Abstract
Medical image based diagnosis is constantly faced with uncertainties. In an ambiguous scenario, different experts will reach different conclusions from their initial assumptions. It is thus important for machine learning models to be capable of proposing different plausible predictions, along with meaningful uncertainty measures. In this work we propose such a novel learning-based framework, named modal uncertainty estimation (MUE), to learn such one-to-many relationship with faithful uncertainty estimation in the medical image understanding tasks. Technically, MUE is based on conditional generative models, but it crucially uses a set of discrete latent variables, each representing a latent mode hypothesis that explains one type of input-output relationship. We justify the use of discrete latent variables by the multi-modal posterior collapse problem in the common conditional generative models. Consequently, MUE can estimate the uncertainty effectively. MUE demonstrates significantly more accurate uncertainty estimation for one-to-many relationship than the current state-of-the-art, and is more informative for practical use. We validate these points on both real and synthetic tasks.
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
Alemi, A., Poole, B., Fischer, I., Dillon, J., Saurous, R.A., Murphy, K.: Fixing a broken ELBO. In: International Conference on Machine Learning, pp. 159–168 (2018)
Armato III, S.G., et al.: The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Med. Phys. 38(2), 915–931 (2011)
Armato III, S.G., et al.: Data from LIDC-IDRI (2015)
Baumgartner, C.F., et al.: PHiSeg: capturing uncertainty in medical image segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 119–127. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_14
Bellemare, M.G., et al.: The cramer distance as a solution to biased Wasserstein gradients. arXiv preprint arXiv:1705.10743 (2017)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)
Clark, K., et al.: The cancer imaging archive (TCIA): maintaining and operating a public information repository. J. Digit. Imaging 26(6), 1045–1057 (2013)
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)
Huang, X., Liu, M.Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 172–189 (2018)
Ilg, E., et al.: Uncertainty estimates and multi-hypotheses networks for optical flow. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 652–667 (2018)
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)
Kendall, A., Badrinarayanan, V., Cipolla, R.: Bayesian SegNet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv preprint arXiv:1511.02680 (2015)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015). http://arxiv.org/abs/1412.6980
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: Bengio, Y., LeCun, Y. (eds.) 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, 14–16 April 2014, Conference Track Proceedings (2014). http://arxiv.org/abs/1312.6114
Kohl, S., et al.: A probabilistic u-net for segmentation of ambiguous images. In: Advances in Neural Information Processing Systems, pp. 6965–6975 (2018)
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)
LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010). http://yann.lecun.com/exdb/mnist/
van den Oord, A., Vinyals, O., et al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, pp. 6306–6315 (2017)
Paszke, A., et al.: Automatic differentiation in PyTorch (2017)
Razavi, A., van den Oord, A., Poole, B., Vinyals, O.: Preventing posterior collapse with delta-VAEs. In: International Conference on Learning Representations (2018)
Razavi, A., van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: Advances in Neural Information Processing Systems, pp. 14837–14847 (2019)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Rupprecht, C., et al.: Learning in an uncertain world: representing ambiguity through multiple hypotheses. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3591–3600 (2017)
Salimans, T., Zhang, H., Radford, A., Metaxas, D.: Improving GANs using optimal transport. In: International Conference on Learning Representations (2018)
Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: Advances in Neural Information Processing Systems, pp. 3483–3491 (2015)
Székely, G.J., Rizzo, M.L.: Energy statistics: a class of statistics based on distances. J. Stat. Plann. Inference 143(8), 1249–1272 (2013)
Zhao, T., Lee, K., Eskenazi, M.: Unsupervised discrete sentence representation learning for interpretable neural dialog generation. arXiv preprint arXiv:1804.08069 (2018)
Zheng, C., Cham, T.J., Cai, J.: Pluralistic image completion. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1438–1447 (2019)
Zhu, J.Y., et al.: Toward multimodal image-to-image translation. In: Advances in Neural Information Processing Systems, pp. 465–476 (2017)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Qiu, D., Lui, L.M. (2021). Modal Uncertainty Estimation for Medical Imaging Based Diagnosis. In: Sudre, C.H., et al. Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, and Perinatal Imaging, Placental and Preterm Image Analysis. UNSURE PIPPI 2021 2021. Lecture Notes in Computer Science(), vol 12959. Springer, Cham. https://doi.org/10.1007/978-3-030-87735-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-87735-4_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87734-7
Online ISBN: 978-3-030-87735-4
eBook Packages: Computer ScienceComputer Science (R0)
