A Self-Supervised Learning Frameworks for MRI-Based Medical Image Classification:
A Systematic Review
DOI:
https://doi.org/10.63503/j.ijcma.2025.161Keywords:
Self Supervised Learning, SimCLR, Contrastive Learning, MRI imagesAbstract
In recent years Self Supervised learning has evolved as a framework that eliminates the bottle neck of dependence on labelled data for conventional supervised learning paradigms. It has opened entirely new possibilities by removing dependence on the annotated data, which is particularly useful for medical image classification problems as finding the annotated data is scarce in this domain. In this paper we have gathered and presented a structured view of the usage of SSL framework and techniques for MRI-based medical image classification. We have consolidated a detailed review of this modality that can be practical for future research and experimentation.
References
[1] Huang, S. C., Pareek, A., Jensen, M., Lungren, M. P., Yeung, S., & Chaudhari, A. S. (2023). Self-supervised learning for medical image classification: a systematic review and implementation guidelines. NPJ Digital Medicine, 6(1), 74.
[2] Gui, J., Chen, T., Zhang, J., Cao, Q., Sun, Z., Luo, H., & Tao, D. (2024). A survey on self-supervised learning: Algorithms, applications, and future trends. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 9052-9071.
[3] Azizi, S., Mustafa, B., Ryan, F., Beaver, Z., Freyberg, J., Deaton, J., ... & Norouzi, M. (2021). Big self-supervised models advance medical image classification. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 3478-3488).
[4] Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020, November). A simple framework for contrastive learning of visual representations. In International conference on machine learning (pp. 1597-1607). PmLR.
[5] Xie, Y., Gu, L., Harada, T., Zhang, J., Xia, Y., & Wu, Q. (2024). Rethinking masked image modelling for medical image representation. Medical Image Analysis, 98, 103304.
[6] FIRILDAK, K., & Others. (2024). SimCLR-Based Self-Supervised Learning Approach for Limited Brain MRI and Unlabelled Images.
[7] Dufumier, B. et al. Contrastive Learning with Continuous Proxy Meta-data for 3D MRI Classification. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2021 58–68 (2021).
[8] Li, B., Li, Y. & Eliceiri, K. W. Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. (2021).
[9] Manna, S., Bhattacharya, S. & Pal, U. Interpretive self-supervised pre-training: boosting performance on visual medical data. In Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and Image Processing 1–9 (2021).
[10] . Li, H. et al. Imbalance-Aware Self-supervised Learning for 3D Radiomic Representations. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2021 36–46 (2021).
[11] Fedorov, A. et al. Tasting the cake: evaluating self-supervised generalization on out-of-distribution multimodal MRI data. In RobustML Workshop ICLR 2021 (2021).
[12] Ouyang, J. et al. Self-supervised Longitudinal Neighbourhood Embedding. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2021 80–89 (Springer International Publishing, 2021).
[13] Zhao, Q., Liu, Z., Adeli, E. & Pohl, K. M. Longitudinal Self-Supervised Learning. Med. Image Anal. 71, (2021).
[14] Osin, J. et al. Learning Personal Representations from fMRI by Predicting Neurofeedback Performance. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2020 469–478 (2020).
[15] Fedorov, A. et al. On self-supervised multi-modal representation learning: An application to Alzheimer’s disease. In IEEE 18th International Symposium on Biomedical Imaging (2021).
[16] Manna, S., Bhattacharya, S. & Pal, U. Self-Supervised Representation Learning for Detection of ACL Tear Injury in Knee MR Videos. Pattern Recognit. Lett. 154, 37–43 (2022).
[17] Hashimoto, Y., Ogata, Y., Honda, M. & Yamashita, Y. Deep Feature Extraction for Resting-State Functional MRI by Self-Supervised Learning and Application to Schizophrenia Diagnosis. Front. Neurosci. 15, 696853 (2021).
[18] Dezaki, F. T. et al. Echo-Rhythm Net: Semi-Supervised Learning For Automatic Detection of Atrial Fibrillation in Echocardiography. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI) 110–113 (2021).
[19] . Zhu, Y. Self-supervised Learning for Small Shot COVID-19 Classification. In 2021 3rd International Conference on Information Technology and Computer Communications 36–40 (2021).
[20] Liu, H., Wei, D., Lu, D., Sun, J., Wang, L., & Zheng, Y. (2023, June). M3AE: Multimodal representation learning for brain tumor segmentation with missing modalities. In Proceedings of the AAAI conference on artificial intelligence (Vol. 37, No. 2, pp. 1657-1665).
[21] Haghighi, F., Taher, M. R. H., Zhou, Z., Gotway, M. B. & Liang, J. Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Selfsupervised Learning. IEEE Trans. Med. Imaging, (2021).
[22] Hsieh, W.-T., Lefort-Besnard, J., Yang, H.-C., Kuo, L.-W. & Lee, C.-C. Behavior ScoreEmbedded Brain Encoder Network for Improved Classification of Alzheimer Disease Using Resting State fMRI. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2020, 5486–5489 (2020).
[23] V. R. de Sa, “Learning classification with unlabeled data,” inNeural Inf. Process. Syst., pp. 112–119, 1994.
[24] L. Jing and Y. Tian, “Self-supervised visual feature learning withdeep neural networks: A survey,” IEEE Trans. Pattern Anal. Mach.Intell., vol. 43, no. 11, pp. 4037–4058, 2021.
[25] J. Gui, Z. Sun, Y. Wen, D. Tao, and J. Ye, “A review on genera-tive adversarial networks: Algorithms, theory, and applications,”IEEE T. Knowl. Data Eng., 2022.
