Multi-class Gradient Harmonized Dice Loss with Application to Knee MR Image Segmentation
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.
KeywordsGradient Harmonized Dice Loss Knee MR image Segmentation
This work was partially supported by the National Key Research and Development Program of China (2018YFC0116400).
- 1.Buyu, L., Liu, Y., Wang, X.: Gradient harmonized single-stage detector. arXiv preprint arXiv: 1811.05181 (2018)
- 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.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.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.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.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