A Robust Segmentation Method Based on Improved U-Net

Accurately reading spinal CT images is very important in clinical, but it usually costs some minutes and deeply depends on doctor's individual experiences. In this paper, we construct a scheme for spinal fracture lesions segmentation based on U-net, by introducing attention module, combining dilated convolution and U-net to get accurate lesions segmentation. First, we present four network schemes to compete in same data set, then get the best one, DU-net(dilated convolution), which replaces original convolution layer with dilated convolution in both contraction path and expansion path of U-net, to increase receptive field for more lesions feature information. Second, we introduce attention module to DU-net for accurate lesions segmentation by focusing on specific regions to improve lesions recognition of training model. Finally, we get prediction results by trained model of lesions segmentation on test data test. The experimental results show that our presented network has a better lesions segmentation performance than U-net, which can save time and reduce patients' suffering clinically.

Automated summary

In this paper, a scheme for spinal fracture lesions segmentation based on U-net was proposed, which introduces an attention module and dilated convolution to achieve more accurate lesions segmentation. The attention module focuses on specific regions to improve the model's recognition of lesions, while dilated convolution increases the receptive field for more lesion feature information. Experimental results show that the proposed network outperforms U-net in lesions segmentation performance.