HqRF: New Shape Descriptors to Assist in Breast Cancer Diagnosis

• Walter Alexandre A. de Oliveira UFU
• Denise Guliato UFU

Abstract

Malignant breast tumors and benign masses appear in breast cancer exams with different shape characteristics: the former usually have rough, spiculated, or microlobulated contours, whereas the latter commonly have smooth, round, oval, or macrolobulated contours. Visual features that characterize shape roughness can assist in distinguishing between tumor types. In this work we propose two new approachs to describe 2D and 3D shapes based on Hilbert curves. The descriptors are aplied to content-based images/volumes retrieval. The methods were evaluated using a set of breast contours and a 3D object synthetic database. As the experimental evaluations show, we achieved a mean average precision of 1.00 (to 2D shapes) and 0.99 (to 3D shapes).

References

Alto, H., Rangayyan, R., and Desautels, J. (2005). Content-based retrieval and analysis of mammographic masses. Journal of Electronic Imaging.

American College of Radiology, Reston, VA (1998). Illustrated breast imaging reporting and data system BI-RADSTM ).

Armstrong, J., Ahmed, M., and Chau, S.-C. (2009). A rotation-invariant approach to 2d shape representation using the Hilbert curve. Image Analysis and Recognition, 5627:594–603.

Barcelos, C., Ribeiro, E., and Batista, M. (2008). Image characterization via multilayer neural networks. International Conference on Tools with Artificial Intelligence, pages 325–332.

Chen, W., Giger, M., and Bick, U. (2006). A fuzzy c-means (fcm)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced mr images. Acad. Radiol., 13(1):63–72.

Croft, W., Metzler, D., and Strohman, T. (2009). Search Engines: Information Retrieval in Practice. Addison Wesley.

Ebrahim, Y., Ahmed, M., Abdelsalam, W., and Chau, S.-C. (2008). Shape representation and description using Hilbert curve. Pattern Recognition Letters.

Guliato, D., de Oliveira, W., and Jr., C. T. (2010). A new feature descriptor derived from Hilbert space-filling curve to assist breast cancer classification. 1:303–308.

Guliato, D., Rangayyan, R., Carvalho, J., and Santiago, S. (2008a). Polygonal modeling of contours of breast tumors with the preservation of spicules. IEEE Trans Biomed Eng.

Guliato, D., Rangayyan, R., de Carvalho, J., and Santiago, S. (2008b). Feature extraction from the turning angle function for the classification of contours of breast tumors. J. Digit Imaging.

Gupta, S., P.F., C., and Markey, M. (2006). Breast cancer cadx based on BI RADSTM descriptors from two mammographic views. Med. Phys., 33(6):1810–1817.

Heath, M., Bowyer, K., and Kopans, D. (1998). Current status of the digital database for screening mammography.

Manning, C., Raghavan, P., and Schütze, H. (2009). An Introduction to Information Retrieval. Cambridge University Press.

Prusinkiewicz, P. and Lindenmayer, A. (2004). The Algorithmic Beauty of Plants. Springer-Verlag.

Rangayyan, R., El-Faramawy, N., Desautels, J., and Alim, O. (1997). Measures of acutance and shape for classification of breast tumors. IEEE Transactions on Medical Imaging.

Rangayyan, R., Mudigonda, N., and Desautels, J. (2000). Boundary modelling and shape analysis methods for classification of mammographic masses. Medical and Biological Engineering and Computing.

R.G.-Caballero, C.J.G.-Orellana, H.M.G.-Velasco, and M.M.-Macías (2007). Independent component analysis applied to detection of early breast cancer signs. Computational and Ambient Intelligence.

Shilane, P., Min, P., Kazhdan, M., and Funkhouser, T. (2004). The princeton shape benchmark. Shape Modeling International.

Suckling, J., Parker, J., Dance, D., Astley, S., Hutt, I., Boggis, C., Ricketts, I., Stamatakis, E., Cerneaz, N., Kok, S., Taylor, P., Betal, D., and Savage, J. (1994). The mammographic image analysis society digital mammogram database.

Turnbull, L., Brown, S., Harvey, I., Olivier, C., Drew, P., Napp, V., Hanby, A., and Brown, J. (2010). Comparative effectiveness of mri in breast cancer (comice) trial: a randomised controlled trial. The Lancet, 375(9714):563–571.

Weiqiang, Z., Xiangmin, X., and Wei, H. (2008). Shape and boundary analysis for classification of breast masses. International Symposium on Computational Intelligence and Design.

WHO (2010). Breast cancer: prevention and control.