English

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

Image and Video Processing 2022-09-23 v1 Computer Vision and Pattern Recognition

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. The code is available in https://github.com/laihaoran/Semi-SupervisednnUNet.

Keywords

Cite

@article{arxiv.2209.10984,
  title  = {DLUNet: Semi-supervised Learning based Dual-Light UNet for Multi-organ Segmentation},
  author = {Haoran Lai and Tao Wang and Shuoling Zhou},
  journal= {arXiv preprint arXiv:2209.10984},
  year   = {2022}
}

Comments

13 page, 3 figures

R2 v1 2026-06-28T01:53:44.116Z