The DOI matches its Crossref record.
Evaluation of cross-validation protocols for the classification of endoscopic images of colonic polyps
Abstract
We evaluate different cross-validation (CV) protocols for an automated classification of colonic polyps. For this purpose we select six previously developed methods which achieved promising results already in the past. We then evaluate the methods using the cross-validation protocols leave-one-image-out (LOO-CV), leave-one-parent-image-out (LOPIO-CV), leave-one-lesion-out (LOLO-CV), and leave-one-patient-out (LOPO-CV). We show that, in general, the more restrictive cross-validation protocols lead to high results drops. While in case of LOO-CV the accuracies are rather high across all methods evaluated, the picture changes the more strictness a cross-validation mode imposes on the set of training images.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“So, similar to the studies reported previously [47,48] the k-fold cross-validation method is not the optimal method for classifying epoched datasets of EEG signals at this case.”
From Alzheimer's Disease and Frontotemporal Dementia: A Robust Classification Method of EEG Signals and a Comparison of Validation Methods (2021) · cites this paper as [48]
In the citing paper
“Hafner, in 2012, proposed that validation methods using samples from the same participant both in the training and in the test set might produce increased accuracy due to bias because the classifier has been trained with samples very similar to the ones that it must be tested, and referred to the leave-one-patient-out cross-validation method as the most realistic one because in prohibits”
From Alzheimer's Disease and Frontotemporal Dementia: A Robust Classification Method of EEG Signals and a Comparison of Validation Methods (2021) · cites this paper as [48]
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 13
- selesnick, 2005, The dual-tree complex wavelet transform - A coherent framework for multiscale signal and image processing, IEEE Signal Processing Magazine, 22, 123, 10.1109/MSP.2005.1550194 · DOI
- 10.1109/RBME.2011.2175445 · DOI
- 10.1016/0031-3203(95)00067-4 · DOI · Paper page
- 10.1109/ITAB.2009.5394423 · DOI
- 10.1109/18.119732 · DOI
- 10.1136/gut.52.suppl_4.iv7 · DOI
- liedlgruber, 2007, Statistical and structural wavelet packet features for Pit pattern classification in zoom-endoscopic colon images, Proceedings of the 7th WSEAS International Conference on Wavelet Analysis & Multirate Systems (WAMUS'07), 147
- hegenbart, 2011, Systematic assessment of performance prediction techniques in medical image classification - A case study on celiac disease, Proceedings of the 22nd International Conference on Information Processing in Medical Imaging (IPMI'11), 498, 10.1007/978-3-642-22092-0_41 · DOI
- 10.1016/j.media.2011.05.006 · DOI
- 10.1049/cp:20080453 · DOI
- 10.1109/ICPR.2010.667 · DOI
- 10.1136/jcp.47.10.880 · DOI
- kato, 2006, Magnifying colonoscopy as a non-biopsy technique for differential diagnosis of non-neoplastic and neoplastic lesions, World Journal of Gastroenterology, 12, 1416, 10.3748/wjg.v12.i9.1416 · DOI
Cited by
Sorted by citations
Miltiadous, A., Tzimourta, K. D., Giannakeas, N., Tsipouras, M. G., Afrantou, T., Ioannidis, P., & Tzallas, A. T. (2021) · Diagnostics · doi:10.3390/diagnostics11081437 · Cited by 160
Metadata
- Authors
- Hafner, M., Liedlgruber, M., Maimone, S., Uhl, A., Vecsei, A., & Wrba, F.
- Affiliations
- University of Salzburg (AT)
- Medical University of Vienna (AT)
- Venue
- 2012 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS)
- Publisher
- IEEE
- Published
- 2012-06
- Pages
- 1-6
- ISSN
- 1063-7125 (ISSN-L)
- OpenAlex
- W2059495483
- Cited by
- 13
- References
- 0
- Citations by year
- 2026: 1 · 2025: 1 · 2021: 2 · 2019: 1 · 2017: 3 · 2016: 3 · 2015: 1 · 2014: 1
- FWCI
- 4.63
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - IEEE Symposium on Computer-Based Medical Systems (publishedVersion)
- Topics
- Health Sciences › Medicine › Oncology › Colorectal Cancer Screening and Detection
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Keywords
- colonic polyps, endoscopic image classification
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Evaluation of cross-validation protocols for the classification of endoscopic images of colonic polyps. https://app.cochat.ai/papers/10.1109/cbms.2012.6266355
- The paper
- Hafner, M., Liedlgruber, M., Maimone, S., Uhl, A., Vecsei, A., & Wrba, F. (2012). Evaluation of cross-validation protocols for the classification of endoscopic images of colonic polyps. 2012 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS). https://doi.org/10.1109/cbms.2012.6266355
