摘要
The manual ground truth of abdominal multi-organ is laborintensive. In order to make full use of CT data, we developed a semisupervised 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.
学科与关键词
- MagicNet: Semi-Supervised Multi-Organ Segmentation via Magic-Cube Partition and RecoveryChen, Duowen; Bai, Yunhao; Shen, Wei; Li, Qingli; Yu, Lequan; Wang, Yan*IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, CANADA, 2023-06-17 To 2023-06-24.被引 2
- AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?Ma, Jun; Zhang, Yao; Gu, Song; Zhu, Cheng; Ge, Cheng; Zhang, Yichi; An, Xingle; Wang, Congcong; Wang, Qiyuan; Liu, Xin; Cao, Shucheng; Zhang, Qi; Liu, Shangqing; Wang, Yunpeng; Li, Yuhui; He, Jian; Yang, Xiaoping*IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(10): 6695-6714.被引 81
- Multi-Organ Segmentation with Missing Organs in Abdominal CT ImagesMiyuki Suzuki; Marius George Linguraru; Kazunori OkadaMedical Image Computing and Computer-Assisted Intervention – MICCAI 2012, Springer Berlin Heidelberg, 418-425, 2012.
