Advertisement

Multi-class Gradient Harmonized Dice Loss with Application to Knee MR Image Segmentation

  • Qin Liu
  • Xiongfeng Tang
  • Deming Guo
  • Yanguo Qin
  • Pengfei Jia
  • Yiqiang Zhan
  • Xiang Zhou
  • Dijia WuEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11769)

Abstract

The Dice loss function is widely used in volumetric medical image segmentation for its robustness against the imbalance between the numbers of foreground and background voxels. However, it is not able to differentiate hard examples from easy ones, which usually comprise the majority of training examples and therefore dominate the loss function. In this work, we propose a novel loss function, termed as Gradient Harmonized Dice Loss, to both address the quantity imbalance between classes and focus on hard examples in training, with further generalization to multi-class segmentation. The proposed loss function is employed in a 3D fully convolutional neural network for multiple object segmentation of MRI knee joint images and validated on both public SKI10 dataset and 637 MRI knee scans collected from local hospitals. The experimental results show that the Gradient Harmonized Dice Loss outperforms the popular loss functions, such as Dice loss and Focal loss, and achieves the state-of-the-art results on the validation data of SKI10.

Keywords

Gradient Harmonized Dice Loss Knee MR image Segmentation 

Notes

Acknowledgement

This work was partially supported by the National Key Research and Development Program of China (2018YFC0116400).

References

  1. 1.
    Buyu, L., Liu, Y., Wang, X.: Gradient harmonized single-stage detector. arXiv preprint arXiv: 1811.05181 (2018)
  2. 2.
    Felix, A., Alexander, T., Moritz, E., Zachow, S.: Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks: data from the osteoarthritis initiative. Med. Image Anal. 52, 109–118 (2019)CrossRefGoogle Scholar
  3. 3.
    Folkesson, J., Dam, E.B., Olsen, O.F., Karsdal, M., Pettersen, P., Christiansen, C.: Automatic quantification of local and global articular cartilage surface curvatures: biomarkers for osteoarthritis? Magn. Reson. Med. 59, 1340–1346 (2008)CrossRefGoogle Scholar
  4. 4.
    Fripp, J., Crozier, S., Warfield, S., Ourselin, S.: Automatic segmentation and quantitative analysis of the articular cartilages from magnetic resonance images of the knee. IEEE Trans. Med. Imaging 29, 55–64 (2010)CrossRefGoogle Scholar
  5. 5.
    Lin, T.Y., Goyal, P., Girshick, R., Kaiming, H., Dollar, P.: Focal loss for dense object detection. In: IEEE International Conference on Computer Vision (ICCV), pp. 2999–3007 (2017)Google Scholar
  6. 6.
    Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565–571. IEEE (2016)Google Scholar
  7. 7.
    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
  8. 8.
    Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Jorge Cardoso, M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso, M.J., et al. (eds.) DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 240–248. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67558-9_28CrossRefGoogle Scholar
  9. 9.
    Tobias, H., Bryan, J.M., Martin, A.S., Niethammer, M., Simon, K.W.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: MICCAI Workshop on Medical Image Analysis for the Clinic, pp. 207–214 (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Qin Liu
    • 1
  • Xiongfeng Tang
    • 2
  • Deming Guo
    • 2
  • Yanguo Qin
    • 2
  • Pengfei Jia
    • 1
  • Yiqiang Zhan
    • 1
  • Xiang Zhou
    • 1
  • Dijia Wu
    • 1
    Email author
  1. 1.Shanghai United Imaging Intelligence Co., Ltd.ShanghaiChina
  2. 2.Department of OrthopedicsThe Second Hospital of Jilin UniversityChangchunChina

Personalised recommendations