Abstract
Many state-of-the art visualization techniquesmust be tailored to the specific type of dataset, its modality (CT, MRI, etc.), the recorded object or anatomical region (head, spine, abdomen, etc.) and other parameters related to the data acquisition process. While parts of the information (imaging modality and acquisition sequence) may be obtained from the meta-data stored with the volume scan, there is important information which is not stored explicitly, e.g. anatomical region. Also, meta-data might be incomplete, inappropriate or simply missing.
This paper presents a novel and simple method of determining the type of dataset from previously defined categories. A 2D histogram of the dataset is used as input to the neural network, which classifies it into one of several categories it was trained with. Two types of 2D histograms have been experimented with, one based on intensity and gradient magnitude, the other one on intensity and distance from center.
A significant result is the ability of the system to classify datasets into a specific class after being trained with only one dataset of that class. Other advantages of the method are its easy implementation and its high computational performance.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ankerst, M., Kastenmüller, G., Kriegel, H.-P., Seidl, T.: 3D shape histograms for similarity search and classification in spatial databases. In: Proc. of the 6th Int. Symposium on Advances in Spatial Databases (SSD), London, UK, pp. 207–226. Springer, Heidelberg (1999)
Cabral, B., Cam, N., Foran, J.: Accelerated volume rendering and tomographic reconstruction using texture mapping hardware. In: Proc. of the symposium on Volume visualization (VVS), pp. 91–98. ACM Press, New York (1994)
Cerquides, J., López-Sánchez, M., Ontañón, S., Puertas, E., Puig, A., Pujol, O., Tost, D.: Classification algorithms for biomedical volume datasets (chapter 16). In: Marín, R., Onaindía, E., Bugarín, A., Santos, J. (eds.) CAEPIA 2005. LNCS (LNAI), vol. 4177, pp. 143–152. Springer, Heidelberg (2006)
Chester, D.L.: Why two hidden layers are better than one. In: Int. Joint Conference on Neural Networks, Washington DC, pp. 265–268. Lawrence Erlbaum Associates, Mahwah (1990)
de Villiers, J., Barnard, E.: Backpropagation neural nets with one and two hidden layers. IEEE Trans. on Neural Networks 4(1), 136–141 (1992)
del Río, A., Fischer, J., Köbele, M., Bartz, D., Straßer, W.: Augmented Reality Interaction for Semiautomatic Volume Classification. In: Kjems, E., Blach, R. (eds.) Eurographics Workshop on Virtual Environments (EGVE), Aalborg, Denmark, pp. 113–120. Eurographics Association (2005)
Engel, K., Kraus, M., Ertl, T.: High-quality pre-integrated volume rendering using hardware-accelerated pixel shading. In: Proc. of the ACM SIGGRAPH/EUROGRAPHICS workshop on Graphics hardware (HWWS), pp. 9–16. ACM, New York (2001)
Hadwiger, M., Kniss, J.M., Rezk-Salama, C., Weiskopf, D., Engel, K.: Real-time Volume Graphics. A. K. Peters, Ltd, Natick (2006)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)
Kindlmann, G., Durkin, J.W.: Semi-automatic generation of transfer functions for direct volume rendering. In: Proc. of the 1998 IEEE symposium on Volume visualization (VVS), pp. 79–86. ACM Press, New York (1998)
Kniss, J., Kindlmann, G., Hansen, C.: Interactive Volume Rendering using Multi-dimensional Transfer Functions and Direct Manipulation Widgets. In: Proc. of IEEE Visualization (VIS), pp. 255–262 (2001)
Krüger, J., Westermann, R.: Acceleration Techniques for GPU-based Volume Rendering. In: Proc. of IEEE Visualization (VIS), pp. 287–292 (2003)
Liu, Y., Dellaert, F.: A classification based similarity metric for 3D image retrieval. In: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 800–805 (1998)
Lundström, C., Ljung, P., Ynnerman, A.: Extending and simplifying Transfer Function design in medical Volume Rendering using local histograms. In: Eurographics/IEEE VGTC Symposium on Visualization (EuroVis), June 2005, pp. 263–270 (2005)
Pfister, H., Hardenbergh, J., Knittel, J., Lauer, H., Seiler, L.: The VolumePro real-time ray-casting system. In: Proc. of ACM SIGGRAPH, pp. 251–260. ACM Press/Addison-Wesley Publishing Co., New York (1999)
Rautek, P., Bruckner, S., Gröller, M.E.: Semantic layers for illustrative volume rendering. IEEE Trans. on Visualization and Computer Graphics 13(6), 1336–1343 (2007)
Rezk-Salama, C., Engel, K., Bauer, M., Greiner, G., Ertl, T.: Interactive volume rendering on standard PC graphics hardware using multi-textures and multi-stage rasterization. In: Proc. of the ACM SIGGRAPH/EUROGRAPHICS workshop on Graphics hardware (HWWS), pp. 109–118. ACM Press, New York (2000)
Rezk-Salama, C., Keller, M., Kohlmann, P.: High-Level User Interfaces for Transfer Function Design with Semantics. IEEE Trans. on Visualization and Computer Graphics (Proc. IEEE Visualization) 11(5), 1021–1028 (2006)
Roettger, S., Guthe, S., Weiskopf, D., Ertl, T., Strasser, W.: Smart Hardware-Accelerated Volume Rendering. In: Proc. of the symposium on Data visualisation 2003 (VISSYM), Aire-la-Ville, Switzerland, pp. 231–238. Eurographics Association (2003)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)
Serlie, I.W.O., Vos, F.M., Truyen, R., Post, F.H., van Vliet, L.J.: Classifying CT image data into material fractions by a scale and rotation invariant edge model. IEEE Trans. on Image Processing 16(12), 2891–2904 (2007)
Stegmaier, S., Strengert, M., Klein, T., Ertl, T.: A Simple and Flexible Volume Rendering Framework for Graphics-Hardware-based Raycasting. In: Proc. of the Int. Workshop on Volume Graphics, pp. 187–195 (2005)
Svozil, D., Kvasnička, V., Pospíchal, J.: Introduction to multi-layer feed-forward neural networks. Chemometrics and Intelligent Laboratory Systems 39(20), 43–62 (1997)
Tzeng, F.-Y., Lum, E.B., Ma, K.-L.: A Novel Interface for Higher-Dimensional Classification of Volume Data. In: Proc. of IEEE Visualization (VIS), pp. 505–512 (2003)
Šereda, P., Vilanova Bartolí, A., Serlie, I.W.O., Gerritsen, F.A.: Visualization of Boundaries in Volumetric Data Sets Using LH Histograms. Trans. on Vis. and Comp. Graph. 12(2), 208–218 (2006)
Wilson, O., Van Gelder, A., Wilhelms, J.: Direct Volume Rendering via 3D-textures. Technical Report UCSC-CRL-94-19, Univ. of California, Santa Cruz (1994)
Zhang, J., Sun, J.: Automatic classification of MRI images for three-dimensional volume reconstruction by using general regression neural networks. In: IEEE Nuclear Science Symposium Conference Record, October 2003, vol. 5, pp. 3188–3189 (2003)
Zukić, D., Elsner, A., Avdagić, Z., Domik, G.: Neural networks in 3D medical scan visualization. In: Plemenos, D. (ed.) In Proc. of the Int. Conf. on Computer Graphics and Artificial Intelligence (3IA), TEI Athens, May 2008, pp. 183–190 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Zukić, D., Rezk-Salama, C., Kolb, A. (2009). Classifying Volume Datasets Based on Intensities and Geometric Features. In: Plemenos, D., Miaoulis, G. (eds) Intelligent Computer Graphics 2009. Studies in Computational Intelligence, vol 240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03452-7_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-03452-7_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03451-0
Online ISBN: 978-3-642-03452-7
eBook Packages: EngineeringEngineering (R0)