Abstract
We propose a graph cut (GC) based approach for combining annotations from multiple experts and segmenting Crohns disease (CD) tissues in magnetic resonance (MR) images. Random forest (RF) based semi supervised learning (SSL) predicts missing expert labels while a novel self consistency (SC) score quantifies the reliability of each expert label and also serves as the penalty cost in a second order Markov random field (MRF) cost function. The final consensus label is obtained by GC optimization. Experimental results on synthetic images and real CD patient data show our final segmentation to be more accurate than those obtained by competing methods. It also highlights the effectiveness of SC score in quantifying expert reliability and accuracy of SSL in predicting missing labels.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Vos, F.M., et. al.: Computational modeling for assessment of IBD: to be or not to be? In: Proceedings of IEEE EMBC, pp. 3974–3977 (2012)
Mahapatra, D., Schüffler, P., Tielbeek, J., Makanyanga, J., et al.: Automatic detection and segmentation of Crohn’s disease tissues from abdominal MRI. IEEE Trans. Med. Imaging 32, 1232–1248 (2013)
Mahapatra, D., Schüffler, P., Tielbeek, J., Vos, F., Buhmann, J.: Semi-supervised and active learning for automatic segmentation of Crohn’s disease. In: Proceedings of MICCAI, Part 2, pp. 214–221 (2013)
Schüffler, P., Mahapatra, D., Tielbeek, J., Vos, F., et al.: A model development pipeline for crohns disease severity assessment from magnetic resonance images. In: Proceedings of MICCAI-ABD, pp. 1–10 (2013)
Warfield, S., Zhou, K., Wells, W.: Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans. Med. Imaging 23, 903–921 (2004)
Commowick, O., Warfield, S.: Incorporating priors on expert performance parameters for segmentation validation and label fusion: a maximum a posteriori STAPLE. In: Proceedings of MICCAI Part III, pp. 25–32 (2010)
Commowick, O., Akhondi-Asl, A., Warfield, S.: Estimating a reference standard segmentation with spatially varying performance parameters: local MAP STAPLE. IEEE Trans. Med. Imaging 31, 1593–1606 (2012)
Raykar, V., Yu, S., Zhao, L., Valadez, G., et al.: Learning from crowds. J. Mach. Learn. Res. 11, 1297–1322 (2010)
Chatelain, P., Pauly, O., Peter, L., Ahmadi, A., et al.: Learning from multiple experts with random forests: application to the segmentation of the midbrain in 3D ultrasound. In: Proceedings of MICCAI Part II, pp. 230–237 (2013)
Budvytis, I., Badrinarayanan, V., Cipolla, R.: Semi-supervised video segmentation using tree structured graphical models. In: IEEE CVPR, pp. 2257–2264 (2011)
Criminisi, A., Shotton, J.: Decision Forests for Computer Vision and Medical Image Analysis. Springer, London (2013)
Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)
Boykov, Y., Veksler, O.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23, 1222–1239 (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Mahapatra, D. et al. (2014). Combining Multiple Expert Annotations Using Semi-supervised Learning and Graph Cuts for Crohn’s Disease Segmentation. In: Yoshida, H., Näppi, J., Saini, S. (eds) Abdominal Imaging. Computational and Clinical Applications. ABD-MICCAI 2014. Lecture Notes in Computer Science(), vol 8676. Springer, Cham. https://doi.org/10.1007/978-3-319-13692-9_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-13692-9_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13691-2
Online ISBN: 978-3-319-13692-9
eBook Packages: Computer ScienceComputer Science (R0)