Medical Image Segmentation Based on Semi-Supervised Multi-Scale Consistency Learning

doi:10.19678/j.issn.1000-3428.0069662

Abstract

Abstract:

Deep supervised learning has made remarkable achievements in medical image segmentation. However, it is heavily dependent on a large amount of high-quality, labeled medical image data, which are difficult to obtain. To address this issue, this paper proposes a Semi-Supervised Multi-scale Consistency Network (SSMC-Net) for medical image lesion segmentation. The network architecture of SSMC-Net is built upon a joint training framework, learning from both labeled and unlabeled data. Moreover, to alleviate the loss of details during the down-sampling and up-sampling processes, a Multi-scale Subtraction (MS) module is incorporated to capture a broader spectrum of differential features, including the Subtraction Unit (SU) and Multiple Feature Fusion Unit (MFFU). The SU is responsible for extracting differential information from the multi-scale encoding outputs, and the MFFU selectively merges the most correlated features to provide more precise interactive representations for the decoder. Finally, the loss function is redesigned. The supervised part comprehensively calculates the pixel-level information outputs at various resolutions, whereas the unsupervised part introduces a multi-scale joint consistency loss and designs a distance function to diminish the impact of unreliable samples. Ablation and comparative experiments on the CPD, ATLAS, and ACDC datasets demonstrate that the proposed method achieves superior performance in terms of the Dice Similarity Coefficient (DSC) and F2 value compared to existing semi-supervised segmentation methods, even with only 50% labeled data.

Key words: lesion segmentation, semi-supervised learning, consistency regularization, Multi-scale Subtraction (MS), multiple feature fusions

摘要：

深度监督学习在医学图像分割领域已经取得了显著成就，但它在很大程度上依赖于大量标签数据，难以获取高质量标签的医学图像数据。基于此，提出一种半监督多尺度一致性网络(SSMC-Net)的医学图像病灶分割方法。该方法构建的网络采用联合训练架构，同时从标签数据和无标签数据中学习。此外，为了减少下采样和上采样过程中细节信息的丢失，设计了多尺度减法(MS)模块来捕获更广泛的差分特征，包括减法单元(SU)和多特征融合单元(MFFU)。SU负责提取多尺度编码器中的差分信息，MFFU有选择性地融合其中最相关的重要特征，为解码器提供更精确的特征表示。最后，重新设计了损失函数，在有监督部分综合计算各分辨率下的像素级输出的损失值，在无监督部分提出多尺度联合一致性损失，并设计距离函数来减少不可靠样本的影响。在CPD、ATLAS和ACDC数据集上的实验结果表明，相比现有半监督分割方法，该方法在50%标签占比下的Dice相似系数(DSC)、F2值等关键评价指标更优。

关键词: 病灶分割, 半监督学习, 一致性正则化, 多尺度减法, 多特征融合

LI Ping, ZHANG Xueying, WANG Suzhe, LI Fenglian, ZHANG Hua. Medical Image Segmentation Based on Semi-Supervised Multi-Scale Consistency Learning[J]. Computer Engineering, 2025, 51(10): 295-307.

李萍, 张雪英, 王夙喆, 李凤莲, 张华. 基于半监督多尺度一致性学习的医学影像分割[J]. 计算机工程, 2025, 51(10): 295-307.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0069662

https://www.ecice06.com/EN/Y2025/V51/I10/295

Figures/Tables 21

Fig.1 Overall architecture of SSMC-Net model

Fig.2 MS module

Fig.3 Schematic diagram of SU

Fig.4 Schematic diagram of MFFU

Fig.5 Schematic diagram of loss function computation

Fig.6 Change curves of loss function during model training

Fig.7 Performance changes after improving the loss function

Fig.8 Rain-cloud distribution images and box images before and after loss function improvement

Fig.9 Visualization results of different methods on the CPD dataset

References 38

1	QURESHI I, YAN J H, ABBAS Q, et al. Medical image segmentation using deep semantic-based methods: a review of techniques, applications and emerging trends. Information Fusion, 2023, 90, 316- 352. doi: 10.1016/j.inffus.2022.09.031
2	贾小慧, 张雪英, 王夙喆, 等. 基于双向循环U-Net模型的脑卒中病灶分割方法. 太原理工大学学报, 2022, 53(6): 1127- 1133.
	JIA X H, ZHANG X Y, WANG S Z, et al. Segmentation method of stroke lesions based on bidirectional recurrent U-Net model. Journal of Taiyuan University of Technology, 2022, 53(6): 1127- 1133.
3	CHEN Z. Medical image segmentation based on U-Net. Journal of Physics: Conference Series, 2023, 2547(1): 012010. doi: 10.1088/1742-6596/2547/1/012010
4	QI K H, YANG H, LI C, et al. X-Net: brain stroke lesion segmentation based on depthwise separable convolution and long-range dependencies[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2019: 247-255.
5	RUAN J C, XIE M Y, GAO J S, et al. EGE-UNet: an efficient group enhanced unet for skin lesion segmentation[EB/OL]. [2024-02-18]. https://arxiv.org/pdf/2307.08473.
6	CHEN J N, LU Y Y, YU Q H, et al. TransUNet: Transformers make strong encoders for medical image segmentation[EB/OL]. [2024-02-18]. https://arxiv.org/pdf/2102.04306.
7	WANG S S, LI C, WANG R P, et al. Annotation-efficient deep learning for automatic medical image segmentation. Nature Communications, 2021, 12(1): 5915. doi: 10.1038/s41467-021-26216-9
8	梁爽. 基于深度神经网络的医学图像特征学习与分析[D]. 北京: 北京科技大学, 2022.
	LIANG S. Deep neural network-based feature learning methods for medical image analysis[D]. Beijing: University of Science and Technology Beijing, 2022. (in Chinese)
9	YANG X L, SONG Z X, KING I, et al. A survey on deep semi-supervised learning. IEEE Transactions on Knowledge and Data Engineering, 2022, 35(9): 8934- 8954.
10	CHEN B, JIANG J, WANG X, et al. Debiased self-training for semi-supervised learning. Advances in Neural Information Processing Systems, 2022, 35, 32424- 32437.
11	ZHENG X, FU C, XIE H, et al. Uncertainty-aware deep co-training for semi-supervised medical image segmentation[EB/OL]. [2024-02-18]. https://arxiv.org/pdf/2111.11629.
12	SOULY N, SPAMPINATO C, SHAH M. Semi supervised semantic segmentation using generative adversarial network[C]//Proceedings of the IEEE International Conference on Computer Vision. Washington D.C., USA: IEEE Press, 2017: 5688-5696.
13	CHAITANYA K, ERDIL E, KARANI N, et al. Local contrastive loss with pseudo-label based self-training for semi-supervised medical image segmentation. Medical Image Analysis, 2023, 87, 102792. doi: 10.1016/j.media.2023.102792
14	ZHANG Y Y, GONG Z Q, ZHAO X Y, et al. Uncertainty guided ensemble self-training for semi-supervised global field reconstruction. Complex & Intelligent Systems, 2024, 10(1): 469- 483.
15	LIU X F, XING F X, SHUSHARINA N, et al. ACT: semi-supervised domain-adaptive medical image segmentation with asymmetric co-training[EB/OL]. [2024-02-18]. https://arxiv.org/pdf/2206.02288.
16	PENG J Z, ESTRADA G, PEDERSOLI M, et al. Deep co-training for semi-supervised image segmentation. Pattern Recognition, 2020, 107, 107269. doi: 10.1016/j.patcog.2020.107269
17	HAN L Y, HUANG Y Z, DOU H R, et al. Semi-supervised segmentation of lesion from breast ultrasound images with attentional generative adversarial network. Computer Methods and Programs in Biomedicine, 2020, 189, 105275. doi: 10.1016/j.cmpb.2019.105275
18	邵伟志, 潘丽丽, 雷前慧, 等. 基于一致性正则化与熵最小化的半监督学习算法. 郑州大学学报(理学版), 2021, 53(3): 79- 84.
	SHAO W Z, PAN L L, LEI Q H, et al. Semi-supervised learning algorithm based on the consistency regularization and entropy minimization. Journal of Zhengzhou University (Science Edition), 2021, 53(3): 79- 84.
19	TACK J, YU S Y, JEONG J, et al. Consistency regularization for adversarial robustness[EB/OL]. [2024-02-18]. https://arxiv.org/pdf/2103.04623.
20	LAINE S, AILA T. Temporal ensembling for semi-supervised learning[EB/OL]. [2024-02-18]. https://arxiv.org/pdf/1610.02242.
21	TARVAINEN A, VALPOLA H. Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results[EB/OL]. [2024-02-18]. https://arxiv.org/pdf/1703.01780.
22	LU L Y, YIN M X, FU L Y, et al. Uncertainty-aware pseudo-label and consistency for semi-supervised medical image segmentation. Biomedical Signal Processing and Control, 2023, 79, 583- 592.
23	LUO X, HU M, SONG T, et al. Semi-supervised medical image segmentation via cross teaching between cnn and transformer[EB/OL]. [2024-02-18]. https://arxiv.org/pdf/2112.04894.
24	WU Y, GE Z, ZHANG D, et al. Mutual consistency learning for semi-supervised medical image segmentation. Medical Image Analysis, 2022, 81, 102530. doi: 10.1016/j.media.2022.102530
25	OUALI Y, HUDELOT C, TAMI M. Semi-supervised semantic segmentation with cross-consistency training[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2020: 12674-12684.
26	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 International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2021: 318-329.
27	谢娟英, 张凯云. SOSNet: 一种非对称编码器-解码器结构的非小细胞肺癌CT图像分割模型. 电子学报, 2024, 52(3): 824- 837.
	XIE J Y, ZHANG K Y. SOSNet: an asymmetric encoder-decoder structure model for automatic segmenting non-small cell lung cancer CT images. Acta Electronica Sinica, 2024, 52(3): 824- 837.
28	LAI W S, HUANG J B, AHUJA N, et al. Deep laplacian pyramid networks for fast and accurate super-resolution[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2017: 624-632.
29	ZHAO X Q, ZHANG L H, LU H C. Automatic polyp segmentation via multi-scale subtraction network[EB/OL]. [2024-02-18]. https://arxiv.org/pdf/2108.05082.
30	HURTIK P, TOMASIELLO S, HULA J, et al. Binary cross-entropy with dynamical clipping. Neural Computing and Applications, 2022, 34(14): 12029- 12041. doi: 10.1007/s00521-022-07091-x
31	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 Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). New York, USA: ACM Press, 2019: 605-613.
32	LIEW S L, ANGLIN J M, BANKS N W, et al. A large, open source dataset of stroke anatomical brain images and manual lesion segmentations. Scientific Data, 2018, 5(1): 180001- 180011. doi: 10.1038/sdata.2018.1
33	BERNARD O, LALANDE A, ZOTTI C, et al. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved?. IEEE Transactions on Medical Imaging, 2018, 37(11): 2514- 2525. doi: 10.1109/TMI.2018.2837502
34	SETIAWAN A W. Image segmentation metrics in skin lesion: accuracy, sensitivity, specificity, dice coefficient, Jaccard index, and Matthews correlation coefficient[C]//Proceedings of International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM). Washington D. C., USA: IEEE Press, 2020: 97-102.
35	苏晓东, 李世洲, 赵佳圆, 等. 基于多级叠加和注意力机制的图像语义分割. 计算机工程, 2023, 49(9): 265-271, 278. doi: 10.19678/j.issn.1000-3428.0065940
	SU X D, LI S Z, ZHAO J Y, et al. Image semantic segmentation based on multi-level superposition and attention mechanism. Computer Engineering, 2023, 49(9): 265-271, 278. doi: 10.19678/j.issn.1000-3428.0065940
36	胡帅, 李华玲, 郝德琛. 改进U-Net的多级边缘增强医学图像分割网络. 计算机工程, 2024, 50(4): 286- 293. doi: 10.19678/j.issn.1000-3428.0067779
	HU S, LI H L, HAO D C. Improved multistage edge enhanced medical image segmentation network of U-Net. Computer Engineering, 2024, 50(4): 286- 293. doi: 10.19678/j.issn.1000-3428.0067779
37	CHEN G P, DAI Y, ZHANG J X, et al. MBANet: multi-branch aware network for kidney ultrasound images segmentation. Computers in Biology and Medicine, 2022, 141, 105140. doi: 10.1016/j.compbiomed.2021.105140
38	HUTTENLOCHER D P, KLANDERMAN G A, RUCKLIDGE W J. Comparing images using the Hausdorff distance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(9): 850- 863. doi: 10.1109/34.232073

[1]	ZHU Siyuan, LI Jiasheng, ZOU Danping, HE Di, YU Wenxian. Unstructured Road Defect Detection Algorithm Based on Semi-Supervised Learning [J]. Computer Engineering, 2025, 51(9): 14-24.
[2]	GAO Rui, AN Guocheng, ZOU Danping, PEI Ling. Semi-Supervised Vehicle Detection Algorithm Based on Improved YOLOv5 [J]. Computer Engineering, 2025, 51(3): 300-309.
[3]	YANG Chunxia, JIANG Yao, ZHAI Xuetong, ZHOU Yuanyuan. Multi-View Time Series Prediction Based on Consistent Functional Neural Process [J]. Computer Engineering, 2025, 51(10): 111-120.
[4]	ZHANG Xinbo, ZHANG Xueying, HUANG Lixia, CHEN Guijun. Classification Algorithm and Application Based on Semi-Supervised Deep Auto-Encoder Network [J]. Computer Engineering, 2025, 51(1): 71-80.
[5]	GUO Min, ZHANG Xihan, LI Yang. Integrated Attentional Teacher Mutual Consistency Semi-Supervised Medical Image Segmentation [J]. Computer Engineering, 2024, 50(9): 313-323.
[6]	GU Yonggen, GAO Lingxuan, WU Xiaohong, TAO Jie. Research on Data Sharing of Federated Semi-Supervised Learning with Non-IID [J]. Computer Engineering, 2024, 50(6): 188-196.
[7]	CHEN Zhonglei, YI Peng, CHEN Xiang, HU Tao. Real-time Anomaly Detection Framework via System Calls Based on Integrated Learning [J]. Computer Engineering, 2023, 49(6): 162-169,179.
[8]	LEI Jie, RAO Wenbi, YANG Yanchao, XIONG Shengwu. Pseudo-Label Object Detection Algorithm Based on Classification Uncertainty [J]. Computer Engineering, 2023, 49(1): 49-56.
[9]	SHE Zhaoyang, YAN Xin, XU Guangyi, CHEN Wei, DENG Zhongying. Adverse Drug Reaction Detection Combined with Data Augmentation and Semi-supervised Learning [J]. Computer Engineering, 2022, 48(6): 314-320.
[10]	HU Bin, WANG Xiaojun, ZHANG Lei. A Semi-Supervised Adversarial Robust Model-Agnostic Meta-Learning Method [J]. Computer Engineering, 2022, 48(12): 112-118.
[11]	GAO Wei, WU Shun. Scratch Repairing of Old Photos Based on Multi-Scale Attention Semi-Supervised Learning [J]. Computer Engineering, 2022, 48(10): 245-251,261.
[12]	KANG Lulu, FAN Xingrong, WANG Qianzhu, YANG Xiaoya, MING Rui. Mouse Trajectory Recognition Based on Feature Group Hierarchy and Semi-Supervised Learning [J]. Computer Engineering, 2021, 47(4): 277-284.
[13]	XUE Zihan, PAN Di, HE Li. Optimization of LGC Semi-Supervised Learning Method Combined with Improved Density Peaks Clustering [J]. Computer Engineering, 2021, 47(2): 77-83,89.
[14]	JI Bin, REN Jianjun, ZHENG Xiujuan, TAN Cong, JI Rong, ZHAO Yu, LIU Kai. Application of Improved U-Net in Segmentation of Laryngeal Leukoplakia Lesion [J]. Computer Engineering, 2020, 46(9): 248-253.
[15]	ZHUANG Lichun, ZHANG Zhengjun, ZHANG Naijin, LI Jundi. Improved UDEED Algorithm Based on Nonlinear Logistic Model [J]. Computer Engineering, 2019, 45(7): 208-211.

Please choose a citation manager

Content to export