CoChat
Sign Up
Cited by 93Domain Adaptation and Few-Shot LearningMedical Image Segmentation TechniquesArtificial Intelligence in Healthcare and Education

Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

Open access
Cheplygina, Veronika, de Bruijne, Marleen, Pluim, Josien P.W.·2019·Medical Image Analysis
DOI 10.1016/j.media.2019.03.009
Open this paper in CoChat — free account

Abstract

Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods that can learn with less/other types of supervision, have been proposed. We give an overview of semi-supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research. A dataset with the details of the surveyed papers is available via https://figshare.com/articles/Database_of_surveyed_literature_in_Not-so-supervised_a_survey_of_semi-supervised_multi-instance_and_transfer_learning_in_medical_image_analysis_/7479416.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.media.2019.03.009

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Manual annotation of medical images is labor-intensive, time-consuming, and a significant bottleneck in developing and deploying medical imaging AI, requiring extensive domain expertise.

    “Manual annotation of medical images is a labor-intensive and time-consuming process, posing a significant bottleneck in the development and deployment of robust medical imaging AI systems.”

    From Beyond Manual Annotation: A Human-AI Collaborative Framework for Medical Image Segmentation Using Only "Better or Worse" Expert Feedback (2025) · cites this paper as [5]

    The Introduction (p. 1) says manual labeling is expensive and/or time-consuming and that the lack of labeled data is a frequent problem when applying machine learning to medical images. Section 6.4 (p. 17) discusses expert labels, but the paper does not establish that manual annotation requires extensive domain expertise or specifically identify it as a bottleneck to deployment. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • Methods for leveraging unlabeled data to create better classification models with fewer annotated datasets, e.g. with self-training and active learning, have been proposed.

    “Methods for leveraging unlabeled data to create better classification models with fewer annotated datasets, e.g. with self-training (Cheplygina et al. , 2019) and active learning (Tajbakhsh et al., 2020) have been proposed.”

    From SegQC: a segmentation network-based framework for multi-metric segmentation quality control and segmentation error detection in volumetric medical images (2024) · cites this paper as Cheplygina et al., 2019

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 187 · Cited by 93

Research works printed but not linked: 31

  1. An, L., Adeli, E., Liu, M., Zhang, J., Shen, D., 2016. Semisupervised hierarchical multimodal feature and sample selection for Alzheimers disease diagnosis, in: Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer. pp. 79-87.
  2. Batmanghelich, K.N., Dong, H.Y., Pohl, K.M., Taskar, B., Davatzikos, C., et al., 2011. Disease classification and prediction via semi-supervised dimensionality reduction, in: International Symposium on Biomedical Imaging (ISBI), IEEE. pp. 1086-1090.
  3. Biggio, B., 2010. Adversarial Pattern Classification. Ph.D. thesis. University of Cagliari, Cagliari (Italy).
  4. Borga, M., Andersson, T., Leinhard, O.D., 2016. Semisupervised learning of anatomical manifolds for atlasbased segmentation of medical images, in: International Conference on Pattern Recognition (ICPR), IEEE. pp. 3146-3149.
  5. Chapelle, O., Sch¨ olkopf, B., Zien, A., et al., 2006. Semisupervised learning. volume 2. MIT press Cambridge.
  6. Chen, L., Tong, T., Ho, C.P., Patel, R., Cohen, D., Dawson, A.C., Halse, O., Geraghty, O., Rinne, P.E.M., White, C.J., Nakornchai, T., Bentley, P., Rueckert, D., 2015b. Identification of cerebral small vessel disease using multiple instance learning, in: Medical Image Computing and Computer Assisted Intervention (MICCAI). Springer International Publishing, pp. 523-530.
  7. Chen, Q., Xu, X., Hu, S., Li, X., Zou, Q., Li, Y., 2017a. A transfer learning approach for classification of clinical significant prostate cancers from mpMRI scans, in: SPIE Medical Imaging, International Society for Optics and Photonics. pp. 101344F-101344F.
  8. Cheplygina, V., van Opbroek, A., Ikram, M.A., Vernooij, M.W., de Bruijne, M., 2016a. Asymmetric similarityweighted ensembles for image segmentation, in: International Symposium on Biomedical Imaging (ISBI), IEEE. pp. 273-277.
  9. Cheplygina, V., Perez-Rovira, A., Kuo, W., Tiddens, H., de Bruijne, M., 2016b. Early experiences with crowdsourcing airway annotations in chest CT, in: Large-scale Annotation of Biomedical data and Expert Label Synthesis (MICCAI LABELS), pp. 209-218.
  10. Cheplygina, V., Sørensen, L., Tax, D.M.J., Pedersen, J.H., Loog, M., De Bruijne, M., 2014. Classification of COPD with multiple instance learning, in: International Conference on Pattern Recognition (ICPR), pp. 1508-1513.
  11. Dundar, M.M., Fung, G., Krishnapuram, B., Rao, R.B., 2007. Multiple-instance learning algorithms for computeraided detection. IEEE Transactions on Biomedical Engineering 55, 1015-1021.
  12. Elmahdy, M.S., Abdeldayem, S.S., Yassine, I.A., 2017. Low quality dermal image classification using transfer learning, in: IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), IEEE. pp. 373-376.
  13. Gadermayr, M., Strauch, M., Klinkhammer, B.M., Djudjaj, S., Boor, P., Merhof, D., 2016. Domain adaptive classification for compensating variability in histopathological whole slide images, in: International Conference Image Analysis and Recognition. Springer International Publishing, pp. 616-622.
  14. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y., 2014. Generative adversarial nets, in: Advances in neural information processing systems, pp. 2672-2680.
  15. Guerrero, R., Ledig, C., Rueckert, D., 2014. Manifold alignment and transfer learning for classification of Alzheimer's disease, in: Machine Learning in Medical Imaging (MICCAI MLMI). Springer. volume 8679, pp. 77-84.
  16. Hou, L., Samaras, D., Kurc, T.M., Gao, Y., Davis, J.E., Saltz, J.H., 2015. Efficient multiple instance convolutional neural networks for gigapixel resolution image classification. arXiv preprint .
  17. Iglesias, J.E., Liu, C.Y., Thompson, P., Tu, Z., 2010. Agreement-based semi-supervised learning for skull stripping., in: Medical Image Computing and ComputerAssisted Intervention (MICCAI), pp. 147-154.
  18. Liu, T., Xie, S., Zhang, Y., Yu, J., Niu, L., Sun, W., 2017. Feature selection and thyroid nodule classification using transfer learning, in: International Symposium on Biomedical Imaging (ISBI), IEEE. pp. 1096-1099.
  19. Manivannan, S., Cobb, C., Burgess, S., Trucco, E., 2016. Sub-category classifiers for multiple-instance learning and its application to retinal nerve fiber layer visibility classification, in: Medical Image Computing and Computer Assisted Intervention (MICCAI).
  20. Meier, R., Bauer, S., Slotboom, J., Wiest, R., Reyes, M., 2014. Patient-specific semi-supervised learning for postoperative brain tumor segmentation., in: Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 714-721.
  21. Menegola, A., Fornaciali, M., Pires, R., Bittencourt, F.V., Avila, S., Valle, E., 2017. Knowledge transfer for melanoma screening with deep learning. arXiv preprint arXiv:1703.07479 . · arXiv
  22. Murthy, V., Hou, L., Samaras, D., Kurc, T.M., Saltz, J.H., 2017. Center-focusing multi-task CNN with injected features for classification of glioma nuclear images, in: IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE. pp. 834-841.
  23. Nappi, J.J., Hironaka, T., Regge, D., Yoshida, H., 2016. Deep transfer learning of virtual endoluminal views for the detection of polyps in CT colonography, International Society for Optics and Photonics. pp. 97852B-97852B.
  24. Ribeiro, E., H¨ afner, M., Wimmer, G., Tamaki, T., Tischendorf, J., Yoshida, S., Tanaka, S., Uhl, A., 2017. Exploring texture transfer learning for colonic polyp classification via convolutional neural networks, in: International Symposium on Biomedical Imaging (ISBI), IEEE. pp. 10441048.
  25. van Rikxoort, E., Galperin-Aizenberg, M., Goldin, J., Kockelkorn, T.T.J.P., van Ginneken, B., Brown, M., 2010. Multi-classifier semi-supervised classification of tuberculosis patterns on chest CT scans, in: Pulmonary Image Analysis (MICCAI PIA), pp. 41-48.
  26. Shin, S.Y., Lee, S., Yun, I.D., Lee, K.M., 2017. Joint weakly and semi-supervised deep learning for localization and classification of masses in breast ultrasound images. arXiv preprint arXiv:1710.03778 . · arXiv
  27. Venkatesan, R., Chandakkar, P.S., Li, B., 2015. Simpler non- parametric methods provide as good or better results to multiple-instance learning . International Conference on Computer Vision (ICCV) , 2605-2613doi: 10.1109/ICCV. 2015.299 . · DOI
  28. Vural, V., Fung, G., Krishnapuram, B., Dy, J., Rao, B., 2006. Batch classification with applications in computer aided diagnosis, in: European Conference on Machine Learning (ECML). Springer, pp. 449-460.
  29. Wang, L., Li, S., Chen, Y., Lin, J., Liu, C., Zeng, X., Li, S., 2017. Direct aneurysm volume estimation by multiview semi-supervised manifold learning, in: International Symposium on Biomedical Imaging, IEEE. pp. 1222-1225.
  30. Xu, K., Su, H., Zhu, J., Guan, J.S., Zhang, B., 2016. Neuron segmentation based on CNN with semi-supervised regularization, in: Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 20-28.
  31. Zhou, Z.H., Xu, J.M., 2007. On the relation between multiinstance learning and semi-supervised learning, in: International Conference on Machine learning (ICML), pp. 1167-1174.

Authors
Cheplygina, V., de Bruijne, M., & Pluim, J. P. W.
Affiliations
  • Eindhoven University of Technology (NL)
  • University Medical Center Utrecht (NL)
Corresponding author
Cheplygina, Veronika
ORCID
Venue
Medical Image Analysis
Publisher
Elsevier BV
Published
2019-05
Volume
54
Pages
280-296
ISSN
1361-8415 (ISSN-L)
DOI
10.1016/j.media.2019.03.009
OpenAlex
W2797248706
Cited by
93
References
187
Citations by year
2026: 22 · 2025: 1 · 2024: 5 · 2023: 16 · 2022: 16 · 2021: 10 · 2020: 12 · 2019: 11
FWCI
5.59
Type
journal article
Language
en
Open access
Licence
Locations
  • Medical Image Analysis (publishedVersion)
  • PubMed (publishedVersion)
  • EUR Research Repository (Erasmus University Rotterdam) (publishedVersion, other-oa)
  • arXiv (Cornell University) (submittedVersion)
  • Research at the University of Copenhagen (University of Copenhagen) (submittedVersion)
  • TU/e Research Portal (submittedVersion, other-oa)
  • TU/e Research Portal (submittedVersion)
  • EUR Research Repository (Erasmus University Rotterdam) (submittedVersion, other-oa)
  • RePub (Erasmus University Rotterdam) (submittedVersion, other-oa)
  • Utrecht University Repository (Utrecht University) (submittedVersion)
  • Utrecht University Repository (Utrecht University) (submittedVersion, other-oa)
  • arXiv (Cornell University)
Funders
NWO (639.022.010)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
semi-supervised learning, multiple instance learning, transfer learning, limited labeled data, medical image segmentation, medical image diagnosis
MeSH terms
Supervised Machine Learning, Diagnostic Imaging, Humans, Image Processing, Computer-Assisted

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review