Abstract
Deep learning models can perform well in complex medical imaging classification tasks, even when basing their conclusions on spurious correlations (i.e. confounders), should they be prevalent in the training dataset, rather than on the causal image markers of interest. This would thereby limit their ability to generalize across the population. Explainability based on counterfactual image generation can be used to expose the confounders but does not provide a strategy to mitigate the bias. In this work, we introduce the first end-to-end training framework that integrates both (i) popular debiasing classifiers (e.g. distributionally robust optimization (DRO)) to avoid latching onto the spurious correlations and (ii) counterfactual image generation to unveil generalizable imaging markers of relevance to the task. Additionally, we propose a novel metric, Spurious Correlation Latching Score (SCLS), to quantify the extent of the classifier reliance on the spurious correlation as exposed by the counterfactual images. Through comprehensive experiments on two public datasets (with the simulated and real visual artifacts), we demonstrate that the debiasing method: (i) learns generalizable markers across the population, and (ii) successfully ignores spurious correlations and focuses on the underlying disease pathology.
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
Burlina, P., Joshi, N., Paul, W., Pacheco, K.D., Bressler, N.M.: Addressing artificial intelligence bias in retinal diagnostics. Transl. Vis. Sci. Technol. 10(2), 13 (2021)
Cohen, J.P., et al.: Gifsplanation via latent shift: a simple autoencoder approach to counterfactual generation for chest X-rays. In: Medical Imaging with Deep Learning, pp. 74–104. PMLR (2021)
DeGrave, A.J., Janizek, J.D., Lee, S.I.: AI for radiographic COVID-19 detection selects shortcuts over signal. Nat. Mach. Intell. 3(7), 610–619 (2021)
Hore, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: 2010 20th International Conference on Pattern Recognition, pp. 2366–2369. IEEE (2010)
Irvin, J., et al.: CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 590–597 (2019)
Jiang, H., et al.: A multi-label deep learning model with interpretable grad-cam for diabetic retinopathy classification. In: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 1560–1563. IEEE (2020)
Kumar, A., et al.: Counterfactual image synthesis for discovery of personalized predictive image markers. In: Kakileti, S.T., et al. (eds.) MIABID AIIIMA 2022 2022. LNCS, vol. 13602, pp. 113–124. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19660-7_11
Larrazabal, A.J., Nieto, N., Peterson, V., Milone, D.H., Ferrante, E.: Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proc. Natl. Acad. Sci. 117(23), 12592–12594 (2020)
Light, R.W.: Pleural effusion. N. Engl. J. Med. 346(25), 1971–1977 (2002)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Magesh, P.R., Myloth, R.D., Tom, R.J.: An explainable machine learning model for early detection of Parkinson’s disease using LIME on DaTSCAN imagery. Comput. Biol. Med. 126, 104041 (2020)
Mehta, R., Shui, C., Arbel, T.: Evaluating the fairness of deep learning uncertainty estimates in medical image analysis. In: Medical Imaging with Deep Learning (2023)
Mertes, S., Huber, T., Weitz, K., Heimerl, A., André, E.: GANterfactual-counterfactual explanations for medical non-experts using generative adversarial learning. Front. Artif. Intell. 5, 825565 (2022)
Mothilal, R.K., Sharma, A., Tan, C.: Explaining machine learning classifiers through diverse counterfactual explanations. In: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pp. 607–617 (2020)
Nemirovsky, D., Thiebaut, N., Xu, Y., Gupta, A.: CounteRGAN: Generating realistic counterfactuals with residual generative adversarial nets. arXiv preprint arXiv:2009.05199 (2020)
Panwar, H., Gupta, P., Siddiqui, M.K., Morales-Menendez, R., Bhardwaj, P., Singh, V.: A deep learning and grad-CAM based color visualization approach for fast detection of COVID-19 cases using chest X-ray and CT-scan images. Chaos, Solitons Fractals 140, 110190 (2020)
Ricci Lara, M.A., Echeveste, R., Ferrante, E.: Addressing fairness in artificial intelligence for medical imaging. Nat. Commun. 13(1), 4581 (2022)
Sagawa, S., Koh, P.W., Hashimoto, T.B., Liang, P.: Distributionally robust neural networks for group shifts: on the importance of regularization for worst-case generalization. In: International Conference on Learning Representations (2019)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Shui, C., Szeto, J., Mehta, R., Arnold, D., Arbel, T.: Mitigating calibration bias without fixed attribute grouping for improved fairness in medical imaging analysis. arXiv preprint arXiv:2307.01738 (2023)
Singla, S., Eslami, M., Pollack, B., Wallace, S., Batmanghelich, K.: Explaining the black-box smoothly-a counterfactual approach. Med. Image Anal. 84, 102721 (2023)
Targ, S., Almeida, D., Lyman, K.: Resnet in resnet: Generalizing residual architectures. arXiv preprint arXiv:1603.08029 (2016)
Thiagarajan, J.J., Thopalli, K., Rajan, D., Turaga, P.: Training calibration-based counterfactual explainers for deep learning models in medical image analysis. Sci. Rep. 12(1), 597 (2022)
Vapnik, V.: Principles of risk minimization for learning theory. In: Advances in Neural Information Processing Systems, vol. 4 (1991)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017)
Zong, Y., Yang, Y., Hospedales, T.: MEDFAIR: benchmarking fairness for medical imaging. In: International Conference on Learning Representations (2023)
Zou, J., Schiebinger, L.: AI can be sexist and racist-it’s time to make it fair (2018)
Acknowledgements
The authors are grateful for funding provided by the Natural Sciences and Engineering Research Council of Canada, the Canadian Institute for Advanced Research (CIFAR) Artificial Intelligence Chairs program, the Mila - Quebec AI Institute technology transfer program, Microsoft Research, Calcul Quebec, and the Digital Research Alliance of Canada. S.A. Tsaftaris acknowledges the support of Canon Medical and the Royal Academy of Engineering and the Research Chairs and Senior Research Fellowships scheme (grant RCSRF1819 / 8 / 25), and the UK’s Engineering and Physical Sciences Research Council (EPSRC) support via grant EP/X017680/1.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kumar, A. et al. (2023). Debiasing Counterfactuals in the Presence of Spurious Correlations. In: Wesarg, S., et al. Clinical Image-Based Procedures, Fairness of AI in Medical Imaging, and Ethical and Philosophical Issues in Medical Imaging. CLIP EPIMI FAIMI 2023 2023 2023. Lecture Notes in Computer Science, vol 14242. Springer, Cham. https://doi.org/10.1007/978-3-031-45249-9_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-45249-9_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45248-2
Online ISBN: 978-3-031-45249-9
eBook Packages: Computer ScienceComputer Science (R0)
