Advertisement

Combining Good Old Random Forest and DeepLabv3+ for ISLES 2018 CT-Based Stroke Segmentation

  • Lasse Böhme
  • Frederic Madesta
  • Thilo Sentker
  • René WernerEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11383)

Abstract

Recent years’ segmentation challenges on Ischemic Stroke Lesion Segmentation (ISLES) attracted great interest in the medical image computing domain, reflected in >80 citations of the 2017 summary article of the initial ISLES 2015 challenge [1]. While 2015–2017 ISLES challenges focussed on MRI images, the 2018 challenge takes into account clinical relevance of (perfusion) CT to triage stroke patients. Thus, from a methodological point of view, it is now to be analyzed whether and to what extent the 2015–2017 methods can be adapted to automated core lesion segmentation using acute stroke CT perfusion imaging.

We strive to deliver a baseline for ISLES 2018 by using two well established machine learning-based segmentation approaches already applied for the initial ISLES 2015 challenge: random forest (RF) with classical hand-crafted image features (i.e. the most frequently used type of algorithm in ISLES 2015) and encoder-decoder-style convolutional neuronal networks (CNNs). In detail, for CNN-based segmentation, we employ the DeepLabv3+ architecture. The performance of the individual as well as a combination of the segmentation approaches is evaluated based on the ISLES 2018 training data set, and respective results are presented. Aiming at an ISLES 2018-specific performance baseline, we do neither make use of additional data other than the provided challenge data nor perform extensive data augmentation. The results highlight the potential to improve stroke lesion segmentation accuracy by combining RF and CNN information.

Keywords

ISLES challenge Stroke segmentation Random forest Convolutional neural networks (CNN) 

Notes

Acknowledgements

Supported by Forschungszentrum Medizintechnik Hamburg, grant 02fmthh2017. We further thank NVIDIA for donating the applied Titan Xp GPU.

References

  1. 1.
    Maier, O., Menze, B.H., von der Gablentz, J., Hani, L., Heinrich, M.P., et al.: ISLES 2015 - a public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI. Med. Image Anal. 35, 250–269 (2017)CrossRefGoogle Scholar
  2. 2.
    Thrift, A.G., Thayabaranathan, T., Howard, G., Howard, V.J., Rothwell, P.M., et al.: Global stroke statistics. Int. J. Stroke 12(121), 13–32 (2017)CrossRefGoogle Scholar
  3. 3.
    ISLES challenge(s). http://www.isles-challenge.org
  4. 4.
    Winzeck, S., Hakim, A., McKinley, R., Pinto, J., Alves, V., et al.: ISLES 2016 and 2017-benchmarking ischemic stroke lesion outcome prediction based on multispectral MRI. Front. Neurol. 9, 679 (2018)CrossRefGoogle Scholar
  5. 5.
    Tatlisumak, T.: Is CT or MRI the method of choice for imaging patients with acute stroke? Why should men divide if fate has united? Stroke 33, 2144–2145 (2002)CrossRefGoogle Scholar
  6. 6.
    Wang, C.-W., Lee, J.-H.: Stroke lesion segmentation of 3D brain MRI using multiple random forests and 3D registration. In: Proceedings of MICCAI-ISLES 2015, pp. 35–38 (2015)Google Scholar
  7. 7.
    Chen, L., Bentley, P., Rueckert, D.: A novel framework for sub-acute stroke lesion segmentation based on random forest. In: Proceedings of MICCAI-ISLES 2015, pp. 9–12 (2015)Google Scholar
  8. 8.
    Maier, O., Wilms, M., Handels, H.: Random forests with selected features for stroke lesion segmentation. In: Proceedings of MICCAI-ISLES 2015, pp. 17–22 (2015)Google Scholar
  9. 9.
    Reza, S.M.S., Pei, L., Iftekharuddin, K.M.: Ischemic stroke lesion segmentation using local gradient and texture features. In: Proceedings of MICCAI-ISLES 2015, pp. 23–26 (2015)Google Scholar
  10. 10.
    Robben, D., Christiaens, D., Rangarajan, J.R., Gelderblom, J., Joris, P., et al.: ISLES challenge 2015: a voxel-wise, cascaded classification approach to stroke lesion segmentation. In: Proceedings of MICCAI-ISLES 2015, pp. 27–30 (2015)Google Scholar
  11. 11.
    Halme, H.-L., Korvenoja, A., Salli, E.: ISLES (SISS) challenge 2015: segmentation of stroke lesions using spatial normalization, random forest classification and contextual clustering. In: Proceedings of MICCAI-ISLES 2015, pp. 31–34 (2015)Google Scholar
  12. 12.
    Goetz, M., Weber, C., Maier-Hein, K.: Input data adaptive learning (IDAL) for sub-acute ischemic stroke lesion segmentation. In: Proceedings of MICCAI-ISLES 2015, pp. 39–42 (2015)Google Scholar
  13. 13.
    Mahmood, Q., Basit, A.: Automatic ischemic stroke lesion segmentation in multi-spectral MRI images using random forests classifier. In: Proceedings of MICCAI-ISLES 2015, pp. 43–46 (2015)Google Scholar
  14. 14.
    Jesson, A., Arbel, T.: Hierarchical segmentation of normal and lesional structures combining an ensemble of probabilistic local classifiers and regional random forest classification. In: Proceedings of MICCAI-ISLES 2015, pp. 57–62 (2015)Google Scholar
  15. 15.
    Muschelli, J.: Prediction of ischemic lesions using local image properties and random forests. In: Proceedings of MICCAI-ISLES 2015, pp. 63–65 (2015)Google Scholar
  16. 16.
    Kamnitsas, K., Chen, L., Ledig, C., Rueckert, D., Glocker, B.: Multi-scale 3D convolutional neural networks for lesion segmentation in brain MRI. In: Proceedings of MICCAI-ISLES 2015, pp. 13–16 (2015)Google Scholar
  17. 17.
    Dutil, F., Havaei, M., Pal, C., Larochelle, H., Jodoin, P.-M.: A convolutional neural network approach to brain lesion segmentation. In: Proceedings of MICCAI-ISLES 2015, pp. 51–56 (2015)Google Scholar
  18. 18.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  19. 19.
    Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  20. 20.
    Maier, O.: MedPy – medical image processing in Python. https://pypi.org/project/MedPy
  21. 21.
    Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833–851. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01234-2_49CrossRefGoogle Scholar
  22. 22.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Lasse Böhme
    • 1
  • Frederic Madesta
    • 1
    • 2
  • Thilo Sentker
    • 1
    • 2
  • René Werner
    • 1
    • 2
    Email author
  1. 1.Department of Computational NeuroscienceUniversity Medical Center Hamburg-EppendorfHamburgGermany
  2. 2.DAISYlabsForschungszentrum Medizintechnik Hamburg (fmthh)HamburgGermany

Personalised recommendations