Mitigating Bias in Radiology Machine Learning: 2. Model Development
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
There are increasing concerns about the bias and fairness of artificial intelligence (AI) models as they are put into clinical practice. Among the steps for implementing machine learning tools into clinical workflow, model development is an important stage where different types of biases can occur. This report focuses on four aspects of model development where such bias may arise: data augmentation, model and loss function, optimizers, and transfer learning. This report emphasizes appropriate considerations and practices that can mitigate biases in radiology AI studies. Keywords: Model, Bias, Machine Learning, Deep Learning, Radiology © RSNA, 2022
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
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.
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
A survey on Image Data Augmentation for Deep Learning
Shorten, C., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0197-0 · Cited by 13,203 · cited 1×
“A more intense augmentation strategy, such as adding noise (9) or synthetic data with the same distribution, such as from a screening or diagnosis), researchers may intentionally tune the model toward false-positive cases (unnecessary further evaluation) or false-negative cases (missed diagnoses).”
BackgroundnnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J., & Maier-Hein, K. H. (2021) · Nature Methods · doi:10.1038/s41592-020-01008-z · Cited by 10,477
Neural Networks and the Bias/Variance Dilemma
Geman, S., Bienenstock, E., & Doursat, R. (1992) · Neural Computation · doi:10.1162/neco.1992.4.1.1 · Cited by 3,578
A systematic study of the class imbalance problem in convolutional neural networks
Buda, M., Maki, A., & Mazurowski, M. A. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.011 · Cited by 3,088 · cited 1×
“Oversampling and under-sampling will prevent the model from seeing substantially more instances of one class over others during training, therefore reducing the risk of overfitting (17).”
BackgroundAn Overview of Overfitting and its Solutions
Ying, X. (2019) · Journal of Physics: Conference Series · doi:10.1088/1742-6596/1168/2/022022 · Cited by 2,352
Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data
Gianfrancesco, M. A., Tamang, S., Yazdany, J., & Schmajuk, G. (2018) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2018.3763 · Cited by 1,395
Towards a Better Understanding of Transfer Learning for Medical Imaging: A Case Study
Alzubaidi, L., Fadhel, M. A., Al-Shamma, O., Zhang, J., Santamaría, J., Duan, Y., & R. Oleiwi, S. (2020) · Applied Sciences · doi:10.3390/app10134523 · Cited by 258 · cited 1×
“On the contrary, transfer learning from in-domain datasets such as ChestX-ray8 (43) and CheXpert (44) has been shown to improve performance compared with ImageNet pretrained models (45).”
ResultIdentification of Anonymous MRI Research Participants with Face-Recognition Software
Schwarz, C. G., Kremers, W. K., Therneau, T. M., Sharp, R. R., Gunter, J. L., Vemuri, P., Arani, A., Spychalla, A. J., Kantarci, K., Knopman, D. S., et al. (2019) · New England Journal of Medicine · doi:10.1056/nejmc1908881 · Cited by 215 · cited 1×
“Given the high dimensionality of clinical AI tasks with image-based or large-sized datasets, algorithms can still leverage proxy features to reconstruct the protected features even if sensitive attributes are excluded (14).”
Background
Cited by
Lekadir, K., Frangi, A. F., Porras, A. R., Glocker, B., Cintas, C., Langlotz, C. P., Weicken, E., Asselbergs, F. W., Prior, F., Collins, G. S., et al. (2025) · BMJ · doi:10.1136/bmj-2024-081554 · Cited by 957
“31 35 To correct for any identified biases, mitigation measures should be tested, such as data resampling, bias free representations, and equalised odds postprocessing, 36-40 to verify their impact on both the tool’s fairness and the model’s accuracy.”
Koçak, B., Ponsiglione, A., Stanzione, A., Bluethgen, C., Santinha, J., Ugga, L., Huisman, M., Klontzas, M. E., Cannella, R., & Cuocolo, R. (2024) · Diagnostic and Interventional Radiology · doi:10.4274/dir.2024.242854 · Cited by 168
“51 Simulation methods testing algorithms in various scenarios with Bayesian parameter search have been proposed to identify bias sources of algorithmic performance reduction.”
Drukker, K., Chen, W., Gichoya, J. W., Gruszauskas, N. P., Kalpathy-Cramer, J., Koyejo, S., Myers, K. J., Sá, R. C., Sahiner, B., Whitney, H. M., et al. (2023) · Journal of Medical Imaging · doi:10.1117/1.jmi.10.6.061104 · Cited by 149
Understanding and Mitigating Bias in Imaging Artificial Intelligence
Tejani, A. S., Ng, Y. S., Xi, Y., & Rayan, J. C. (2024) · RadioGraphics · doi:10.1148/rg.230067 · Cited by 138
Survey on Machine Learning Biases and Mitigation Techniques
Siddique, S., Haque, M. A., George, R., Gupta, K. D., Gupta, D., & Faruk, M. J. H. (2023) · Digital · doi:10.3390/digital4010001 · Cited by 78
Metadata
- Authors
- Zhang, K., Khosravi, B., Vahdati, S., Faghani, S., Nugen, F., Rassoulinejad-Mousavi, S. M., Moassefi, M., Jagtap, J. M. M., Singh, Y., Rouzrokh, P., & Erickson, B. J.
- Venue
- Radiology: Artificial Intelligence
- Published
- 2022-09-01
- Volume
- 4
- Issue
- 5
- Pages
- e220010-e220010
- ISSN
- 2638-6100 (ISSN-L)
- OpenAlex
- W4293004928
- Cited by
- 82
- References
- 9
- FWCI
- 4.16
- Type
- journal article
- Language
- en
- Open access
- green
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: Mitigating Bias in Radiology Machine Learning: 2. Model Development. https://app.cochat.ai/papers/10.1148/ryai.220010
- The paper
- Zhang, K., Khosravi, B., Vahdati, S., Faghani, S., Nugen, F., Rassoulinejad-Mousavi, S. M., Moassefi, M., Jagtap, J. M. M., Singh, Y., Rouzrokh, P., & Erickson, B. J. (2022). Mitigating Bias in Radiology Machine Learning: 2. Model Development. Radiology: Artificial Intelligence. https://doi.org/10.1148/ryai.220010
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.