mechanism through series connection of DenseASPP structure and channel attention mechanism is added into the DeepLabv3+encoder,and the feature map weighting module is added into the DeepLabv3+decoder to improve the network ability of feature extraction and the segmentation accuracy of the target region edge.In terms of the loss function,the improved loss obtained by combining the Huber loss and the noise-robust Dice loss is used to solve the proportional imbalance problem of multi-category pixel number,while improving the robustness against noise.The ablation experimental results show that the mean intersection over union(MIoU)of segmentation results with improved DeepLabv3+network and with improved DeepLabv3+network trained by the improved loss function increase by 0.46 percent and 0.99 percent respectively compared with the original DeepLabv3+network.Proposed method effectively improves the segmentation accuracy of the target region in the monitoring ultrasonic image for HIFU therapy and has strong robustness against noise.