Spinal Cord Gray Matter-White Matter Segmentation on Magnetic Resonance AMIRA Images with MD-GRU
The small butterfly shaped structure of spinal cord (SC) gray matter (GM) is challenging to image and to delineate from its surrounding white matter (WM). Segmenting GM is up to a point a trade-off between accuracy and precision. We propose a new pipeline for GM-WM magnetic resonance (MR) image acquisition and segmentation. We report superior results as compared to the ones recently reported in the SC GM segmentation challenge and show even better results using the averaged magnetization inversion recovery acquisitions (AMIRA) sequence. Scan-rescan experiments with the AMIRA sequence show high reproducibility in terms of Dice coefficient, Hausdorff distance and relative standard deviation. We use a recurrent neural network (RNN) with multi-dimensional gated recurrent units (MD-GRU) to train segmentation models on the AMIRA dataset of 855 slices. We added a generalized dice loss to the cross entropy loss that MD-GRU uses and were able to improve the results.
KeywordsSegmentation Spinal cord Gray matter White matter Deep learning RNN MD-GRU
We thank Dr. Matthias Weigel, Prof. Dr. Oliver Bieri and Tanja Haas for the MR acquisitions with the AMIRA sequence.
- 4.Horváth, A., et al.: A principled approach to combining inversion recovery images. In: Proceedings of the 26th Annual Meeting of ISMRM, Paris, France, June 2018Google Scholar
- 6.Porisky, A., et al.: Grey matter segmentation in spinal cord MRIs via 3D convolutional encoder networks with shortcut connections. In: Cardoso, M.J., et al. (eds.) DLMIA/ML-CDS-2017. LNCS, vol. 10553, pp. 330–337. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67558-9_38CrossRefGoogle 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