The ultrasound imaging is one of most trustful tool to diagnosis the abnormities in kidney. The urinary tract infection is major problem rise due to presence of stones in the kidneys. Automatic detection of region of stone is a challenging task as ultrasound image suffers with speckle noise which is coherent in nature. The present research is aimed to test various binarisation algorithms and conduct statistical analyzes to find the algorithm best suitable for the binarisation of ultrasound images. A comparative study is conducted on clinical and synthetic ultrasound images. The binarisation algorithms are classified into two broad categories namely global and local thresholding. The study included binarisation algorithms such as Otsu's binarisation algorithm under global binarisation, whereas, Souvola's binarisation, Niblack's Binarisation, Bernsen's Binarisation, Morphological binarisation and adaptive binarisation are considered for analysis under local binarisation. These algorithms are tested on 50 ultrasound images collected from ultrasound centres. The statistical metrics considered for testing are Visual Observation and PSNR (Peak signal to noise ratio). The statistical analysis revels that presence of speck is the major hindrance in the segmentation of ultrasound images. Among the tested algorithms, adaptive binarisation and morphological operations based binarisation have shown better results. The speckle noise needs to be suppressed keeping the fine detail like edge information while separating the background from region of interest.

1. N. Otsu, "A threshold selection method from gray-level histograms", IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, Issue 1, pp. 62–66, 1979.
2. W. Niblack, an Introduction to Digital Image Processing, Prentice Hall, Englewood Cliffs, NJ, USA, 1986.
3. J. Sauvola and M. Pietikäinen, "Adaptive document image binarization," Pattern Recognition, vol. 33, no. 2, pp. 225–236, 2000.
4. J. Bernsen, "Dynamic thresholding of grey-level images," in Proceedings of the 8th International Conference on Pattern Recognition, pp. 1251–1255, Paris, France, 1986.
5. Valizadeh, M. , Kabir, E. : "Binarization of degraded document image based on feature space partitioning and classification. International Journal on Document Analysis and Recognition Vol. 15, Issue 1, pp. 57–69, 2012.
6. W. Niblack, "An Introduction to Digital image processing", Prentice Hall, pp 115-116, 1986.
7. Sund,Torbjorn, and Karsten Eilertsen. "An algorithm for fast adaptive image binarization with applications in radiotherapy imaging. " Medical Imaging, IEEE Transactions on 22. 1 (2003): 22-28.
8. Chenyang X, Dzung P, Jerry P. Image segmentation using deformable models. Fitzpatrick JM, Sonka M, editors. SPIE Handbook on Medical Imaging, Medical Image Analysis. 2000;III:129–74.
9. Shareef N, Wang DL, Yagel R. Segmentation of medical images using LEGION. IEEE Trans Med Imaging. 1999;18:74–91.
10. Wiegell, M. R. , Tuch, D. S. , Larsson, H. B. , Wedeen, V. J. , "Automatic segmentation of thalamic nuclei from diffusion tensor magnetic resonance imaging," Neuroimage,2003, pp:391–401.
11. Neculai Archip, Robert Rohling, Peter Cooperberg, etc, "Ultrasound image segmentation using spectral clustering," Ultrasound in Medicine & Biology, 2005, pp:1485-1497.
12. K. B. Raja, M. Madheswaran, and K. Thyagarajah, "Analysis of Ultrasound kidney Images using Content Descriptive Multiple Features for Disorder Identification and ANN based Classification," Proc. of the International Conference on Computing: Theory and Applications, 2007.

Binarization Global Binarisation Local Binarisation Segmentation Ultrasound Images Speckle Noise