Flexible and Latent Structured Output Learning
Malignant tumors that contain a high proportion of regions deprived of adequate oxygen supply (hypoxia) in areas supplied by a microvessel (i.e., a microcirculatory supply unit - MCSU) have been shown to present resistance to common cancer treatments. Given the importance of the estimation of this proportion for improving the clinical prognosis of such treatments, a manual annotation has been proposed, which uses two image modalities of the same histological specimen and produces the number and proportion of MCSUs classified as normoxia (normal oxygenation level), chronic hypoxia (limited diffusion), and acute hypoxia (transient disruptions in perfusion), but this manual annotation requires an expertise that is generally not available in clinical settings. Therefore, in this paper, we propose a new methodology that automates this annotation. The major challenge is that the training set comprises weakly labeled samples that only contains the number of MCSU types per sample, which means that we do not have the underlying structure of MCSU locations and classifications. Hence, we formulate this problem as a latent structured output learning that minimizes a high order loss function based on the number of MCSU types, where the underlying MCSU structure is flexible in terms of number of nodes and connections. Using a database of 89 pairs of weakly annotated images (from eight tumors), we show that our methodology produces highly correlated number and proportion of MCSU types compared to the manual annotations.
KeywordsWeakly supervised training Latent structured output learning High order loss function
Unable to display preview. Download preview PDF.
- 3.Yu, C.N.J., Joachims, T.: Learning structural svms with latent variables. In: ICML, pp. 1169–1176 (2009)Google Scholar
- 4.Kumar, M.P.: Weakly Supervised Learning for Structured Output Prediction. PhD thesis, Ecole Normale Supérieure de Cachan (2014)Google Scholar
- 5.Lou, X., Hamprecht, F.: Structured learning from partial annotations (2012). arXiv preprint arXiv:1206.6421
- 6.Pletscher, P., Kohli, P.: Learning low-order models for enforcing high-order statistics. In: AISTATS, pp. 886–894 (2012)Google Scholar
- 7.Carneiro, G., et al.: Semantic-based indexing of fetal anatomies from 3-d ultrasound data using global/semi-local context and sequential sampling. In: CVPR (2008)Google Scholar
- 9.Tu, Z., et al.: Brain anatomical structure segmentation by hybrid discriminative/generative models. TMI 27(4), 495–508 (2008)Google Scholar
- 10.Barbu, A., et al.: Automatic detection and segmentation of lymph nodes from ct data. TMI 31(2), 240–250 (2012)Google Scholar
- 11.Pauly, O., Glocker, B., Criminisi, A., Mateus, D., Möller, A.M., Nekolla, S., Navab, N.: Fast multiple organ detection and localization in whole-body MR dixon sequences. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011, Part III. LNCS, vol. 6893, pp. 239–247. Springer, Heidelberg (2011) CrossRefGoogle Scholar
- 13.Fiaschi, L., et al.: Tracking indistinguishable translucent objects over time using weakly supervised structured learning. In: CVPR (2014)Google Scholar
- 14.Mahapatra, D., et al.: Weakly supervised semantic segmentation of crohn’s disease tissues from abdominal mri. In: ISBI (2013)Google Scholar
- 15.Quellec, G., et al.: Weakly supervised classification of medical images. In: ISBI (2012)Google Scholar
- 19.Zhu, J., et al.: Multi-class adaboost. Statistics and Its (2009)Google Scholar
- 20.Tsochantaridis, I., et al.: Support vector machine learning for interdependent and structured output spaces. In: ICML (2004)Google Scholar
- 22.Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)Google Scholar
- 23.Grygorash, O., Zhou, Y., Jorgensen, Z.: Minimum spanning tree based clustering algorithms. In: ICTAI (2006)Google Scholar
- 24.Peng, T., Yigitsoy, M., Eslami, A., Bayer, C., Navab, N.: Deformable registration of multi-modal microscopic images using a pyramidal interactive registration-learning methodology. In: Ourselin, S., Modat, M. (eds.) WBIR 2014. LNCS, vol. 8545, pp. 144–153. Springer, Heidelberg (2014) Google Scholar
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 2.5 International License (http://creativecommons.org/licenses/by-nc/2.5/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
The images or other third party material in this chapter are included in the chapter's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.