A Preliminary Analysis of Self-Supervision for Wireless Capsule Endoscopy
Abstract
Human learning relies on both supervised as well as unsupervised tasks in grasping visual semantics in general. Is it then possible to learn meaningful features from data without annotations or even knowledge about the number of inherent classes within a dataset? This problem is open and being heavily researched as of today. However, most of the focus in finding answers lies in the domain of natural images. Despite impressive progress, the state-of-the-art from such methods is rarely, if ever, transferable directly to other domains. In this paper, we veer off from natural images to investigate self-supervised learning in a challenging medical domain, that of wireless capsule endoscopy. We implement self-supervision pipeline, with the adaptation of two different pretext tasks for learning representations and evaluate the utility of the self-supervised features for clinical diagnosis. We further infer that a gap exists between the actual requirements and resulting characteristics of features when trained under inadequately adapted “self-supervision” which is more pronounced in medical domains and discuss the factors that influence this gap.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Nine of the innate relationship studies designed their pre-text task based on different image transformations, including rotation prediction, horizontal flip prediction, reordering shuffled slices, and patch order prediction.
“Nine of these studies designed their innate relationship pre-text task based on different image transformations, including rotation prediction44–47, horizontal flip prediction48, reordering shuffled slices49, and patch order prediction46,50–52.”
From Self-supervised learning for medical image classification: a systematic review and implementation guidelines (2023) · cites this paper as [44]
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
(2008) · Journal of Machine Learning Research · Cited by 33,051 · see citing works
Zhang, R., Isola, P., & Efros, A. A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46487-9_40 · Cited by 3,361 · see citing works
Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
Noroozi, M., & Favaro, P. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_5 · Cited by 2,775 · see citing works
Unsupervised Visual Representation Learning by Context Prediction
Doersch, C., Gupta, A., & Efros, A. A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.167 · Cited by 2,629 · see citing works
Unsupervised Representation Learning by Predicting Image Rotations
Gidaris, S., Singh, P., & Komodakis, N. (2018) · arXiv · doi:10.48550/arxiv.1803.07728 · Cited by 2,477 · see citing works
Learning Representations for Automatic Colorization
Larsson, G., Maire, M., & Shakhnarovich, G. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_35 · Cited by 946 · see citing works
CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise
Lee, K.-H., He, X., Zhang, L., & Yang, L. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00571 · Cited by 506 · see citing works
Mylonaki, M., Fritscher-Ravens, A., & Swain, P. (2003) · Gut · doi:10.1136/gut.52.8.1122 · Cited by 477 · see citing works
Tracking Emerges by Colorizing Videos
Vondrick, C., Shrivastava, A., Fathi, A., Guadarrama, S., & Murphy, K. P. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01261-8_24 · Cited by 393 · see citing works
Software for enhanced video capsule endoscopy: challenges for essential progress
Iakovidis, D. K., & Koulaouzidis, A. (2015) · Nature Reviews Gastroenterology & Hepatology · doi:10.1038/nrgastro.2015.13 · Cited by 203 · see citing works
KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes
Koulaouzidis, A., Iakovidis, D. K., Yung, D. E., et al. (2017) · Endoscopy International Open · doi:10.1055/s-0043-105488 · Cited by 141 · see citing works
Review on the Applications of Deep Learning in the Analysis of Gastrointestinal Endoscopy Images
Du, W., Rao, N., Liu, D., Jiang, H., Luo, C., Li, Z., Gan, T., & Zeng, B. (2019) · IEEE Access · doi:10.1109/access.2019.2944676 · Cited by 117 · see citing works
A critical analysis of self-supervision, or what we can learn from a single image
Asano, Y. M., Rupprecht, C., & Vedaldi, A. (2019) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.48550/arxiv.1904.13132 · Cited by 115 · see citing works
Leenhardt, R., Li, C., Mouel, J. L., Rahmi, G., Saurin, J. C., Cholet, F., Boureille, A., Amiot, X., Delvaux, M. M., Duburque, C., et al. (2020) · Endoscopy International Open · doi:10.1055/a-1035-9088 · Cited by 65 · see citing works
Y-Net: A deep Convolutional Neural Network for Polyp DetectionPreprint
Mohammed, A. K., Yayilgan, S. Y., Farup, I., et al. (2018) · arXiv (Cornell University) · doi:10.13140/rg.2.2.19550.95048 · Cited by 34 · see citing works
Self-citationHow much off-the-shelf knowledge is transferable from natural images to pathology images?
Li, X., & Plataniotis, K. N. (2020) · PLoS ONE · doi:10.1371/journal.pone.0240530 · Cited by 27 · see citing works
Mohammed, A. K., Farup, I., Pedersen, M., et al. (2020) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2020.103062 · Cited by 21 · see citing works
Self-citationVideo Capsule Colonoscopy: Where Will We Be in 2015?
Eliakim, R. (2010) · Gastroenterology · doi:10.1053/j.gastro.2010.09.026 · Cited by 19 · see citing works
Multiple Pretext-Task for Self-Supervised Learning via Mixing Multiple Image TransformationsPreprint
Yamaguchi, S., Kanai, S., Shioda, T., & Takeda, S. (2019) · arXiv (Cornell University) · Cited by 8 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Huang, S.-C., Pareek, A., Jensen, M., Lungren, M. P., Yeung, S., & Chaudhari, A. S. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00811-0 · Cited by 479 · see citing works
“Nine of these studies designed their innate relationship pre-text task based on different image transformations, including rotation prediction 44 – 47 , horizontal fl ip prediction 48 , reordering shuf fl ed slices 49 , and patch order prediction 46,50 – 52 .”
Background
- Authors
- Vats, A., Pedersen, M., & Mohammed, A.
- Affiliations
- Norwegian University of Science and Technology (NO)
- Venue
- 2021 9th European Workshop on Visual Information Processing (EUVIP)
- Publisher
- IEEE
- Published
- 2021-06-23
- Volume
- 9908
- Pages
- 1-6
- OpenAlex
- W3183550611
- Cited by
- 5
- References
- 20
- Citations by year
- 2025: 1 · 2023: 3 · 2022: 1
- FWCI
- 0.46
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- European Workshop on Visual Information Processing (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Health Sciences › Medicine › Gastroenterology › Gastrointestinal Bleeding Diagnosis and Treatment
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Keywords
- self-supervised learning, capsule endoscopy, pretext tasks, representation learning, medical image analysis, diagnosis, feature transferability, unsupervised feature learning
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
