Analysis of Sonographic Images of Breast

Authors: M. Bastanfard, S. Jafari, B.Jalaeian

Abstract:

Ultrasound images are very useful diagnostic tool to distinguish benignant from malignant masses of the breast. However, there is a considerable overlap between benignancy and malignancy in ultrasonic images which makes it difficult to interpret. In this paper, a new noise removal algorithm was used to improve the images and classification process. The masses are classified by wavelet transform's coefficients, morphological and textural features as a novel feature set for this goal. The Bayesian estimation theory is used to classify the tissues in three classes according to their features.

Keywords: Bayesian estimation theory, breast, ultrasound, wavelet.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1329835

References:

[1] J. R. Sullins. Distributed learning of texture classification. In O. Faugeras, editor, First European Conference on Computer Vision, 2004.
[2] Anil K. Jain. Fundamentals of Digital Image Processing, Prentice Hall International, Inc., 8:313-387, 1989.
[3] B.V., Kluwer. Breast Cancer Research and Treatment, Springer Science+Business Media Academic Publishers B.V., Volume 89, Number 2, January 2005.
[4] C. M. Bishop. Neural Networks for Pattern Recognition. Clarendon Press, 1995.
[5] H. Gmb, European Radiology journal, Springer-Verlag, Volume 14, Number 8, August 2004.
[6] Hassan J. Eghbali, "Adaptive digital image filtering in wavelet domain", vol.12, no 2, pp.275-290, 2003.
[7] Kulkarni S, Muradali D, Moore L. SonoCT compound imaging; 176
[American Roentgen Ray Society 101st Annual Meeting Abstract Book suppl] AJR 2001.
[8] Mallat, S. G. A Theory for multi resolution signal decomposition: The Wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, No. 7, 674-693, 1989.
[9] Pisano ED, Braeuning MP, Burke E. Case 8. Solitary intra ductal papilloma. Radiology; 210:795-798, 1999.
[10] Prof S K Shah, Fellow, V Gandhi, Non-member, "Image Classification Based on Textural features using Artificial Neural Network (ANN)", MS University of Baroda, 2004.
[11] R. ˇS'ara, D. Smutek, P. Sucharda, and ˇS. Svaˇcina. Systematic construction of texture features for Hashimoto-s lymphocytic thyroiditis recognition from sonographic images. In S. Quaglini, P. Barahona, and S. Andreassen, editors, Artificial Intelligence in Medicine, LNCS, Berlin-Heidelberg, Germany, 2001.
[12] R. ˇS'ara. Sonograph images: Texture analysis
[online]. C 1998, last revision 9th of November 2000. http://cmp.felk.cvut.cz/~sara/Sono/sono.html.
[13] R. O. Duda and P. E. Hart. Pattern Classification and Scene Analysis. A Willey-interscience publication, 1973.
[14] Vargas HI, Romero L, Chlebowski RT. Management of bloody nipple discharge. Curr Treat Options Oncol; 3(2):157-61, 2002.
[15] Yeh ED, Keel SB, Slanetz PJ. Intra ductal papilloma of the breast, 2003.