Skip to main content

Leveraging Uncertainty Estimates to Improve Segmentation Performance in Cardiac MR

  • 907 Accesses

Part of the Lecture Notes in Computer Science book series (LNIP,volume 12959)


In medical image segmentation, several studies have used Bayesian neural networks to segment and quantify the uncertainty of the images. These studies show that there might be an increased epistemic uncertainty in areas where there are semantically and visually challenging pixels. The uncertain areas of the image can be of a great interest as they can possibly indicate the regions of incorrect segmentation. To leverage the uncertainty information, we propose a segmentation model that incorporates the uncertainty into its learning process. Firstly, we generate the uncertainty estimate (sample variance) using Monte-Carlo dropout during training. Then we incorporate it into the loss function to improve the segmentation accuracy and probability calibration. The proposed method is validated on the publicly available EMIDEC MICCAI 2020 dataset that mainly focuses on segmentation of healthy and infarcted myocardium. Our method achieves the state of the art results outperforming the top ranked methods of the challenge. The experimental results show that adding the uncertainty information to the loss function improves the segmentation results by enhancing the geometrical and clinical segmentation metrics of both the scar and myocardium. These improvements are particularly significant at the visually challenging and difficult images which have higher epistemic uncertainty. The proposed system also produces more calibrated probabilities.


  • Cardiac MRI Segmentation
  • Myocardial scar
  • Uncertainty
  • Bayesian deep learning

This is a preview of subscription content, access via your institution.

Buying options

USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-87735-4_3
  • Chapter length: 10 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
USD   54.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-87735-4
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   69.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.


  1. 1.


  1. Abbas, A., Matthews, G.H., Brown, I.W., Shambrook, J., Peebles, C., Harden, S.: Cardiac MR assessment of microvascular obstruction. Br. J. Radiol. 88(1047), 20140470 (2015)

    CrossRef  Google Scholar 

  2. Arega, T.W., Bricq, S.: Automatic myocardial scar segmentation from multi-sequence cardiac MRI using fully convolutional densenet with inception and squeeze-excitation module. In: Zhuang, X., Li, L. (eds.) MyoPS 2020. LNCS, vol. 12554, pp. 102–117. Springer, Cham (2020).

    CrossRef  Google Scholar 

  3. Bernard, O., et al.: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans. Med. Imaging 37, 2514–2525 (2018)

    CrossRef  Google Scholar 

  4. Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural network. In: International Conference on Machine Learning, pp. 1613–1622. PMLR (2015)

    Google Scholar 

  5. Feng, X., Kramer, C.M., Salerno, M., Meyer, C.H.: Automatic scar segmentation from DE-MRI using 2D dilated UNet with rotation-based augmentation. In: Puyol Anton, E., et al. (eds.) STACOM 2020. LNCS, vol. 12592, pp. 400–405. Springer, Cham (2021).

    CrossRef  Google Scholar 

  6. Fortunato, M., Blundell, C., Vinyals, O.: Bayesian recurrent neural networks. arXiv preprint arXiv:1704.02798 (2017)

  7. Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050–1059. PMLR (2016)

    Google Scholar 

  8. Girum, K.B., Skandarani, Y., Hussain, R., Grayeli, A.B., Créhange, G., Lalande, A.: Automatic myocardial infarction evaluation from delayed-enhancement cardiac MRI using deep convolutional networks. In: Puyol Anton, E., et al. (eds.) STACOM 2020. LNCS, vol. 12592, pp. 378–384. Springer, Cham (2021).

    CrossRef  Google Scholar 

  9. Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021)

    CrossRef  Google Scholar 

  10. Jungo, A., Reyes, M.: Assessing reliability and challenges of uncertainty estimations for medical image segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 48–56. Springer, Cham (2019).

    CrossRef  Google Scholar 

  11. Kate Meier, C., Oyama, M.A.: Chapter 41 - Myocardial infarction. In: Silverstein, D.C., Hopper, K. (eds.) Small Animal Critical Care Medicine, pp. 174–176. W.B. Saunders, Saint Louis (2009).,

  12. 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)

  13. Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7482–7491 (2018)

    Google Scholar 

  14. Lalande, A., et al.: Emidec: a database usable for the automatic evaluation of myocardial infarction from delayed-enhancement cardiac MRI. Data 5(4), 89 (2020)

    CrossRef  Google Scholar 

  15. Ma, J.: Cascaded framework for automatic evaluation of myocardial infarction from delayed-enhancement cardiac MRI. arXiv preprint arXiv:2012.14556 (2020)

  16. Mehrtash, A., Wells, W.M., Tempany, C.M., Abolmaesumi, P., Kapur, T.: Confidence calibration and predictive uncertainty estimation for deep medical image segmentation. IEEE Trans. Med. Imaging 39(12), 3868–3878 (2020)

    CrossRef  Google Scholar 

  17. Nair, T., Precup, D., Arnold, D.L., Arbel, T.: Exploring uncertainty measures in deep networks for multiple sclerosis lesion detection and segmentation. Med. Image Anal. 59, 101557 (2020)

    CrossRef  Google Scholar 

  18. Ng, M., et al.: Estimating uncertainty in neural networks for cardiac MRI segmentation: a benchmark study. arXiv preprint arXiv:2012.15772 (2020)

  19. Petitjean, C., Dacher, J.N.: A review of segmentation methods in short axis cardiac MR images. Med. Image Anal. 15(2), 169–184 (2011)

    CrossRef  Google Scholar 

  20. Roy, A.G., Conjeti, S., Navab, N., Wachinger, C.: Inherent brain segmentation quality control from fully ConvNet Monte Carlo sampling. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 664–672. Springer, Cham (2018).

    CrossRef  Google Scholar 

  21. Sander, J., de Vos, B.D., Wolterink, J.M., Išgum, I.: Towards increased trustworthiness of deep learning segmentation methods on cardiac MRI. In: Medical Imaging 2019: Image Processing, vol. 10949, p. 1094919. International Society for Optics and Photonics (2019)

    Google Scholar 

  22. Wang, G., Li, W., Ourselin, S., Vercauteren, T.: Automatic brain tumor segmentation based on cascaded convolutional neural networks with uncertainty estimation. Front. Comput. Neurosci. 13, 56 (2019)

    CrossRef  Google Scholar 

  23. Zabihollahy, F., White, J.A., Ukwatta, E.: Myocardial scar segmentation from magnetic resonance images using convolutional neural network. In: Medical Imaging 2018: Computer-Aided Diagnosis, vol. 10575, p. 105752Z. International Society for Optics and Photonics (2018)

    Google Scholar 

  24. Zhang, Y.: Cascaded convolutional neural network for automatic myocardial infarction segmentation from delayed-enhancement cardiac MRI. arXiv preprint arXiv:2012.14128 (2020)

Download references


This work was supported by the French National Research Agency (ANR), with reference ANR-19-CE45-0001-01-ACCECIT. Calculations were performed using HPC resources from DNUM CCUB (Centre de Calcul de l’Université de Bourgogne). We also thank the Mesocentre of Franche-Comté for the computing facilities.

Author information

Authors and Affiliations


Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (zip 367 KB)

Supplementary material 2 (pdf 266 KB)

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Arega, T.W., Bricq, S., Meriaudeau, F. (2021). Leveraging Uncertainty Estimates to Improve Segmentation Performance in Cardiac MR. In: , 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.

Download citation

  • DOI:

  • 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)