Semi-supervised Segmentation of Medical Images
DOI:
https://doi.org/10.18372/1990-5548.81.18986Keywords:
semi-supervised learning, medical image segmentation, consistency regularization, pseudo-labeling, mean teacher, deep learningAbstract
This article is devoted to the development of a method (algorithm) of medical image segmentation based on semi-supervised learning. Semi-supervised learning methods are shown to have significant potential for improving medical image segmentation through effective use of unlabeled data. However, challenges remain in adapting these methods to the specific characteristics of medical images, such as high variability, class imbalance, and the presence of noise and artifacts. To overcome these difficulties, it is proposed to integrate several approaches (consistency regularization, pseudo-labeling, average teacher model) into a single structure. To increase the robustness and generalizability of the model for different imaging methods, we include industry-specific data supplements tailored to the unique characteristics and challenges of each method. Large-scale experiments on magnetic resonance imaging, computed tomography, and optical coherence tomography datasets demonstrate that the proposed framework significantly outperforms fully supervised and individual semisupervised learning methods, especially in scenarios with low data labeling.
References
S. K. Mathivanan, S. Sonaimuthu, Murugesan S., and et al., “Employing deep learning and transfer learning for accurate brain tumor detection,” Scientific Reports, 14, 2024, Article 7232. https://doi.org/10.1038/s41598-024-57970-7.
O. Ronneberger, P. Fischer, & T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2015, pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
K. Han, V. S. Sheng, Y. Song, Y. Liu, C. Qiu, S. Ma, & Z. Liu, “Deep semi-supervised learning for medical image segmentation: A review,” Expert Systems with Applications, 245, Article 123052, 2024. https://doi.org/10.1016/j.eswa.2023.123052
Ö. Çiçek, A. Abdulkadir, S. S. Lienkamp, T. Brox, & O. Ronneberger, “3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation,” Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2016, pp. 424–432. https://doi.org/10.1007/978-3-319-46723-8_49
O. Oktay, et al., “Attention U-Net: Learning Where to Look for the Pancreas,” 2018. arXiv preprint arXiv:1804.03999.
Z. Zhang, Q. Liu, & Y. Wang, “Road Extraction by Deep Residual U-Net,” IEEE Geoscience and Remote Sensing Letters, 15(5), 2018, pp. 749–753. https://doi.org/10.1109/LGRS.2018.2802944
L. Dai, M. G. Md Johar, & M. Alkawaz, “Review of Semi-supervised Medical Image Segmentation Based on the U-Net,” Academic Journal of Science and Technology, 11, pp. 147–154, 2024. https://doi.org/10.54097/gmhkht38
X. Li, et al. “Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation,” Medical Image Computing and Computer Assisted Intervention – MICCAI 2020, 2020, pp. 559–568. https://doi.org/10.1007/978-3-030-59710-8_60
W. Bai, et al., “Semi-supervised learning for network-based cardiac MR image segmentation,” Medical Image Analysis, 43, 2017, pp. 165–177.
A. Tarvainen, & H. Valpola, “Mean Teachers are Better Role Models: Weight-averaged Consistency Targets Improve Semi-supervised Deep Learning Results,” Advances in Neural Information Processing Systems, 2017, pp. 1195–1204.
C. S. Perone,, P. L. Ballester, & J. Cohen-Adad, “Unsupervised Domain Adaptation for Medical Imaging Segmentation with Self-Ensembling,” NeuroImage, 194, pp. 1–11, 2019. https://doi.org/10.1016/j.neuroimage.2019.03.026
Y. Zhang, L. Yang, J. Chen, & D. Z. Chen, “Deep Adversarial Networks for Biomedical Image Segmentation Utilizing Unannotated Images,” Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 408–416, 2017. https://doi.org/10.1007/978-3-319-66179-7_47
Downloads
Published
Issue
Section
License
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).