Abstract
Trustworthy deployment of deep learning medical imaging models into real-world clinical practice requires that they be calibrated. However, models that are well calibrated overall can still be poorly calibrated for a sub-population, potentially resulting in a clinician unwittingly making poor decisions for this group based on the recommendations of the model. Although methods have been shown to successfully mitigate biases across subgroups in terms of model accuracy, this work focuses on the open problem of mitigating calibration biases in the context of medical image analysis. Our method does not require subgroup attributes during training, permitting the flexibility to mitigate biases for different choices of sensitive attributes without re-training. To this end, we propose a novel two-stage method: Cluster-Focal to first identify poorly calibrated samples, cluster them into groups, and then introduce group-wise focal loss to improve calibration bias. We evaluate our method on skin lesion classification with the public HAM10000 dataset, and on predicting future lesional activity for multiple sclerosis (MS) patients. In addition to considering traditional sensitive attributes (e.g. age, sex) with demographic subgroups, we also consider biases among groups with different image-derived attributes, such as lesion load, which are required in medical image analysis. Our results demonstrate that our method effectively controls calibration error in the worst-performing subgroups while preserving prediction performance, and outperforming recent baselines.
C. Shui and J. Szeto—Equal contribution.
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. Vision Sci. Technol. 10(2), 13–13 (2021)
Calabresi, P.A., et al.: Pegylated interferon beta-1a for relapsing-remitting multiple sclerosis (ADVANCE): a randomised, phase 3, double-blind study. Lancet Neurol. 13(7), 657–665 (2014)
Codella, N.C., et al.: Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pp. 168–172. IEEE (2018)
Creager, E., Jacobsen, J.H., Zemel, R.: Environment inference for invariant learning. In: International Conference on Machine Learning, pp. 2189–2200. PMLR (2021)
Devonshire, V., et al.: Relapse and disability outcomes in patients with multiple sclerosis treated with fingolimod: subgroup analyses of the double-blind, randomised, placebo-controlled FREEDOMS study. The Lancet Neurology 11(5), 420–428 (2012)
Diana, E., Gill, W., Kearns, M., Kenthapadi, K., Roth, A.: Minimax group fairness: algorithms and experiments. In: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pp. 66–76 (2021)
Gold, R., et al.: Placebo-controlled phase 3 study of oral BG-12 for relapsing multiple sclerosis. N. Engl. J. Med. 367(12), 1098–1107 (2012)
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: International Conference on Machine Learning, pp. 1321–1330. PMLR (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Lahoti, P., et al.: Fairness without demographics through adversarially reweighted learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 728–740 (2020)
Lampl, C., You, X., Limmroth, V.: Weekly IM interferon beta-1a in multiple sclerosis patients over 50 years of age. Eur. J. Neurol. 19(1), 142–148 (2012)
Lampl, C., et al.: Efficacy and safety of interferon beta-1b SC in older RRMS patients: a post hoc analysis of the beyond study. J. Neurol. 260(7), 1838–1845 (2013)
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)
Liu, E.Z., et al.: Just train twice: improving group robustness without training group information. In: International Conference on Machine Learning, pp. 6781–6792. PMLR (2021)
Menze, B.H., et al.: The multimodal brain tumor image segmentation benchmark (brats). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2015)
Mukhoti, J., Kulharia, V., Sanyal, A., Golodetz, S., Torr, P., Dokania, P.: Calibrating deep neural networks using focal loss. Adv. Neural. Inf. Process. Syst. 33, 15288–15299 (2020)
Nixon, J., Dusenberry, M.W., Zhang, L., Jerfel, G., Tran, D.: Measuring calibration in deep learning. In: CVPR Workshops, vol. 2 (2019)
Ricci Lara, M.A., Echeveste, R., Ferrante, E.: Addressing fairness in artificial intelligence for medical imaging. Nat. Commun. 13(1), 4581 (2022)
Roelofs, R., Cain, N., Shlens, J., Mozer, M.C.: Mitigating bias in calibration error estimation. In: International Conference on Artificial Intelligence and Statistics, pp. 4036–4054. PMLR (2022)
Sagawa, S., Koh, P.W., Hashimoto, T.B., Liang, P.: Distributionally robust neural networks. In: International Conference on Learning Representations (2020)
Sepahvand, N.M., Hassner, T., Arnold, D.L., Arbel, T.: CNN prediction of future disease activity for multiple sclerosis patients from baseline MRI and lesion labels. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11383, pp. 57–69. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11723-8_6
Signori, A., Schiavetti, I., Gallo, F., Sormani, M.P.: Subgroups of multiple sclerosis patients with larger treatment benefits: a meta-analysis of randomized trials. Eur. J. Neurol. 22(6), 960–966 (2015)
Simon, J., et al.: Ten-year follow-up of the ‘minimal MRI lesion’ subgroup from the original CHAMPS Multiple Sclerosis Prevention Trial. Multiple Sclerosis J. 21(4), 415–422 (2015). Publisher: SAGE Publications Ltd. STM
Tousignant, A., Lemaître, P., Precup, D., Arnold, D.L., Arbel, T.: Prediction of disease progression in multiple sclerosis patients using deep learning analysis of MRI data. In: Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning (MIDL), vol. 102, pp. 483–492. PMLR, 08–10 July 2019
Vapnik, V.: Principles of risk minimization for learning theory. In: Advances in Neural Information Processing Systems, vol. 4 (1991)
Vollmer, T.L., et al.: On behalf of the BRAVO study group: a randomized placebo-controlled phase III trial of oral laquinimod for multiple sclerosis. J. Neurol. 261(4), 773–783 (2014)
Zong, Y., Yang, Y., Hospedales, T.: Medfair: benchmarking fairness for medical imaging. In: International Conference on Learning Representations (ICLR) (2023)
Zou, J., Schiebinger, L.: AI can be sexist and racist-it’s time to make it fair. Nature (2018)
Acknowledgements
This paper was supported by the Canada Institute for Advanced Research (CIFAR) AI Chairs program and the Natural Sciences and Engineering Research Council of Canada (NSERC). The MS portion of this paper was supported by the International Progressive Multiple Sclerosis Alliance (PA-1412-02420), the companies who generously provided the MS data: Biogen, BioMS, MedDay, Novartis, Roche/Genentech, and Teva, Multiple Sclerosis Society of Canada, Calcul Quebec, and the Digital Research Alliance of Canada.
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
Shui, C., Szeto, J., Mehta, R., Arnold, D.L., Arbel, T. (2023). Mitigating Calibration Bias Without Fixed Attribute Grouping for Improved Fairness in Medical Imaging Analysis. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14222. Springer, Cham. https://doi.org/10.1007/978-3-031-43898-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-43898-1_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43897-4
Online ISBN: 978-3-031-43898-1
eBook Packages: Computer ScienceComputer Science (R0)
