Multi atlas based image segmentation is a successful method in recent days in segmenting and labeling MRI images and is mainly based on registration and label fusion. In atlas-based label propagation, an pre labeled image is registered to the target image using image registration methods which produces a segmentation based on the labels in the atlas image. The segmentation of the unknown input image is then achieved by warping the atlas label to the target image space. A single atlas will produce a single segmentation which may prone to errors whereas use of N atlases gives N segmentations; then all N segmentations will be merged to get a final target segmentation. Use of N atlas gives more accurate result than use of single atlas. Many label fusion methods have been proposed. In this paper, the performance of two label fusion methods for segmenting three crucial subcortical brain structures using atlases is evaluated and compared. The result shows that joint label fusion outperforms majority voting method.

MR Images, atlas based segmentation, multiple atlases, brain structures, label fusion

[1]. Lotjonen, J., Wolz, R., Koikkalainen, J., Thurfjell, L., Waldemar, G., Soininen, H., Rueckert, D.: Fast and robust multi-atlas segmentation of brain magnetic resonance images. Neuroimage 49, 2352–2365 (2010).
[2]. Heckemann R, Hajnal J, Aljabar P, Rueckert D, Hammers A. Automatic anatomical brain MRI segmentation combining label propagation and decision fusion. NeuroImage. 2006;33(1):115–126.
[3]. A. F. Frangi, D. Rueckert, J. A. Schnabel, and W. J. Niessen, “Automatic construction of multiple-object three-dimensional statistical shape models: application to cardiac modeling,” Medical Imaging, IEEE Transactions on, vol. 21, no. 9, pp. 1151–1166, 2002.
[4]. 4.M. Lorenzo-Vald´es, G. I. Sanchez-Ortiz, R. Mohiaddin, and D. Rueckert, “Atlas-Based Segmentation and Tracking of 3D Cardiac MR Images Using Non-rigid Registration,” in MICCAI (1), pp. 642–650,2002.
[5]. S. Joshi, B. Davis, M. Jomier, and G. Gerig, “Unbiased diffeomorphic atlas construction for computational anatomy.” Neuroimage, vol. 23 Suppl 1, 2004.
[6]. 6.P. Lorenzen, M. Prastawa, B. Davis, G. Gerig, E. Bullitt, and S. Joshi, “Multi-Modal Image Set Registration and Atlas Formation,” Medical Image Analisys, vol. 10, no. 3, pp. 440–451, June 2006.
[7]. 7. Dipanjan Moitra, Dr. Rakesh Kumar Mandal “SEGMENTATION STRATEGY OF PETBRAIN TUMOR IMAGE” Indian Journal of Computer Science and Engineering (IJCSE), ISSN : 0976-5166 Vol. 4 No.5 Oct-Nov 2013 .
[8]. 8. D. N. Lohare, R. Telgade, R. R. Manza, “Review Brain Tumor Detection Using Image Processing Techniques”, International Journal of Computer Sciences and Engineering, Vol.6, Issue.5, pp.735-740, 2018.
[9]. 9. Huo J., Wang G., Wu Q.M.J., Thangarajah A. (2015) Label Fusion for Multi-atlas Segmentation Based on Majority Voting. In: Kamel M., Campilho A. (eds) Image Analysis and Recognition. ICIAR 2015
[10]. 10. Wang, H., Suh, J. W., Das, S. R., Pluta, J., Craige, C., & Yushkevich, P. A. (2013). Multi-Atlas Segmentation with Joint Label Fusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(3), 611–623.