Abstract
Medical imaging cohorts are often confounded by factors such as acquisition devices, hospital sites, patient backgrounds, and many more. As a result, deep learning models tend to learn spurious correlations instead of causally related features, limiting their generalizability to new and unseen data. This problem can be addressed by minimizing dependence measures between intermediate representations of task-related and non-task-related variables. These measures include mutual information, distance correlation, and the performance of adversarial classifiers. Here, we benchmark such dependence measures for the task of preventing shortcut learning. We study a simplified setting using Morpho-MNIST and a medical imaging task with CheXpert chest radiographs. Our results provide insights into how to mitigate confounding factors in medical imaging. The project’s code is publicly available (https://github.com/berenslab/dependence-measures-medical-imaging).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Belghazi, M.I., et al.: Mutual information neural estimation. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 531–540. PMLR (2018)
Castro, D.C., Tan, J., Kainz, B., Konukoglu, E., Glocker, B.: Morpho-mnist: quantitative assessment and diagnostics for representation learning. J. Mach. Learn. Res. 20(178), 1–29 (2019)
Castro, D.C., Walker, I., Glocker, B.: Causality matters in medical imaging. Nat. Commun. 11(1) (2020). https://doi.org/10.1038/s41467-020-17478-w
Falcon, W.: The PyTorch Lightning team: PyTorch Lightning (2019). https://doi.org/10.5281/zenodo.3828935
Fay, L., Cobos, E., Yang, B., Gatidis, S., Küstner, T.: Avoiding shortcut-learning by mutual information minimization in deep learning-based image processing. IEEE Access 11, 64070–64086 (2023). https://doi.org/10.1109/ACCESS.2023.3289397
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, vol. 37, pp. 1180–1189 (2015)
Geirhos, R., et al.: Shortcut learning in deep neural networks. Nat. Mach. Intell. 2(11) (2020). https://doi.org/10.1038/s42256-020-00257-z
Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)
Gretton, A., Borgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. (2012)
He, C., Wang, S., Kang, H., Zheng, L., Tan, T., Fan, X.: Adversarial domain adaptation network for tumor image diagnosis. Int. J. Approx. Reason. 135, 38–52 (2021). https://doi.org/10.1016/j.ijar.2021.04.010
Hu, Q., Wei, Y., Pang, J., Liang, M.: Unsupervised domain adaptation for brain structure segmentation via mutual information maximization alignment. Biomed. Signal Process. Control 90, 105784 (2024). https://doi.org/10.1016/j.bspc.2023.105784
Irvin, J., et al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison (2019)
Kamnitsas, K., et al.: Unsupervised domain adaptation in brain lesion segmentation with adversarial networks. In: Niethammer, M., et al. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 597–609. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59050-9_47
Koch, L.M., Baumgartner, C.F., Berens, P.: Distribution shift detection for the postmarket surveillance of medical ai algorithms: a retrospective simulation study. npj Dig. Med. (2024). https://doi.org/10.1038/s41746-024-01085-w
Liu, X., Thermos, S., Valvano, G., Chartsias, A., O’Neil, A., Tsaftaris, S.A.: Measuring the biases and effectiveness of content-style disentanglement. In: Proceedings of the British Machine Vision Conference (BMVC) (2021)
Müller, S., Koch, L.M., Lensch, H.P.A., Berens, P.: Disentangling representations of retinal images with generative models (2024)
Sun, S., Koch, L.M., Baumgartner, C.F.: Right for the wrong reason: can interpretable ml techniques detect spurious correlations? In: Greenspan, H., et al. (eds.) MICCAI 2023. LNCS, vol. 14221, pp. 425–434. Springer, Heidelberg (2023). https://doi.org/10.1007/978-3-031-43895-0_40
Székely, G.J., Rizzo, M.L., Bakirov, N.K.: Measuring and testing dependence by correlation of distances. Ann. Stat. 35(6) (2007). https://doi.org/10.1214/009053607000000505
Xie, X., Chen, J., Li, Y., Shen, L., Ma, K., Zheng, Y.: MI\(^2\)GAN: generative adversarial network for medical image domain adaptation using mutual information constraint. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12262, pp. 516–525. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59713-9_50
Zhen, X., Meng, Z., Chakraborty, R., Singh, V.: On the versatile uses of partial distance correlation in deep learning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, vol. 13686, pp. 327–346. Springer, Heidelberg (2022). https://doi.org/10.1007/978-3-031-19809-0_19
Acknowledgments
This project was supported by the Hertie Foundation and by the Deutsche Forschungsgemeinschaft under Germany’s Excellence Strategy with the Excellence Cluster 2064 “Machine Learning - New Perspectives for Science”, project number 390727645. This research utilized compute resources at the Tübingen Machine Learning Cloud, INST 37/1057-1 FUGG. PB is a member of the Else Kröner Medical Scientist Kolleg “ClinbrAIn: Artificial Intelligence for Clinical Brain Research”. The authors thank the International Max Planck Research School for Intelligent Systems (IMPRS-IS) for supporting SM.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Ethics declarations
Disclosure of Interests
The authors declare no competing interests.
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Müller, S., Fay, L., Koch, L.M., Gatidis, S., Küstner, T., Berens, P. (2025). Benchmarking Dependence Measures to Prevent Shortcut Learning in Medical Imaging. In: Xu, X., Cui, Z., Rekik, I., Ouyang, X., Sun, K. (eds) Machine Learning in Medical Imaging. MLMI 2024. Lecture Notes in Computer Science, vol 15242. Springer, Cham. https://doi.org/10.1007/978-3-031-73290-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-73290-4_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-73292-8
Online ISBN: 978-3-031-73290-4
eBook Packages: Computer ScienceComputer Science (R0)