Automatic Segmentation of Kidney Ultrasound Images Using Deep Supervised Network

Ultrasound imaging has been widely used in the screening of kidney diseases. The segmentation of the kidney in ultrasound images can aid in the diagnosis of clinical diseases. However, segmenting the kidney from ultrasound images is challenging, due to the effects of heterostructure, image quality, and other factors. In this paper, an architecture combining multi-branch and deep supervision strategies is proposed to segment kidneys. Specifically, the architecture consists of two parts: multi-branch encoding network and refined decoding network. The multi-branch encoding network consists of a multi-scale feature input pyramid and three branch encoders. The multi-branch encoding network can reduce the sensitivity of the network to the input data through the multi-scale feature pyramid, and utilize the information exchange between the three branch encoders to improve the generalization ability of the network. In the refined decoding network, the introduction of side-output and boundary sup ervision module can further guide the network to effectively segment the kidney with complete contour. Objective comparisons with several state-of-the-art segmentation methods on six commonly used metrics are performed. The method proposed in this paper has achieved the best results in terms of evaluation indicators and segmentation results, and has a good clinical diagnosis prospect