Intravascular Ultrasound Tissue Characterization with Sub-class Error-Correcting Output Codes
- 149 Downloads
Intravascular ultrasound (IVUS) represents a powerful imaging technique to explore coronary vessels and to study their morphology and histologic properties. In this paper, we characterize different tissues based on radial frequency, texture-based, and combined features. To deal with the classification of multiple tissues, we require the use of robust multi-class learning techniques. In this sense, error-correcting output codes (ECOC) show to robustly combine binary classifiers to solve multi-class problems. In this context, we propose a strategy to model multi-class classification tasks using sub-classes information in the ECOC framework. The new strategy splits the classes into different sub-sets according to the applied base classifier. Complex IVUS data sets containing overlapping data are learnt by splitting the original set of classes into sub-classes, and embedding the binary problems in a problem-dependent ECOC design. The method automatically characterizes different tissues, showing performance improvements over the state-of-the-art ECOC techniques for different base classifiers. Furthermore, the combination of RF and texture-based features also shows improvements over the state-of-the-art approaches.
KeywordsIntravascular ultrasound Multi-class classification Embedding of dichotomies Sub-classes Error-correcting output codes
This work has been supported in part by TIN2006-15308-C02 and FIS ref. PI061290.
- 1.World Health Organization (2006). World Health Organization Statistics. http://www.who.int/entity/healthinfo/statistics/.
- 4.Windeatt, T., & Ardeshir, G. (2003). Boosted ECOC ensembles for face recognition. International Conference on Visual Information Engineering, 165–168.Google Scholar
- 5.Kittler, J., Ghaderi, R., Windeatt, T., & Matas, J. (2001). Face verification using error correcting output codes. CVPR, 1, 755–760.Google Scholar
- 6.Ghani, R. (2001). Combining labeled and unlabeled data for text classification with a large number of categories. International Conference on Data Mining, 597–598.Google Scholar
- 7.Zhou, J., & Suen, C., (2005). Unconstrained numeral pair recognition using enhanced error correcting output coding: A holistic approach. Proceedings in Conference on Document Analysis and Records, 1, 484–488.Google Scholar
- 10.Pujol, O., Radeva, P., & Vitrià, J. (2006). Discriminant ECOC: A heuristic method for application dependent design of error correcting output codes. PAMI, 28, 1001–1007.Google Scholar
- 11.Pudil, P., Ferri, F., Novovicova, J., & Kittler, J. (1994). Floating search methods for feature selection with nonmonotonic criterion functions. ICPR, 279–283.Google Scholar
- 12.Escalera, S., Pujol, O., & Radeva, P. (2008). Loss-weighted decoding for error-correcting output coding. International Conference on Computer Vision Theory and Applications, 2, 117–122.Google Scholar
- 13.Karla, C., Joel, B., Oriol, P., Salvatella, N., & Radeva, P. (2006). In-vivo IVUS tissue classification: A comparison between RF signal analysis and reconstructed images. Progress in Pattern Recognition (pp. 137–146). Berlin: SpringerGoogle Scholar
- 15.Nilsson, N. J. ( 1965). Learning machines, McGraw-Hill.Google Scholar
- 19.Pujol, O., Rosales, M., & Radeva, P. (2003). Intravascular ultrasound images vessel characterization using adaBoost. Functional Imaging and Modelling of the Heart: Lecture Notes in Computer Science, 242–251.Google Scholar
- 21.de Korte, C. L., PasterKamp, G., van der Steen, A. F. W., & Woutman, H. A. (1999). Characterisation of plaque components with IVUS elastography. IEEE Ultrasonics Symposium Proceedings, 1645-1648.Google Scholar
- 25.Proakis, J., Rader, C., Ling, F., & Nikias, C. (1992). Advanced digital signal processing. Mc Millan.Google Scholar
- 28.Daugman, J. G. (1985). Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. Journal of the Optical Society of America, 2(A),1160–1169.Google Scholar
- 30.Gil, D., Hernandez, A., Rodríguez, O., Mauri, F., & Radeva, P. (2006). Statistical strategy for anisotropic adventitia modelling in IVUS. IEEE Transaction Medical Imaging, 27, 1022–1030.Google Scholar