Skip to main content
Top

Hint

Swipe to navigate through the chapters of this book

2018 | OriginalPaper | Chapter

Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation

Authors : Tanya Nair, Doina Precup, Douglas L. Arnold, Tal Arbel

Published in: Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

Publisher: Springer International Publishing

share
SHARE

Abstract

Deep learning (DL) networks have recently been shown to outperform other segmentation methods on various public, medical-image challenge datasets [3, 11, 16], especially for large pathologies. However, in the context of diseases such as Multiple Sclerosis (MS), monitoring all the focal lesions visible on MRI sequences, even very small ones, is essential for disease staging, prognosis, and evaluating treatment efficacy. Moreover, producing deterministic outputs hinders DL adoption into clinical routines. Uncertainty estimates for the predictions would permit subsequent revision by clinicians. We present the first exploration of multiple uncertainty estimates based on Monte Carlo (MC) dropout [4] in the context of deep networks for lesion detection and segmentation in medical images. Specifically, we develop a 3D MS lesion segmentation CNN, augmented to provide four different voxel-based uncertainty measures based on MC dropout. We train the network on a proprietary, large-scale, multi-site, multi-scanner, clinical MS dataset, and compute lesion-wise uncertainties by accumulating evidence from voxel-wise uncertainties within detected lesions. We analyze the performance of voxel-based segmentation and lesion-level detection by choosing operating points based on the uncertainty. Empirical evidence suggests that uncertainty measures consistently allow us to choose superior operating points compared only using the network’s sigmoid output as a probability.
Literature
1.
2.
go back to reference Brosch, T., et al.: Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation. TMI 35(5), 1229–1239 (2016) Brosch, T., et al.: Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation. TMI 35(5), 1229–1239 (2016)
3.
go back to reference Carass, A., et al.: Longitudinal multiple sclerosis lesion segmentation: resource and challenge. NeuroImage 148, 77–102 (2017) CrossRef Carass, A., et al.: Longitudinal multiple sclerosis lesion segmentation: resource and challenge. NeuroImage 148, 77–102 (2017) CrossRef
4.
go back to reference Gal, Y., Ghahramani, Z.: Dropout as a bayesian approximation: representing model uncertainty in deep learning. In: ICML, pp. 1050–1059 (2016) Gal, Y., Ghahramani, Z.: Dropout as a bayesian approximation: representing model uncertainty in deep learning. In: ICML, pp. 1050–1059 (2016)
5.
go back to reference Gal, Y., et al.: Deep Bayesian active learning with image data. In: ICML (2017) Gal, Y., et al.: Deep Bayesian active learning with image data. In: ICML (2017)
6.
go back to reference Ghafoorian, M., et al.: Non-uniform patch sampling with deep convolutional neural networks for white matter hyperintensity segmentation. In: ISBI, pp. 1414–1417 (2016) Ghafoorian, M., et al.: Non-uniform patch sampling with deep convolutional neural networks for white matter hyperintensity segmentation. In: ISBI, pp. 1414–1417 (2016)
8.
go back to reference Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: NIPS, pp. 5580–5590 (2017) Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: NIPS, pp. 5580–5590 (2017)
9.
go back to reference Kendall, A., et al.: Bayesian SegNet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. In: BMVC (2017) Kendall, A., et al.: Bayesian SegNet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. In: BMVC (2017)
11.
go back to reference Menze, B.H., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). TMI 34(10), 1993–2024 (2015) Menze, B.H., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). TMI 34(10), 1993–2024 (2015)
12.
go back to reference Ozdemir, O., et al.: Propagating uncertainty in multi-stage Bayesian convolutional neural networks with application to pulmonary nodule detection. In: NIPS (2017) Ozdemir, O., et al.: Propagating uncertainty in multi-stage Bayesian convolutional neural networks with application to pulmonary nodule detection. In: NIPS (2017)
13.
14.
go back to reference Sled, J.G., Zijdenbos, A.P., Evans, A.C.: A nonparametric method for automatic correction of intensity nonuniformity in MRI data. TMI 17(1), 87–97 (1998) Sled, J.G., Zijdenbos, A.P., Evans, A.C.: A nonparametric method for automatic correction of intensity nonuniformity in MRI data. TMI 17(1), 87–97 (1998)
15.
go back to reference Smith, S.M.: Fast robust automated brain extraction. HBM 17(3), 143–155 (2002) CrossRef Smith, S.M.: Fast robust automated brain extraction. HBM 17(3), 143–155 (2002) CrossRef
16.
go back to reference Styner, M., et al.: 3D segmentation in the clinic: a grand challenge II: MS lesion segmentation. MIDAS 2008, 1–6 (2008) Styner, M., et al.: 3D segmentation in the clinic: a grand challenge II: MS lesion segmentation. MIDAS 2008, 1–6 (2008)
Metadata
Title
Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation
Authors
Tanya Nair
Doina Precup
Douglas L. Arnold
Tal Arbel
Copyright Year
2018
DOI
https://doi.org/10.1007/978-3-030-00928-1_74

Premium Partner