Comparative Validation of Graphical Models for Learning Tumor Segmentations from Noisy Manual Annotations
Classification-based approaches for segmenting medical images commonly suffer from missing ground truth: often one has to resort to manual labelings by human experts, which may show considerable intra-rater and inter-rater variability. We experimentally evaluate several latent class and latent score models for tumor classification based on manual segmentations of different quality, using approximate variational techniques for inference. For the first time, we also study models that make use of image feature information on this specific task. Additionally, we analyze the outcome of hybrid techniques formed by combining aspects of different models. Benchmarking results on simulated MR images of brain tumors are presented: while simple baseline techniques already gave very competitive performance, significant improvements could be made by explicitly accounting for rater quality. Furthermore, we point out the transfer of these models to the task of fusing manual tumor segmentations derived from different imaging modalities on real-world data.
Unable to display preview. Download preview PDF.
- Buntine, W.: Operations for Learning with Graphical Models. Journal of Artificial Intelligence Research 2, 159–225 (1994)Google Scholar
- Minka, T.: Expectation Propagation for approximate Bayesian inference. In: Proceedings of the 17th Conference on Uncertainty in Artificial Intelligence, pp. 362–369 (2001)Google Scholar
- Minka, T., Winn, J., Guiver, J., et al.: Infer.NET 2.3. Microsoft Research, Cambridge (2009), http://research.microsoft.com/infernet
- Minka, T., Winn, J.: Gates. In: Koller, D., Schuurmans, D., Bengio, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems 21, pp. 1073–1080. MIT Press, Cambridge (2009)Google Scholar
- Schmidt, M., Levner, I., Greiner, R., et al.: Segmenting Brain Tumors using Alignment-Based Features. In: Proceedings of the Fourth International Conference on Machine Learning and Applications (ICMLA), pp. 215–220 (2005)Google Scholar
- Smyth, P., Fayyad, U., Burl, M., et al.: Inferring Ground Truth From Subjective Labelling of Venus Images. In: Tesauro, G., Toretzy, D., Leen, T. (eds.) Advances in Neural Information Processing Systems, vol. 7, pp. 1085–1092. MIT Press, Cambridge (1995)Google Scholar
- Whitehill, J., Ruvolo, P.: fan Wu, T., et al.: Whose Vote Should Count More: Optimal Integration of Labels from Labelers of Unknown Expertise. In: Bengio, Y., Schuurmans, D., Lafferty, J., Williams, C.K.I., Culotta, A. (eds.) Advances in Neural Information Processing Systems 22, pp. 2035–2043. MIT Press, Cambridge (2009)Google Scholar