A review of research and development of semi-supervised learning strategies for medical image processing





Deep Learning, semi-supervised learning, Medical Image Processing, neural network


Accurate and robust segmentation of organs or lesions from medical images plays a vital role in many clinical applications such as diagnosis and treatment planning. With the massive increase in labeled data, deep learning has achieved great success in image segmentation. However, for medical images, the acquisition of labeled data is usually expensive because generating accurate annotations requires expertise and time, especially in 3D images. To reduce the cost of labeling, many approaches have been proposed in recent years to develop a high-performance medical image segmentation model to reduce the labeling data. For example, combining user interaction with deep neural networks to interactively perform image segmentation can reduce the labeling effort. Self-supervised learning methods utilize unlabeled data to train the model in a supervised manner, learn the basics and then perform knowledge transfer. Semi-supervised learning frameworks learn directly from a limited amount of labeled data and a large amount of unlabeled data to get high quality segmentation results. Weakly supervised learning approaches learn image segmentation from borders, graffiti, or image-level labels instead of using pixel-level labeling, which reduces the burden of labeling. However, the performance of weakly supervised learning and self-supervised learning is still limited on medical image segmentation tasks, especially on 3D medical images. In addition to this, a small amount of labeled data and a large amount of unlabeled data are more in line with actual clinical scenarios. Therefore, semi-supervised learning strategies become very important in the field of medical image processing.


Xu Y, Wang Y. Intelligent recognition technology of heavy metal pollution based on deep learning and fuzzy clustering and its application. First International Meeting for Applied Geoscience & Energy; 2021; 2021.

Razzak MI, Naz S, Zaib A. Deep Learning for Medical Image Processing: Overview, Challenges and Future. 2018.

Hesamian MH, Jia W, He X, Kennedy P. Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges. Journal of Digital Imaging 2019, 32(8).

Van Engelen JE, Hoos HH. A survey on semi-supervised learning. Machine Learning 2020, 109(2): 373-440.

Hudelot C, Tami M, Ouali Y. An Overview of Deep Semi-Supervised Learning. 2020.

Ren Z, Kong X, Zhang Y, Wang S. UKSSL: Underlying Knowledge based Semi-Supervised Learning for Medical Image Classification. IEEE Open Journal of Engineering in Medicine and Biology 2023: 1-8.

Yuan J, Chen C, Yang W, Liu M, Xia J, Liu S. A survey of visual analytics techniques for machine learning. Computational Visual Media 2021, 7(1): 3-36.

Pise NN, Kulkarni P. A Survey of Semi-Supervised Learning Methods. IEEE 2008.

Jian-Wei L, Yuan L, Xiong-Lin L. Semi-Supervised Learning Methods. Chinese Journal of Computers 2015.

Wang S, Zhang Y. Grad-CAM:Understanding AI Models. 计算机、材料和连续体(英文) 2023, 76(8): 1321-1324.

Kulis B, Basu S, Dhillon I, Mooney R. Semi-supervised graph clustering: a kernel approach. Machine Learning 2009, 74(1): 1-22.

Cirean DC, Meier U, Gambardella LM, Schmidhuber J. Deep, big, simple neural nets for handwritten digit recognition. Neural computation 2010(12): 22.

Pham DL, Xu C, Prince JL. Current methods in medical image segmentation. Annual Review of Biomedical Engineering 2000, 2(2): 315-337.

Laine S, Aila T. Temporal Ensembling for Semi-Supervised Learning. 2016.

Hendrycks D, Lee K, Mazeika M. Using Pre-Training Can Improve Model Robustness and Uncertainty. 2019.

Mei-Qin H, Jian-Hua S. π-Module Algebra and π-Module Ideal. Mathematics in Practice and Theory 2015.

Klinker F. Exponential moving average versus movingexponentialaverage. Mathematische Semesterberichte 2011, 58(1): 97-107.

Tarvainen A, Valpola H. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. 2017.

Mangarin RA, Chan LV. Needs Analysis on the Competence of Secondary School Mathematics Teachers: Springboard for a Teacher Training Module. International Journal of Research and Innovation in Social Science 2021(03).

O'Connor, Michael, Mcgraw, Robert, Killen, Larry, Reich, Dennis. A computer-based training module for suturing [1] self-directed basic. Medical Teacher 1998.

Xie Q, Dai Z, Hovy EH, Luong T, Le Q. Unsupervised Data Augmentation for Consistency Training. Neural Information Processing Systems; 2020; 2020.

Wang J, Khan MA, Wang S, Zhang Y. SNSVM:SqueezeNet-Guided SVM for Breast Cancer Diagnosis. 计算机、材料和连续体(英文) 2023, 76(8): 2201-2216.

Tanha J, Someren MV, De Bakker M, Bouteny W, Shamounbaranesy J, Afsarmanesh H. Multiclass semi-supervised learning for animal behavior recognition from accelerometer data. IEEE International Conference on Tools with Artificial Intelligence; 2013; 2013.

Chen M, Tan X, Zhang L. An iterative self-training support vector machine algorithm in brain-computer interfaces. Intelligent Data Analysis 2016, 20(1): 67-82.

Tanha J, Someren MV, Afsarmanesh H. Boosting for multiclass semi-supervised learning. Elsevier Science Inc 2014.

Ferguson MBAL, emailprotected, Emailprotected E, Ferguson AL, Andrew L. Ferguson * Andrew L. FergusonPritzker School of Molecular Engineering UoC, Chicago, Illinois , United States*Email: emailprotectedMore by Andrew L. Fergusonhttps://orcid.org/---, a, Lee MBJ, Lee J, Junhee Lee Junhee LeePritzker School of Molecular Engineering UoC, Chicago, Illinois , United StatesMore by Junhee Lee. Permutationally Invariant Networks for Enhanced Sampling (PINES): Discovery of Multimolecular and Solvent-Inclusive Collective Variables.

Tanha J, Van Someren M, Afsarmanesh H. [IEEE 2012 IEEE 12th International Conference on Data Mining (ICDM) - Brussels, Belgium (2012.12.10-2012.12.13)] 2012 IEEE 12th International Conference on Data Mining - An AdaBoost Algorithm for Multiclass Semi-supervised Learning. 2012: 1116-1121.

Dong CDC, Yin YYY, Guo XGX, Yang GYG, Zhou GZG. On Co-Training Style Algorithms. Fourth International Conference on Natural Computation; 2008; 2008.

Chen DD, Wang W, Gao W, Zhou ZH. Tri-net for Semi-Supervised Deep Learning. Twenty-Seventh International Joint Conference on Artificial Intelligence IJCAI-18; 2018; 2018.

Zhou ZH, Li M. Tri-training: exploiting unlabeled data using three classifiers. IEEE Transactions on Knowledge and Data Engineering 2005, 17(11): 1529-1541.

Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. Generative Adversarial Networks. 2014.

Duan X, Lieber CM. Laser-Assisted Catalytic Growth of Single Crystal GaN Nanowires. Journal of the American Chemical Society 2000, 122(1): 188--189.

Creswell A, White T, Dumoulin V, Arulkumaran K, Sengupta B, Bharath AA. Generative Adversarial Networks: An Overview. IEEE Signal Processing Magazine 2017, 35(1): 53-65.

Salimans T, Goodfellow I, Zaremba W, Cheung V, Radford A, Chen X. Improved Techniques for Training GANs. 2016.

Odena A. Semi-Supervised Learning with Generative Adversarial Networks. arXiv; 2016.

Sohn K, Berthelot D, Li CL, Zhang Z, Carlini N, Cubuk ED, Kurakin A, Zhang H, Raffel C. FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence. 2020.

Berthelot D, Carlini N, Goodfellow I, Papernot N, Oliver A, Raffel C. MixMatch: A Holistic Approach to Semi-Supervised Learning. 2019.

Shi Z, Liu L, Liu R. Hodge and Podge: Hybrid Supervised Sound Event Detection with Multi-Hot MixMatch and Composition Consistence Training. European Signal Processing Conference; 2021; 2021.

Zhang H, Cisse M, Dauphin YN, Lopez-Paz D. mixup: Beyond Empirical Risk Minimization. 2017.

Wang ZF. Graph-based semi-supervised learning. Artificial Life&Robotics 2009.

Wang D, Cui P, Zhu W. Structural Deep Network Embedding. Acm Sigkdd International Conference on Knowledge Discovery & Data Mining; 2016; 2016.

Muramatsu J, Miyake S. Construction of Codes for the Wiretap Channel and the Secret Key Agreement From Correlated Source Outputs Based on the Hash Property. IEEE Transactions on Information Theory 2012, 58(2): 671-692.

Joyce JM. Kullback-Leibler Divergence. Springer Berlin Heidelberg 2011.

Lee DH. Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks. 2013.

Shaaban A, Hilton B, Clements K, Dodwell D, Sharma N, Kirwan C, Sawyer E, Maxwell A, Wallis M, Stobart H. The presentation, management and outcome of patients with ductal carcinoma in situ (DCIS) with microinvasion (invasion ≤1mm in size)—results from the UK Sloane Project. British Journal of Cancer 2022, 127: 2125 - 2132.

Xiaomeng_Li, Yu L, Chen H, Heng PA. Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Model. arXiv e-prints 2018.

Li X, Yu L, Chen H, Fu CW, Xing L, Heng PA. Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation. 2021.

B SZA, B JZA, B BTA, C TL, Envelope ZXABP. Multi-modal contrastive mutual learning and pseudo-label re-learning for semi-supervised medical image segmentation - ScienceDirect. Medical Image Analysis 2022.

Li R, Wagner C, Chen X, Auer D. A Generic Ensemble Based Deep Convolutional Neural Network for Semi-Supervised Medical Image Segmentation. 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI); 2020; 2020.

Peiris H, Chen Z, Egan G, Harandi M. Duo-SegNet: Adversarial Dual-Views for Semi-Supervised Medical Image Segmentation. 2021.

Zhang W, Zhu L, Hallinan J, Makmur A, Zhang S, Cai Q, Ooi BC. BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation. arXiv e-prints 2022.

Zhao X, Fang C, Fan DJ, Lin X, Gao F, Li G. Cross-level Contrastive Learning and Consistency Constraint for Semi-supervised Medical Image Segmentation. 2022.

Su JC, Maji S. The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop. 2021.

Li J, Cheng K, Wang S, Morstatter F, Trevino RP, Tang J, Liu H. Feature Selection: A Data Perspective. Association for Computing Machinery (ACM) 2017(6).




How to Cite

S. Yang, “A review of research and development of semi-supervised learning strategies for medical image processing”, EAI Endorsed Trans e-Learn, vol. 9, Jan. 2024.