DLUNet: Semi-supervised Learning based Dual-Light UNet for Multi-organ Segmentation

Haoran Lai, Tao Wang, Shuoling Zhou

Keywords: Semi-supervised learning, UNet, Robust segmentation loss

TL;DR: semi-supervised learning for CT organ segmenation

Abstract: The manual ground truth of abdominal multi-organ is labor-intensive. In order to make full use of CT data, we developed a semi-supervised learning based dual-light UNet. In the training phase, it consists of two light UNets, which make full use of label and unlabeled data simultaneously by using consistent-based learning. Moreover, separable convolution and residual concatenation was introduced light UNet to reduce the computational cost. Further, a robust segmentation loss was applied to improve the performance. In the inference phase, only a light UNet is used, which required low time cost and less GPU memory utilization. The average DSC of this method in the validation set is 0.8718.