交换标签部分和交叉监督的半监督医学图像分割

doi:10.3778/j.issn.1002-8331.2310-0062

摘要/Abstract

摘要： 针对目前医学图像分割领域存在的分割精度不高和数据获取成本高、难度大的问题，提出了交换标签部分和交叉监督的半监督医学图像分割算法。交换标签部分算法定位两张图片的标签部分并进行交换，解决数据分布不匹配和经验分布差距问题。将Transformer网络应用在Mean Teachers架构，用于与CNN进行交叉监督，辅助CNN提高伪标签的生成质量。添加在预训练和自训练中加入交换标签后图像的训练策略，扩充训练数据集，使模型能学习到更多特征。在ACDC数据集10%有标签实验中Dice系数达到90.67%，较基准模型提升了2.26个百分点，在ACDC数据集5%有标签实验和PROMISE12数据集20%有标签实验中Dice系数分别达到88.69%和84.34%。与其他方法相比，多个实验各项指标均达到最优，实验结果证明了提出方法的有效性和可靠性。

关键词: 医学图像分割, 半监督, 交换标签部分, 交叉监督

Abstract: A semi-supervised medical image segmentation algorithm incorporating label-part switching and cross-teaching is proposed in response to the current challenges in the field of medical image segmentation, including low segmentation accuracy and high costs and difficulty in data acquisition. The label-part switching algorithm locates and exchanges the label portions of two images, addressing issues related to data distribution mismatch and empirical distribution gaps. The Transformer network is applied in the Mean Teachers architecture, employed for cross-teaching with CNN to assist in improving the quality of pseudo-label generation. A training strategy is introduced for images with swapped labels during pre-training and self-training, expanding the training dataset to enable the model to learn more features. In experiments with 10% labeled data on the ACDC dataset, the Dice coefficient reaches 90.67%, showing a 2.26 percentage points improvement over the baseline model. In experiments with 5% labeled data on the ACDC dataset and 20% labeled data on the PROMISE12 dataset, the Dice coefficients reach 88.69% and 84.34%, respectively. Comparative experiments with other methods demonstrate optimal performance across various metrics, validating the effectiveness and reliability of the proposed approach.

Key words: medical image segmentation, semi-supervised, label-part switching, cross-teaching

罗毅恒, 张俊华, 张剑青. 交换标签部分和交叉监督的半监督医学图像分割[J]. 计算机工程与应用, 2025, 61(4): 253-261.

LUO Yiheng, ZHANG Junhua, ZHANG Jianqing. Semi-Supervised Medical Image Segmentation with Label-Part Switching and Cross-Teaching[J]. Computer Engineering and Applications, 2025, 61(4): 253-261.

参考文献

[1] WANG G T, ZULUAGA M A, LI W Q, et al. DeepIGeoS: a deep interactive geodesic framework for medical image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(7): 1559-1572.
[2] YANG X L, SONG Z X, KING I, et al. A survey on deep semi-supervised learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(9): 8934-8954.
[3] BAI Y H, CHEN D W, LI Q L, et al. Bidirectional copy-paste for semi-supervised medical image segmentation[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 11514-11524.
[4] VASWANI A, SHAZEER N M, PARMAR N, et al. Attention is all you need[J]. arXiv:1706.03762, 2017.
[5] BERNARD O, LALANDE A, ZOTTI C, et al. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved?[J]. IEEE Transactions on Medical Imaging, 2018, 37(11): 2514-2525.
[6] ROTH H R, LU L, FARAG A, et al. DeepOrgan: multi-level deep convolutional networks for automated pancreas segmentation[C]//LNCS 9349: Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 556-564.
[7] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.
[8] FAN T L, WANG G L, LI Y, et al. MA-net: a multi-scale attention network for liver and tumor segmentation[J]. IEEE Access, 2020, 8: 179656-179665.
[9] ISENSEE F, JAEGER P F, KOHL S A A, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation[J]. Nature Methods, 2021, 18(2): 203-211.
[10] CHEN J N, LU Y Y, YU Q H, et al. TransUNet: transformers make strong encoders for medical image segmentation[J]. arXiv:2102.04306, 2021.
[11] YU L Q, WANG S J, LI X M, et al. Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation[C]//Proceedings of the 22nd International Conference on Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2019: 605-613.
[12] KENDALL A, GAL Y. What uncertainties do we need in Bayesian deep learning for computer vision?[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc, 2017: 5580-5590.
[13] TARVAINEN A, VALPOLA H. Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc, 2017: 1195-1204.
[14] WU Y C, XU M F, GE Z Y, et al. Semi-supervised left atrium segmentation with mutual consistency training[C]//Proceedings of the 24th International Conference on Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2021: 297-306.
[15] SHI Y H, ZHANG J, LING T, et al. Inconsistency-aware uncertainty estimation for semi-supervised medical image segmentation[J]. IEEE Transactions on Medical Imaging, 2022, 41(3): 608-620.
[16] WANG X Y, YUAN Y W, GUO D Y, et al. SSA-Net: spatial self-attention network for COVID-19 pneumonia infection segmentation with semi-supervised few-shot learning[J]. Medical Image Analysis, 2022, 79: 102459.
[17] LUO X D, HU M H, SONG T, et al. Semi-supervised medical image segmentation via cross teaching between CNN and transformer[C]//Proceedings of the 5th International Conference on Medical Imaging with Deep Learning, 2022: 820-833.
[18] BASAK H, YIN Z Z. Pseudo-label guided contrastive learning for semi-supervised medical image segmentation[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 19786-19797.
[19] LI S J, ZHANG Y F, YANG X. Semi-supervised cardiac MRI segmentation based on generative adversarial network and variational auto-encoder[C]//Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine. Piscataway: IEEE, 2021: 1402-1405.
[20] CHEN X K, YUAN Y H, ZENG G, et al. Semi-supervised semantic segmentation with cross pseudo supervision[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 2613-2622.
[21] CAO H, WANG Y Y, CHEN J, et al. Swin-Unet: Unet-like pure transformer for medical image segmentation[C]//Proceedings of the 17th European Conference on Computer Vision. Cham: Springer, 2023: 205-218.
[22] LUO X D, LIAO W J, CHEN J N, et al. Efficient semi-supervised gross target volume of nasopharyngeal carcinoma segmentation via uncertainty rectified pyramid consistency[C]//Proceedings of the 24th International Conference on Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2021: 318-329.
[23] WU Y C, WU Z H, WU Q Y, et al. Exploring smoothness and class-separation for semi-supervised medical image segmentation[C]//Proceedings of the 25th International Conference on Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2022: 34-43.
[24] LIU J H, DESROSIERS C, ZHOU Y F. Semi-supervised medical image segmentation using cross-model pseudo-supervision with shape awareness and local context constraints[C]//Proceedings of the 25th International Conference on Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2022: 140-150.