Abstract
Well-calibrated uncertainty is crucial for medical imaging tasks. However, Monte Carlo (MC) Dropout - one of the most common methods for epistemic uncertainty estimation in deep neural networks (DNN), has been found ineffective for multi-path DNN, such as NASNet, and has been recently bypassed by DropPath and ScheduledDropPath.
In this work, we propose two novel model calibration frameworks for uncertainty estimation: MC ScheduledDropPath and MC Concrete DropPath. Particularly, MC ScheduledDropPath drops out paths in DNN cells during test-time, which has proven to improve the model calibration. At the same time, the MC Concrete DropPath method applies concrete relaxation for DropPath probability optimization, which was found to even better regularize and calibrate DNNs at scale. We further investigate both methods on the problem of brain tumour segmentation and demonstrate a significant Dice score improvement and better calibration ability as compared to state-of-the-art baselines.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Al-Shamahy, H.: Prevalence of CNS tumors and Histo-logical recognition in the operated patients: 10 years experience. Ann. Clin. Med. Case Rep. 6(12), 1–8 (2021)
Ashukha, A., Lyzhov, A., Molchanov, D., Vetrov, D.: Pitfalls of in-domain uncertainty estimation and ensembling in deep learning (2019)
Bakas, S., et al.: Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci. Data 4(1), 1–13 (2017)
Bakas, S., et al.: Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the brats challenge. arXiv preprint arXiv:1811.02629 (2018)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017)
Eaton-Rosen, Z., Bragman, F., Bisdas, S., Ourselin, S., Cardoso, M.J.: Towards safe deep learning: accurately quantifying biomarker uncertainty in neural network predictions. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 691–699. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_78
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation. arXiv preprint arXiv:1506.02157 (2015)
Gal, Y., Hron, J., Kendall, A.: Concrete dropout. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Ghiasi, G., Lin, T.Y., Le, Q.V.: DropBlock: a regularization method for convolutional networks. arXiv preprint arXiv:1810.12890 (2018)
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Improving neural networks by preventing co-adaptation of feature detectors. CoRR abs/1207.0580 (2012). http://arxiv.org/abs/1207.0580
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Isensee, F., Jäger, P.F., Full, P.M., Vollmuth, P., Maier-Hein, K.H.: nnU-Net for brain tumor segmentation. In: Crimi, A., Bakas, S. (eds.) BrainLes 2020. LNCS, vol. 12659, pp. 118–132. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-72087-2_11
Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.G.: Averaging weights leads to wider optima and better generalization. arXiv preprint arXiv:1803.05407 (2018)
Jungo, A., Meier, R., Ermis, E., Herrmann, E., Reyes, M.: Uncertainty-driven sanity check: application to postoperative brain tumor cavity segmentation. arXiv preprint arXiv:1806.03106 (2018)
Kaneko, S., Nomura, K., Yoshimura, T., et al.: Trend of brain tumor incidence by histological subtypes in Japan: estimation from the brain tumor registry of t. J. Neurooncol. 60, 61–69 (2002). https://doi.org/10.1023/A:1020239720852
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)
Larsson, G., Maire, M., Shakhnarovich, G.: FractalNet: ultra-deep neural networks without residuals. arXiv preprint arXiv:1605.07648 (2016)
Loquercio, A., Segu, M., Scaramuzza, D.: A general framework for uncertainty estimation in deep learning. IEEE Robot. Autom. Lett. 5(2), 3153–3160 (2020)
Maddison, C.J., Mnih, A., Teh, Y.W.: The concrete distribution: a continuous relaxation of discrete random variables. arXiv preprint arXiv:1611.00712 (2016)
Mehta, R., Arbel, T.: RS-Net: regression-segmentation 3D CNN for synthesis of full resolution missing brain MRI in the presence of tumours. In: Gooya, A., Goksel, O., Oguz, I., Burgos, N. (eds.) SASHIMI 2018. LNCS, vol. 11037, pp. 119–129. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00536-8_13
Mehta, R., Filos, A., Gal, Y., Arbel, T.: Uncertainty evaluation metric for brain tumour segmentation. arXiv preprint arXiv:2005.14262 (2020)
Menze, B.H., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2014)
Naeini, M.P., Cooper, G., Hauskrecht, M.: Obtaining well calibrated probabilities using Bayesian binning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 29 (2015)
Nalepa, J., Marcinkiewicz, M., Kawulok, M.: Data augmentation for brain-tumor segmentation: a review. Front. Comput. Neurosci. 13, 83 (2019)
Northcutt, C.G., Athalye, A., Mueller, J.: Pervasive label errors in test sets destabilize machine learning benchmarks. arXiv preprint arXiv:2103.14749 (2021)
Ovadia, Y., et al.: Can you trust your model’s uncertainty? Evaluating predictive uncertainty under dataset shift. arXiv preprint arXiv:1906.02530 (2019)
Porter, K.R., McCarthy, B.J., Freels, S., Kim, Y., Davis, F.G.: Prevalence estimates for primary brain tumors in the united states by age, gender, behavior, and histology. Neuro Oncol. 12(6), 520–527 (2010)
Rousseau, A.J., Becker, T., Bertels, J., Blaschko, M.B., Valkenborg, D.: Post training uncertainty calibration of deep networks for medical image segmentation. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1052–1056. IEEE (2021)
Seferbekov, S.: DSB 2018 [ods.ai] topcoders 1st place solution (2018). https://github.com/selimsef/dsb2018_topcoders
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Supplementary Material: The dice AUC, FTP AUC, and FTN AUC for deep ensemble and mc concrete droppath (2021). https://genome.ifmo.ru/files/papers_files/MICCAI2021/UNSURE/AUC.png
Supplementary Material: The prediction and uncertainty visualization (2021). https://genome.ifmo.ru/files/papers_files/MICCAI2021/UNSURE/MRI_uncertainty.png
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)
Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 648–656 (2015)
Wang, G., Li, W., Aertsen, M., Deprest, J., Ourselin, S., Vercauteren, T.: Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks. Neurocomputing 338, 34–45 (2019)
Wang, G., Li, W., Ourselin, S., Vercauteren, T.: Automatic brain tumor segmentation using cascaded anisotropic convolutional neural networks. In: Crimi, A., Bakas, S., Kuijf, H., Menze, B., Reyes, M. (eds.) BrainLes 2017. LNCS, vol. 10670, pp. 178–190. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75238-9_16
Wang, G., Li, W., Ourselin, S., Vercauteren, T.: Automatic brain tumor segmentation using convolutional neural networks with test-time augmentation. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11384, pp. 61–72. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11726-9_6
Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492–1500 (2017)
Zeineldin, R.A., Karar, M.E., Coburger, J., Wirtz, C.R., Burgert, O.: DeepSeg: deep neural network framework for automatic brain tumor segmentation using magnetic resonance flair images. Int. J. Comput. Assist. Radiol. Surg. 15(6), 909–920 (2020). https://doi.org/10.1007/s11548-020-02186-z
Zhang, Z., Dalca, A.V., Sabuncu, M.R.: Confidence calibration for convolutional neural networks using structured dropout. arXiv preprint arXiv:1906.09551 (2019)
Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697–8710 (2018)
Zou, K.H., et al.: Statistical validation of image segmentation quality based on a spatial overlap index1: scientific reports. Acad. Radiol. 11(2), 178–189 (2004)
Acknowledgments
This work is financially supported by National Center for Cognitive Research of ITMO University and Russian Science Foundation, Grant 19-19-00696.
The authors thank Ilya Osmakov and Pavel Ulyanov for useful ideas, Alex Farseev, Inna Anokhina, and Tatyana Polevaya for useful comments.
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
Khanzhina, N., Kashirin, M., Filchenkov, A. (2021). Monte Carlo Concrete DropPath for Epistemic Uncertainty Estimation in Brain Tumor Segmentation. 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_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-87735-4_7
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)