Abstract
The Variational AutoEncoder (VAE) has become one of the most popular models for anomaly detection in applications such as lesion detection in medical images. The VAE is a generative graphical model that is used to learn the data distribution from samples and then generate new samples from this distribution. By training on normal samples, the VAE can be used to detect inputs that deviate from this learned distribution. The VAE models the output as a conditionally independent Gaussian characterized by means and variances for each output dimension. VAEs can therefore use reconstruction probability instead of reconstruction error for anomaly detection. Unfortunately, joint optimization of both mean and variance in the VAE leads to the well-known problem of shrinkage or underestimation of variance. We describe an alternative VAE model, Quantile-Regression VAE (QR-VAE), that avoids this variance shrinkage problem by estimating conditional quantiles for the given input image. Using the estimated quantiles, we compute the conditional mean and variance for input images under the Gaussian model. We then compute reconstruction probability using this model as a principled approach to outlier or anomaly detection. We also show how our approach can be used for heterogeneous thresholding of images for detecting lesions in brain images.
This work is supported by the following grants: R01-NS074980, W81XWH-18-1-0614, R01-NS089212, and R01-EB026299.
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
References
Aggarwal, C.C.: Outlier analysis. Data Mining, pp. 237–263. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-14142-8_8
An, J., Cho, S.: Variational autoencoder based anomaly detection using reconstruction probability. Spec. Lect. IE 2(1), 1–18 (2015)
Baur, C., Wiestler, B., Albarqouni, S., Navab, N.: Deep autoencoding models for unsupervised anomaly segmentation in brain MR images. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11383, pp. 161–169. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11723-8_16
Benjamini, Y., Hochberg, Y.: Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. Roy. Stat. Soc. B (Methodological) 57(1), 289–300 (1995)
Blaauw, M., Bonada, J.: Modeling and transforming speech using variational autoencoders. In: Morgan, N. (ed.) Interspeech 2016; 2016 Sep 8–12; San Francisco, CA, ISCA; 2016. pp. 1770–1774 (2016)
Chen, X., Konukoglu, E.: Unsupervised detection of lesions in brain MRI using constrained adversarial auto-encoders. arXiv preprint arXiv:1806.04972 (2018)
Detlefsen, N.S., Jørgensen, M., Hauberg, S.: Reliable training and estimation of variance networks. arXiv preprint arXiv:1906.03260 (2019)
Gullapalli, R.P.: Investigation of prognostic ability of novel imaging markers for traumatic brain injury (TBI). BALTIMORE UNIV MD, Technical Report (2011)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
Koenker, R., Bassett Jr, G.: Regression quantiles. Econometrica: J. Econometric Soc. 46, 33–50 (1978)
Larsen, A.B.L., Sønderby, S.K., Larochelle, H., Winther, O.: Autoencoding beyond pixels using a learned similarity metric. arXiv preprint arXiv:1512.09300 (2015)
Maier, O., et al.: ISLES 2015-a public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI. Med. Image Anal. 35, 250–269 (2017)
Mattei, P.A., Frellsen, J.: Leveraging the exact likelihood of deep latent variable models. In: Advances in Neural Information Processing Systems, pp. 3855–3866 (2018)
Pawlowski, N., et al.: Unsupervised lesion detection in brain CT using Bayesian convolutional autoencoders. Open Review (2018)
Reinhold, J.C., et al.: Validating uncertainty in medical image translation. arXiv preprint arXiv:2002.04639 (2020)
Rodrigues, F., Pereira, F.C.: Beyond expectation: deep joint mean and quantile regression for spatiotemporal problems. IEEE Trans. Neural Netw. Learn. Syst. 31(12), 5377–5389 (2020)
Skafte, N., Jørgensen, M., Hauberg, S.: Reliable training and estimation of variance networks. In: Advances in Neural Information Processing Systems, pp. 6323–6333 (2019)
Stirn, A., Knowles, D.A.: Variational variance: Simple and reliable predictive variance parameterization. arXiv preprint arXiv:2006.04910 (2020)
Tagasovska, N., Lopez-Paz, D.: Single-model uncertainties for deep learning. In: Advances in Neural Information Processing Systems, pp. 6417–6428 (2019)
Volokitin, A., et al.: Modelling the distribution of 3D brain MRI using a 2D slice VAE. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12267, pp. 657–666. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59728-3_64
Wang, Q., Kulkarni, S.R., Verdú, S.: Divergence estimation for multidimensional densities via \( k \)-nearest-neighbor distances. IEEE Trans. Inf. Theor. 55(5), 2392–2405 (2009)
Wingate, D., Weber, T.: Automated variational inference in probabilistic programming. arXiv preprint arXiv:1301.1299 (2013)
Yu, K., Moyeed, R.A.: Bayesian quantile regression. Stat. Prob. Lett. 54(4), 437–447 (2001)
Yue, J.K., et al.: Transforming research and clinical knowledge in traumatic brain injury pilot: multicenter implementation of the common data elements for traumatic brain injury. J. Neurotrauma 30(22), 1831–1844 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Akrami, H., Joshi, A., Aydore, S., Leahy, R. (2021). Quantile Regression for Uncertainty Estimation in VAEs with Applications to Brain Lesion Detection. In: Feragen, A., Sommer, S., Schnabel, J., Nielsen, M. (eds) Information Processing in Medical Imaging. IPMI 2021. Lecture Notes in Computer Science(), vol 12729. Springer, Cham. https://doi.org/10.1007/978-3-030-78191-0_53
Download citation
DOI: https://doi.org/10.1007/978-3-030-78191-0_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78190-3
Online ISBN: 978-3-030-78191-0
eBook Packages: Computer ScienceComputer Science (R0)