Abstract
The wide-spread adoption of representation learning technologies in clinical decision making strongly emphasizes the need for characterizing model reliability and enabling rigorous introspection of model behavior. In supervised and semi-supervised learning, prediction calibration has emerged as a key technique to achieve improved generalization and to promote trust in learned models. In this paper, we investigate the effectiveness of different prediction calibration techniques in improving the reliability of clinical models. First, we introduce reliability plots, which measures the trade-off between model autonomy and generalization, to quantify model reliability. Second, we propose to utilize an interval calibration objective in lieu of the standard cross entropy loss to build classification models. Finally, using a lesion classification problem with dermoscopy images, we evaluate the proposed prediction calibration approach against both uncalibrated models as well as existing prediction calibration techniques such as mixup and single-shot calibration.
J.J. Thiagarajan—This work was performed under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cabitza, F., Campagner, A.: Who wants accurate models? arguing for a different metrics to take classification models seriously. arXiv preprint arXiv:1910.09246 (2019)
Ching, T., et al.: Opportunities and obstacles for deep learning in biology and medicine. J. R. Soc. Interface 15(141), 20170387 (2018)
Codella, N., et al.: Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC). arXiv preprint arXiv:1902.03368 (2019)
Faust, O., Hagiwara, Y., Hong, T.J., Lih, O.S., Acharya, U.R.: Deep learning for healthcare applications based on physiological signals: a review. Comput. Methods Programs Biomed. 161, 1–13 (2018)
Gal, Y.: Uncertainty in deep learning. University of Cambridge, vol. 1, p. 3 (2016)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050–1059 (2016)
Ghahramani, Z.: Probabilistic machine learning and artificial intelligence. Nature 521(7553), 452–459 (2015)
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1321–1330. JMLR. org (2017)
Heskes, T.: Practical confidence and prediction intervals. In: Advances in Neural Information Processing Systems, pp. 176–182 (1997)
Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: Advances in Neural Information Processing Systems, pp. 5574–5584 (2017)
Kononenko, I.: Machine learning for medical diagnosis: history, state of the art and perspective. Artif. Intell. Med. 23(1), 89–109 (2001)
Kuleshov, V., Fenner, N., Ermon, S.: Accurate uncertainties for deep learning using calibrated regression. arXiv preprint arXiv:1807.00263 (2018)
Kuleshov, V., Liang, P.S.: Calibrated structured prediction. In: Advances in Neural Information Processing Systems, pp. 3474–3482 (2015)
Kumar, A., Sattigeri, P., Balakrishnan, A.: Variational inference of disentangled latent concepts from unlabeled observations. arXiv preprint arXiv:1711.00848 (2017)
Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. In: Advances in Neural Information Processing Systems, pp. 6402–6413 (2017)
Leibig, C., Allken, V., Ayhan, M.S., Berens, P., Wahl, S.: Leveraging uncertainty information from deep neural networks for disease detection. Sci. Rep. 7(1), 1–14 (2017)
Miotto, R., Wang, F., Wang, S., Jiang, X., Dudley, J.T.: Deep learning for healthcare: review, opportunities and challenges. Brief. Bioinform. 19(6), 1236–1246 (2018)
Seo, S., Seo, P.H., Han, B.: Learning for single-shot confidence calibration in deep neural networks through stochastic inferences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9030–9038 (2019)
Smith, R.C.: Uncertainty quantification: theory, implementation, and applications, vol. 12. SIAM (2013)
Thiagarajan, J.J., Kim, I., Anirudh, R., Bremer, P.T.: Understanding deep neural networks through input uncertainties. In: ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2812–2816. IEEE (2019)
Thiagarajan, J.J., Venkatesh, B., Sattigeri, P., Bremer, P.T.: Building calibrated deep models via uncertainty matching with auxiliary interval predictors. AAAI Conference on Artificial Intelligence (2019)
Thulasidasan, S., Chennupati, G., Bilmes, J.A., Bhattacharya, T., Michalak, S.: On mixup training: improved calibration and predictive uncertainty for deep neural networks. In: Advances in Neural Information Processing Systems, pp. 13888–13899 (2019)
Tonekaboni, S., Joshi, S., McCradden, M.D., Goldenberg, A.: What clinicians want: contextualizing explainable machine learning for clinical end use. arXiv preprint arXiv:1905.05134 (2019)
Tschandl, P., Rosendahl, C., Kittler, H.: The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5, 180161 (2018)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Thiagarajan, J.J., Venkatesh, B., Rajan, D., Sattigeri, P. (2020). Improving Reliability of Clinical Models Using Prediction Calibration. In: Sudre, C.H., et al. Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, and Graphs in Biomedical Image Analysis. UNSURE GRAIL 2020 2020. Lecture Notes in Computer Science(), vol 12443. Springer, Cham. https://doi.org/10.1007/978-3-030-60365-6_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-60365-6_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60364-9
Online ISBN: 978-3-030-60365-6
eBook Packages: Computer ScienceComputer Science (R0)