Inflation of test accuracy due to data leakage in deep learning-based classification of OCT images
Open accessThe DOI matches its Crossref record; 39 of the 40 references it cites were found in a registry or an index.
Abstract
In the application of deep learning on optical coherence tomography (OCT) data, it is common to train classification networks using 2D images originating from volumetric data. Given the micrometer resolution of OCT systems, consecutive images are often very similar in both visible structures and noise. Thus, an inappropriate data split can result in overlap between the training and testing sets, with a large portion of the literature overlooking this aspect. In this study, the effect of improper dataset splitting on model evaluation is demonstrated for three classification tasks using three OCT open-access datasets extensively used, Kermany's and Srinivasan's ophthalmology datasets, and AIIMS breast tissue dataset. Results show that the classification performance is inflated by 0.07 up to 0.43 in terms of Matthews Correlation Coefficient (accuracy: 5% to 30%) for models tested on datasets with improper splitting, highlighting the considerable effect of dataset handling on model evaluation. This study intends to raise awareness on the importance of dataset splitting given the increased research interest in implementing deep learning on OCT data.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures


Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The cited source says what the claim attributes to it.
In the citing paper
“Similar patterns of “identity confounding” data leakage have been documented in studies using functional (Wen et al., 2018) and anatomical (Wen et al., 2020) MRI, optical coherence tomography (OCT) (Tampu et al., 2022), accelerometer and gyroscope recordings from smartphones (Saeb et al., 2017), audio voice recordings (Chaibub Neto et al., 2019; Tougui et al., 2021), and performance on motor tasks”
From Data leakage in deep learning studies of translational EEG (2024) · cites this paper as Tampu et al., 2022
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332
A systematic analysis of performance measures for classification tasks
Sokolova, M., & Lapalme, G. (2009) · Information Processing & Management · doi:10.1016/j.ipm.2009.03.002 · Cited by 7,515
Kuhn, M., & Johnson, K. (2013) · doi:10.1007/978-1-4614-6849-3 · Cited by 6,788
Chicco, D., & Jurman, G. (2020) · BMC Genomics · doi:10.1186/s12864-019-6413-7 · Cited by 6,143
Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning
Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C. S., Liang, H., Baxter, S. L., McKeown, A., Yang, G., Wu, X., Yan, F., et al. (2018) · Cell · doi:10.1016/j.cell.2018.02.010 · Cited by 4,842
Refaeilzadeh, P., Tang, L., & Liu, H. (2009) · Encyclopedia of Database Systems · doi:10.1007/978-0-387-39940-9_565 · Cited by 1,549
Deep Learning Applications in Medical Image Analysis
Ker, J., Wang, L., Rao, J., & Lim, T. (2018) · IEEE Access · doi:10.1109/access.2017.2788044 · Cited by 1,481
Medical image analysis using convolutional neural networks: a review
Anwar, S. M., Majid, M., Qayyum, A., Awais, M., Alnowami, M., & Khan, M. K. (2018) · Journal of Medical Systems · doi:10.1007/s10916-018-1088-1 · Cited by 1,431
Xu, Y., & Goodacre, R. (2018) · Journal of Analysis and Testing · doi:10.1007/s41664-018-0068-2 · Cited by 1,030 · cited 5×
“These were selected among the other open-access datasets for several reasons: (1) they are examples of OCT medical images belonging to two different medical disciplines ( ophthalmology and breast oncology) and showing different tissue structures and textures, (2) they are used in literature to evaluate deep learning-b…”
MethodInfluentialChicco, D., Tötsch, N., & Jurman, G. (2021) · BioData Mining · doi:10.1186/s13040-021-00244-z · Cited by 893
Research works printed but not linked: 1
- Karimian, N., Salehi, H. S., Mahdian, M., Alnajjar, H. & Tadinada, A. Deep learning classifier with optical coherence tomography images for early dental caries detection. In Lasers in Dentistry XXIV, vol. 10473, 1047304 (International Society for Optics and Photonics, 2018).
Cited by
Data leakage in deep learning studies of translational EEG
Brookshire, G., Kasper, J., Blauch, N. M., Wu, Y. C., Glatt, R., Merrill, D. A., Gerrol, S., Yoder, K. J., Quirk, C., & Lucero, C. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1373515 · Cited by 103
“Prior research has shown that leakage of subject-specific information—sometimes referred to as “identity confounding” (Chaibub Neto et al., 2019)—occurs in a number of different research areas.”
BackgroundPredicting Adolescent Mental Health Outcomes Across Cultures: A Machine Learning Approach
Rothenberg, W. A., Bizzego, A., Esposito, G., Lansford, J. E., Al‐Hassan, S. M., Bacchini, D., Bornstein, M. H., Chang, L., Deater-Deckard, K. D., Giunta, L. D., et al. (2023) · Journal of Youth and Adolescence · doi:10.1007/s10964-023-01767-w · Cited by 86
“Importantly, in accordance with best practice, missing data were only imputed after the test and training data sets were partitioned, to ensure that that estimates of predictive performance were not biased (Kapoor & Narayanan, 2022; Tampu et al., 2022).”
MethodChowdhury, M. M., Ayon, R. S., & Hossain, M. S. (2023) · Healthcare Analytics · doi:10.1016/j.health.2023.100297 · Cited by 98
Marzi, C., Giannelli, M., Barucci, A., Tessa, C., Mascalchi, M., & Diciotti, S. (2024) · Scientific Data · doi:10.1038/s41597-023-02421-7 · Cited by 85
Applying oversampling before cross-validation will lead to high bias in radiomics
Demircioğlu, A. (2024) · Scientific Reports · doi:10.1038/s41598-024-62585-z · Cited by 85
“The misapplication of the resampling methods is only one source of data leakage, which can occur on several levels and yield a large positive bias 9,22–25 .”
Method
Metadata
- Authors
- Tampu, I. E., Eklund, A., & Haj-Hosseini, N.
- Affiliations
- Linköping University (SE)
- Corresponding author
- Tampu, Iulian Emil
- Venue
- Scientific Data
- Published
- 2022-09-22
- Volume
- 9
- Issue
- 1
- Pages
- 580-580
- ISSN
- 2052-4463 (ISSN-L)
- PMC
- PMC9500039
- OpenAlex
- W4221151810
- Cited by
- 1
- References
- 40
- Citations by year
- 2024: 1
- Type
- data paper
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Scientific Data (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DiVA (Linkoping University) (submittedVersion, other-oa)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University) (cc-by)
- Funders
- Åke Wiberg Stiftelse (M19-0455, M20-0034, M21-0083)
- Forskningsrådet i Sydöstra Sverige (931466)
- ITEA
- VINNOVA (2021-01954, 2017-02447)
- Linköpings Universitet
- Vetenskapsrådet (2021-01954, 2018-, 2018-05250)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Physical Sciences › Engineering › Biomedical Engineering › Optical Coherence Tomography Applications
- Keywords
- optical coherence tomography, data leakage, dataset splitting, model evaluation, ophthalmology, breast tissue classification
- MeSH terms
- Deep Learning, Humans, Tomography, Optical Coherence
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: Inflation of test accuracy due to data leakage in deep learning-based classification of OCT images. https://app.cochat.ai/papers/10.1038/s41597-022-01618-6
- The paper
- Tampu, I. E., Eklund, A., & Haj-Hosseini, N. (2022). Inflation of test accuracy due to data leakage in deep learning-based classification of OCT images. Scientific Data. https://doi.org/10.1038/s41597-022-01618-6
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.