Biased data, biased AI: deep networks predict the acquisition site of TCGA images
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
Background: Deep learning models applied to healthcare applications including digital pathology have been increasing their scope and importance in recent years. Many of these models have been trained on The Cancer Genome Atlas (TCGA) atlas of digital images, or use it as a validation source. One crucial factor that seems to have been widely ignored is the internal bias that originates from the institutions that contributed WSIs to the TCGA dataset, and its effects on models trained on this dataset. Methods: 8,579 paraffin-embedded, hematoxylin and eosin stained, digital slides were selected from the TCGA dataset. More than 140 medical institutions (acquisition sites) contributed to this dataset. Two deep neural networks (DenseNet121 and KimiaNet were used to extract deep features at 20× magnification. DenseNet was pre-trained on non-medical objects. KimiaNet has the same structure but trained for cancer type classification on TCGA images. The extracted deep features were later used to detect each slide’s acquisition site, and also for slide representation in image search. Results: DenseNet’s deep features could distinguish acquisition sites with 70% accuracy whereas KimiaNet’s deep features could reveal acquisition sites with more than 86% accuracy. These findings suggest that there are acquisition site specific patterns that could be picked up by deep neural networks. It has also been shown that these medically irrelevant patterns can interfere with other applications of deep learning in digital pathology, namely image search. Summary: This study shows that there are acquisition site specific patterns that can be used to identify tissue acquisition sites without any explicit training. Furthermore, it was observed that a model trained for cancer subtype classification has exploited such medically irrelevant patterns to classify cancer types. Digital scanner configuration and noise, tissue stain variation and artifacts, and source site patient demographics are among factors that likely account for the observed bias. Therefore, researchers should be cautious of such bias when using histopathology datasets for developing and training deep networks.
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
“Similarly, in pathology, variations in tissue preparation, staining protocols, and scanner-specific parameters can impact the data used in cancer-diagnostic tasks41.”
From Bias recognition and mitigation strategies in artificial intelligence healthcare applications (2025) · cites this paper as [41]
In the citing paper
“In The Cancer Genome Atlas (TCGA), measurement bias was observed due to each contributing medical institution employing different protocols for tissue processing, staining, and imaging. These discrepancies introduced systematic variations in the dataset, which were learned by deep learning models, affecting their accuracy, and demonstrating how measurement methods can introduce bias in AI research”
From Bias recognition and mitigation strategies in artificial intelligence healthcare applications (2025) · cites this paper as [41]
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072
scikit-image: image processing in Python
van der Walt, S., Schönberger, J. L., Nunez-Iglesias, J., Boulogne, F., Warner, J. D., Yager, N., Gouillart, E., & Yu, T. (2014) · PeerJ · doi:10.7717/peerj.453 · Cited by 6,794
Review The Cancer Genome Atlas (TCGA): an immeasurable source of knowledge
Tomczak, K., Czerwińska, P., & Wiznerowicz, M. (2015) · Współczesna Onkologia · doi:10.5114/wo.2014.47136 · Cited by 3,492
Coudray, N., Ocampo, P. S., Sakellaropoulos, T., Narula, N., Snuderl, M., Fenyö, D., Moreira, A. L., Razavian, N., & Tsirigos, A. (2018) · Nature Medicine · doi:10.1038/s41591-018-0177-5 · Cited by 2,930 · cited 1×
“Many research groups have trained and validated deep learning models using TCGA images for various tasks ranging from cancer type classification [3–8], tissue segmentation [9, 10] and somatic mutation prediction [3, 5, 8, 11], to survival estimation [4, 12].”
MethodBias in data‐driven artificial intelligence systems—An introductory survey
Ntoutsi, E., Fafalios, P., Gadiraju, U., Iosifidis, V., Nejdl, W., Vidal, M., Ruggieri, S., Turini, F., Papadopoulos, S., Krasanakis, E., et al. (2020) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1356 · Cited by 1,043
Deep Learning for Content-Based Image Retrieval: A Comprehensive Study
Wan, J., Wang, D., Hoi, S. C. H., Wu, P., Zhu, J., Zhang, Y., & Li, J. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654948 · Cited by 811
AI can be sexist and racist — it’s time to make it fair
Zou, J., & Schiebinger, L. (2018) · Nature · doi:10.1038/d41586-018-05707-8 · Cited by 765
Research works printed but not linked: 1
- Khademi A, Honavar V. Algorithmic bias in recidivism prediction: a causal perspective (student abstract). Proc AAAI Conf Artif Intell. 2020;34:13839–40.
Cited by
Algorithmic fairness in artificial intelligence for medicine and healthcare
Chen, R. J., Wang, J. J., Williamson, D. F. K., Chen, T. Y., Lipkova, J., Lu, M. Y., Sahai, S., & Mahmood, F. (2023) · Nature Biomedical Engineering · doi:10.1038/s41551-023-01056-8 · Cited by 750
Ethical and Bias Considerations in Artificial Intelligence/Machine Learning
Hanna, M. G., Pantanowitz, L., Jackson, B., Palmer, O., Visweswaran, S., Pantanowitz, J., Deebajah, M., & Rashidi, H. H. (2025) · Modern Pathology · doi:10.1016/j.modpat.2024.100686 · Cited by 535
Self-citationFederated Learning and Differential Privacy for Medical Image Analysis
Adnan, M., Kalra, S., Cresswell, J. C., Taylor, G. W., & Tizhoosh, H. (2021) · doi:10.21203/rs.3.rs-1005694/v1 · Cited by 464
Self-citationBias recognition and mitigation strategies in artificial intelligence healthcare applications
Hasanzadeh, F., Josephson, C. B., Waters, G., Adedinsewo, D., Azizi, Z., & White, J. A. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01503-7 · Cited by 320
“These discrepancies introduced systematic variations in the dataset, which were learned by deep learning models, affecting their accuracy, and demonstrating how measurement methods can introduce bias in AI research 41 .”
Computational pathology: A survey review and the way forward
Hosseini, M. S., Bejnordi, B. E., Trinh, V. Q., Chan, L., Hasan, D., Li, X., Yang, S. C., Kim, T., Zhang, H., Wu, T., et al. (2024) · Journal of Pathology Informatics · doi:10.1016/j.jpi.2023.100357 · Cited by 176
Metadata
- Authors
- Dehkharghanian, T., Bidgoli, A. A., Riasatian, A., Mazaheri, P., Campbell, C. J. V., Pantanowitz, L., Tizhoosh, H. R., & Rahnamayan, S.
- Affiliations
- University Health Network (CA)
- Brock University (CA)
- University of Waterloo (CA)
- Ontario Tech University (CA)
- William Osler Health System (CA)
- University of Michigan (US)
- Mayo Clinic (US)
- Corresponding author
- Rahnamayan, Shahryar
- ORCID
- Venue
- Diagnostic Pathology
- Published
- 2023-05-17
- Volume
- 18
- Issue
- 1
- Pages
- 67-67
- ISSN
- 1746-1596 (ISSN-L)
- PMC
- PMC10189924
- OpenAlex
- W4377010966
- Cited by
- 67
- References
- 33
- Citations by year
- 2026: 25 · 2025: 17 · 2024: 16 · 2023: 6
- FWCI
- 6.03
- Type
- journal article
- 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
- Diagnostic Pathology (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Ontario Research Foundation
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- TCGA, digital pathology, deep feature extraction, DenseNet121, cancer subtyping, image search, data bias, paraffin-embedded tissue
- MeSH terms
- Coloring Agents, Eosine Yellowish-(YS), Hematoxylin, Humans, Neoplasms, Neural Networks, Computer
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: Biased data, biased AI: deep networks predict the acquisition site of TCGA images. https://app.cochat.ai/papers/10.1186/s13000-023-01355-3
- The paper
- Dehkharghanian, T., Bidgoli, A. A., Riasatian, A., Mazaheri, P., Campbell, C. J. V., Pantanowitz, L., Tizhoosh, H. R., & Rahnamayan, S. (2023). Biased data, biased AI: deep networks predict the acquisition site of TCGA images. Diagnostic Pathology. https://doi.org/10.1186/s13000-023-01355-3
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.