Semi-supervised Segmentation Using Multiple Segmentation Hypotheses from a Single Atlas
A semi-supervised segmentation method using a single atlas is presented in this paper. Traditional atlas-based segmentation suffers from either a strong bias towards the selected atlas or the need for manual effort to create multiple atlas images. Similar to semi-supervised learning in computer vision, we study a method which exploits information contained in a set of unlabelled images by mutually registering them non-rigidly and propagating the single atlas segmentation over multiple such registration paths to each target. These multiple segmentation hypotheses are then fused by local weighting based on registration similarity. Our results on two datasets of different anatomies and image modalities, corpus callosum MR and mandible CT images, show a significant improvement in segmentation accuracy compared to traditional single atlas based segmentation. We also show that the bias towards the selected atlas is minimized using our method. Additionally, we devise a method for the selection of intermediate targets used for propagation, in order to reduce the number of necessary inter-target registrations without loss of final segmentation accuracy.
KeywordsTarget Image Label Propagation Segmentation Accuracy Normalize Cross Correlation Support Sample
Unable to display preview. Download preview PDF.
- 2.Furnstahl, P., Fuchs, T., Schweizer, A., Nagy, L., Székely, G., Harders, M.: Automatic and robust forearm segmentation using graph cuts. In: ISBI, pp. 77–80 (2008)Google Scholar
- 7.Rohlfing, T., Brandt, R., Menzel, R., Russakoff, D., Maurer, C.: Quo vadis, atlas-based segmentation? In: Handbook of Biomedical Image Analysis, pp. 435–486 (2005)Google Scholar
- 14.Chapelle, O., Schölkopf, B., Zien, A. (eds.): Semi-supervised learning, vol. 2. MIT Press, Cambridge (2006)Google Scholar
- 15.Wang, F., Wang, J., Zhang, C., Shen, H.C., Bay, C.W., Kong, H.: Semi-Supervised Classification Using Linear Neighborhood Propagation. Sci. & Tech. (2006)Google Scholar
- 16.Guillaumin, M., Verbeek, J., Schmid, C.: Multimodal semi-supervised learning for image classification. In: IEEE CVPR, pp. 902–909 (June 2010)Google Scholar
- 17.Zhu, X., Ghahramani, Z.: Learning from labeled and unlabeled data with label propagation. Technical report, School Comput. Sci. Carnegie Mellon Univ. (2002)Google Scholar