Abstract
This paper presents a new supervised learning framework for the efficient recognition and segmentation of anatomical structures in 3D computed tomography (CT), with as little training data as possible. Training supervised classifiers to recognize organs within CT scans requires a large number of manually delineated exemplar 3D images, which are very expensive to obtain. In this study, we borrow ideas from the field of active learning to optimally select a minimum subset of such images that yields accurate anatomy segmentation. The main contribution of this work is in designing a combined generative-discriminative model which: i) drives optimal selection of training data; and ii) increases segmentation accuracy. The optimal training set is constructed by finding unlabeled scans which maximize the disagreement between our two complementary probabilistic models, as measured by a modified version of the Jensen-Shannon divergence. Our algorithm is assessed on a database of 196 labeled clinical CT scans with high variability in resolution, anatomy, pathologies, etc. Quantitative evaluation shows that, compared with randomly selecting the scans to annotate, our method decreases the number of training images by up to 45%. Moreover, our generative model of body shape substantially increases segmentation accuracy when compared to either using the discriminative model alone or a generic smoothness prior (e.g. via a Markov Random Field).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Belis, M., Guiasu, S.: A quantitative-qualitative measure of information in cybernetic systems. IEEE Trans. Inf. Theory 14(4), 593–594 (1968)
Boykov, Y., Veksler, O., Zabih, R.: Efficient approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 20(12), 1222–1239 (2001)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Breunig, M., Kriegel, H., Ng, R., Sander, J.: LOF: identifying density-based local outliers. Sigmod Rec. 29(2), 93–104 (2000)
Criminisi, A., Sharp, T., Blake, A.: GeoS: Geodesic image segmentation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 99–112. Springer, Heidelberg (2008)
Freund, Y., Seung, H., Shamir, E., Tishby, N.: Selective sampling using the query by committee algorithm. Mach. Learn. 28(2), 133–168 (1997)
Geremia, E., Menze, B.H., Clatz, O., Konukoglu, E., Criminisi, A., Ayache, N.: Spatial decision forests for MS lesion segmentation in multi-channel MR images. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6361, pp. 111–118. Springer, Heidelberg (2010)
Lewis, D., Gale, W.: A sequential algorithm for training text classifiers. In: Proc. ACM SIGIR Conf. Res. and Dev. in Inf., pp. 3–12 (1994)
Linguraru, M.G., Sandberg, J.K., Li, Z., Pura, J.A., Summers, R.M.: Atlas-based automated segmentation of spleen and liver using adaptive enhancement estimation. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009. LNCS, vol. 5762, pp. 1001–1008. Springer, Heidelberg (2009)
Montillo, A., Shotton, J., Winn, J., Iglesias, J.E., Metaxas, D., Criminisi, A.: Entangled decision forests and their application for semantic segmentation of CT images. In: Székely, G., Hahn, H.K. (eds.) IPMI 2011. LNCS, vol. 6801, pp. 184–196. Springer, Heidelberg (2011), (this volume)
Muslea, I., Minton, S., Knoblock, C.: Active learning with multiple views. J. Artif. Intell. Res. 27(1), 203–233 (2006)
Park, H., Bland, P., Meyer, C.: Construction of an abdominal probabilistic atlas and its application in segmentation. IEEE Trans. Med. Im. 22(4), 483–492 (2003)
Seifert, S., Barbu, A., Zhou, S., Liu, D., Feulner, J., Huber, M.S.M., Cavallaro, A., Comaniciu, D.: Hierarchical parsing and semantic navigation of full body CT data. In: Proc. of SPIE., vol. 7258, pp. 725902–725909 (2009)
Settles, B.: Active learning literature survey. Computer Sciences Technical Report 1648, University of Wisconsin–Madison (2009)
Shimizu, A., Ohno, R., Ikegami, T., Kobatake, H., Nawano, S., Smutek, D.: Segmentation of multiple organs in non-contrast 3D abdominal CT images. Int. J. Comput. Assisted Radiol. and Surg. 2(3), 135–142 (2007)
Ten Berge, J.: Orthogonal Procrustes rotation for two or more matrices. Psychometrika 42(2), 267–276 (1977)
Tipping, M., Bishop, C.: Probabilistic principal component analysis. J. R. Stat. Soc.: Series B 61(3), 611–622 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Iglesias, J.E., Konukoglu, E., Montillo, A., Tu, Z., Criminisi, A. (2011). Combining Generative and Discriminative Models for Semantic Segmentation of CT Scans via Active Learning. In: Székely, G., Hahn, H.K. (eds) Information Processing in Medical Imaging. IPMI 2011. Lecture Notes in Computer Science, vol 6801. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22092-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-22092-0_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22091-3
Online ISBN: 978-3-642-22092-0
eBook Packages: Computer ScienceComputer Science (R0)