Automatic Segmentation of Abdominal MRI Using Selective Sampling and Random Walker
MRI segmentation is a challenging task due to low anatomical contrast and large inter-patient variation. We propose a feature-driven automatic segmentation framework, combining voxel-wise classification with a Random-Walker (RW) based spatial regularization. Typically, such steps are treated independently, i.e. classification outcome is maximized without taking into account the regularization to follow. Herein we present a method for selective sampling of training patches, in view of the posterior spatial regularization. This aims to concentrate training samples near desired anatomical boundaries, around which the gain from a subsequent RW regularization will potentially be minimal. This trades off a lower classification accuracy for a higher joint segmentation performance. We compare our proposed sampling strategy to conventional uniform sampling on 20 full-body MR T1 scans from the VISCERAL dataset, both with RW and Markov Random Fields regularizations, showing Dice improvements of up to 12\(\times \) with the proposed approach.
This work was funded by the Swiss National Science Foundation (SNSF) and the Highly Specialized Medicine (HSM) project of Zurich Department of Health.
- 1.Kahl, F., Alvén, J., Enqvist, O., Fejne, F., et al.: Good features for reliable registration in multi-atlas segmentation. In: ISBI, pp. 12–17 (2015)Google Scholar
- 4.Heinrich, M.P., Maier, O., Handels, H.: Multi-modal multi-atlas segmentation using discrete optimisation and self-similarities. In: ISBI, pp. 27–30 (2015)Google Scholar
- 5.He, B., Huang, C., Jia, F.: Fully automatic multi-organ segmentation based on multi-boost learning and statistical shape model search. In: ISBI, pp. 18–21 (2015)Google Scholar
- 6.Okada, T., Linguraru, M.G., Hori, M., Suzuki, Y., et al.: Multi-organ segmentation in abdominal CT images. In: 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 3986–3989. IEEE (2012)Google Scholar
- 11.Mukhopadhyay, A., Oksuz, I., Bevilacqua, M., Dharmakumar, R., Tsaftaris, S.A.: Unsupervised myocardial segmentation for cardiac MRI. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 12–20. Springer, Cham (2015). doi: 10.1007/978-3-319-24574-4_2 CrossRefGoogle Scholar