×

Uncertainty quantification using Bayesian neural networks in classification: application to biomedical image segmentation. (English) Zbl 1507.62095

Summary: Most recent research of deep neural networks in the field of computer vision has focused on improving performances of point predictions by developing network architectures or learning algorithms. Reliable uncertainty quantification accompanied by point estimation can lead to a more informed decision, and the quality of prediction can be improved. In this paper, we invoke a Bayesian neural network and propose a natural way of quantifying uncertainties in classification problems by decomposing the moment-based predictive uncertainty into two parts: aleatoric and epistemic uncertainty. The proposed method takes into account the discrete nature of the outcome, yielding the correct interpretation of each uncertainty. We demonstrate that the proposed uncertainty quantification method provides additional insights into the point prediction using two Ischemic Stroke Lesion Segmentation Challenge datasets and the Digital Retinal Images for Vessel Extraction dataset.

MSC:

62-08 Computational methods for problems pertaining to statistics
62P10 Applications of statistics to biology and medical sciences; meta analysis
68T07 Artificial neural networks and deep learning
92C55 Biomedical imaging and signal processing

Software:

U-Net
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Ayhan, M. S.; Berens, P., Test-time data augmentation for estimation of heteroscedastic aleatoric uncertainty in deep neural networks, (International Conference on Medical Imaging with Deep Learning (2018))
[2] Blundell, C.; Cornebise, J.; Kavukcuoglu, K.; Wierstra, D., Weight uncertainty in neural networks, (International Conference on Machine Learning (2015)), 1613-1622
[3] Chen, T.; Fox, E.; Guestrin, C., Stochastic gradient hamiltonian monte carlo, (International Conference on Machine Learning (2014)), 1683-1691
[4] Choi, Y.; Kwon, Y.; Lee, H.; Kim, B. J.; Paik, M. C.; Won, J.-H., Ensemble of deep convolutional neural networks for prognosis of ischemic stroke, (International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (2016), Springer), 231-243
[5] Chollet, F., 2015. keras, https://github.com/fchollet/keras; Chollet, F., 2015. keras, https://github.com/fchollet/keras
[6] Clevert, D.-A., Unterthiner, T., Hochreiter, S., 2015. Fast and accurate deep network learning by exponential linear units (elus), arXiv preprint arXiv:1511.07289; Clevert, D.-A., Unterthiner, T., Hochreiter, S., 2015. Fast and accurate deep network learning by exponential linear units (elus), arXiv preprint arXiv:1511.07289
[7] Der Kiureghian, A.; Ditlevsen, O., Aleatory or epistemic? does it matter?, Struct. Saf., 31, 2, 105-112 (2009)
[8] Dieng, A. B.; Tran, D.; Ranganath, R.; Paisley, J.; Blei, D., Variational inference via \(\chi\) upper bound minimization, (Advances in Neural Information Processing Systems (2017)), 2729-2738
[9] Esteva, A.; Kuprel, B.; Novoa, R. A.; Ko, J.; Swetter, S. M.; Blau, H. M.; Thrun, S., Dermatologist-level classification of skin cancer with deep neural networks, Nature, 542, 7639, 115 (2017)
[10] Fleiss, J.; Levin, B.; Paik, M., (Statistical Methods for Rates and Proportions. Statistical Methods for Rates and Proportions, Wiley Series in Probability and Statistics (2003), Wiley) · Zbl 1034.62113
[11] Gal, Y., Uncertainty in Deep Learning (2016), University of Cambridge, (Ph.D. thesis)
[12] Graves, A., Practical variational inference for neural networks, (Advances in Neural Information Processing Systems (2011)), 2348-2356
[13] Guo, C.; Pleiss, G.; Sun, Y.; Weinberger, K. Q., On Calibration of modern neural networks, (International Conference on Machine Learning (2017)), 1321-1330
[14] He, K.; Zhang, X.; Ren, S.; Sun, J., Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, (Proceedings of the IEEE International Conference on Computer Vision (2015)), 1026-1034
[15] Ioffe, S.; Szegedy, C., Batch normalization: Accelerating deep network training by reducing internal covariate shift, (International Conference on Machine Learning (2015)), 448-456
[16] Jungo, A.; Meier, R.; Ermis, E.; Herrmann, E.; Reyes, M., Uncertainty-driven sanity check: Application to postoperative brain tumor Cavity segmentation, (International Conference on Medical Imaging with Deep Learning (2018))
[17] 2015. Kaggle, Kaggle diabetic retinopathy detection competition. https://www.kaggle.com/c/diabetic-retinopathy-detection; 2015. Kaggle, Kaggle diabetic retinopathy detection competition. https://www.kaggle.com/c/diabetic-retinopathy-detection
[18] Kamnitsas, K.; Ledig, C.; Newcombe, V. F.; Simpson, J. P.; Kane, A. D.; Menon, D. K.; Rueckert, D.; Glocker, B., Efficient multi-scale 3d cnn with fully connected crf for accurate brain lesion segmentation, Med. Image Anal., 36, 61-78 (2017)
[19] Kendall, A.; Gal, Y., What uncertainties do we need in bayesian deep learning for computer vision?, (Advances in Neural Information Processing Systems (2017)), 5580-5590
[20] Kingma, D.P., Ba, J., 2014. Adam: A method for stochastic optimization, arXiv preprint arXiv:1412.6980; Kingma, D.P., Ba, J., 2014. Adam: A method for stochastic optimization, arXiv preprint arXiv:1412.6980
[21] Kingma, D.P., Welling, M., 2013. Auto-encoding variational bayes, arXiv preprint arXiv:1312.6114; Kingma, D.P., Welling, M., 2013. Auto-encoding variational bayes, arXiv preprint arXiv:1312.6114
[22] Lee, H. K., Consistency of posterior distributions for neural networks, Neural Netw., 13, 6, 629-642 (2000)
[23] 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, 17816 (2017)
[24] Li, Y.; Turner, R. E., Rényi Divergence variational inference, (Advances in Neural Information Processing Systems (2016)), 1073-1081
[25] Litjens, G.; Kooi, T.; Bejnordi, B. E.; Setio, A. A.A.; Ciompi, F.; Ghafoorian, M.; van der Laak, J. A.; van Ginneken, B.; Sánchez, C. I., A survey on deep learning in medical image analysis, Med. Image Anal., 42, 60-88 (2017)
[26] Louizos, C.; Welling, M., Multiplicative normalizing flows for variational Bayesian neural networks, (International Conference on Machine Learning (2017)), 2218-2227
[27] MacKay, D. J., A practical Bayesian framework for backpropagation networks, Neural Comput., 4, 3, 448-472 (1992)
[28] Maier, O.; Menze, B. H.; von der Gablentz, J.; Häni, L.; Heinrich, M. P.; Liebrand, M.; Winzeck, S.; Basit, A.; Bentley, P.; Chen, L., Isles 2015-a public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI, Med. Image Anal., 35, 250-269 (2017)
[29] Miller, A. C.; Foti, N. J.; Adams, R. P., Variational boosting: Iteratively refining posterior approximations, (International Conference on Machine Learning (2017)), 2420-2429
[30] Neal, R. M., Bayesian Learning via stochastic dynamics, (Advances in Neural Information Processing Systems (1993)), 475-482
[31] Niemeijer, M.; Staal, J.; van Ginneken, B.; Loog, M.; Abramoff, M., Comparative study of retinal vessel segmentation methods on a new publicly available database, (Fitzpatrick, J. M.; Sonka, M., SPIE Medical Imaging, Vol. 5370 (2004), SPIE), 648-656
[32] Pereyra, G., Tucker, G., Chorowski, J., Kaiser, Ł., Hinton, G., 2017. Regularizing neural networks by penalizing confident output distributions, arXiv preprint arXiv:1701.06548; Pereyra, G., Tucker, G., Chorowski, J., Kaiser, Ł., Hinton, G., 2017. Regularizing neural networks by penalizing confident output distributions, arXiv preprint arXiv:1701.06548
[33] Ronneberger, O.; Fischer, P.; Brox, T., U-net: Convolutional networks for biomedical image segmentation, (International Conference on Medical Image Computing and Computer-Assisted Intervention (2015), Springer), 234-241
[34] Siva Sundhara Raja, D.; Vasuki, S., Automatic detection of blood vessels in retinal images for diabetic retinopathy diagnosis, Comput. Math. Methods Med., 2015 (2015)
[35] Staal, J.; Abràmoff, M. D.; Niemeijer, M.; Viergever, M. A.; Van Ginneken, B., Ridge-based vessel segmentation in color images of the retina, IEEE Trans. Med. Imaging, 23, 4, 501-509 (2004)
[36] Tanno, R.; Worrall, D. E.; Ghosh, A.; Kaden, E.; Sotiropoulos, S. N.; Criminisi, A.; Alexander, D. C., Bayesian image quality transfer with cnns: Exploring uncertainty in dmri super-resolution, (International Conference on Medical Image Computing and Computer-Assisted Intervention (2017), Springer), 611-619
[37] Teye, M., Azizpour, H., Smith, K., 2018. Bayesian Uncertainty Estimation for Batch Normalized Deep Networks, arXiv preprint arXiv:1802.06455; Teye, M., Azizpour, H., Smith, K., 2018. Bayesian Uncertainty Estimation for Batch Normalized Deep Networks, arXiv preprint arXiv:1802.06455
[38] Wang, Y.; Blei, D. M., Frequentist consistency of variational Bayes, J. Amer. Statist. Assoc., just-accepted, 1-85 (2018)
[39] Welling, M.; Teh, Y. W., Bayesian Learning via stochastic gradient langevin dynamics, (International Conference on Machine Learning (2011)), 681-688
[40] Winzeck, S.; Hakim, A.; McKinley, R.; Pinto, J. A.; Alves, V.; Silva, C.; Pisov, M.; Krivov, E.; Belyaev, M.; Monteiro, M., ISLES 2016 and 2017-benchmarking ischemic stroke lesion outcome prediction based on multispectral MRI, Front. Neurol., 9 (2018)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.