Segmentation of masses from breast ultrasound images using parametric active contour algorithm

The active contour (Snake) is a computer generated curve that can trace boundaries of images. As a method which applies the computer technology in mathematics, Snake is computationally formulated based on controlled continuous splines and adopts the mathematical concept of energy minimization. This paper presents the application of Snake for the segmentation of masses on breast ultrasound images. The images used are taken from Malaysian population. The boundaries of the masses identified may be used in classification of cancers or non-cancerous masses. Specifically the Balloon Snake is applied in segmenting the masses in the breast ultrasound images. Comparison on the masses areas segmented by the Balloon Snake is done against the areas traced by an expert (radiologist). It is found that from forty-five masses tested, the average percentage area difference of Balloon Snake is 4.47%. This implies that the accuracy of segmentation results for the Balloon Snake is 95.53%.

[1]  Laurent D. Cohen,et al.  Finite-Element Methods for Active Contour Models and Balloons for 2-D and 3-D Images , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Laurent D. Cohen,et al.  On active contour models and balloons , 1991, CVGIP Image Underst..

[3]  Suresh Kumar Uppu.  A STUDY OF PARAMETRIC ACTIVE CONTOURS FOR THE APPLICATION OF MR AXIAL ABDOMINAL IMAGES , 2006 .

[4]  Jerry L. Prince,et al.  Gradient vector flow: a new external force for snakes , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  L. Tabár,et al.  Beyond randomized controlled trials , 2001, Cancer.

[6]  Jerry L Prince,et al.  Deformable models with application to human cerebral cortex reconstruction from magnetic resonance images , 1999 .

[7]  Raúl San José Estépar,et al.  Pull-push level sets: a new term to encode prior knowledge for the segmentation of teeth images , 2005, SPIE Medical Imaging.

[8]  Etta D Pisano,et al.  A comparative study of 2D and 3D ultrasonography for evaluation of solid breast masses. , 2005, European journal of radiology.

[9]  Akshay K. Singh,et al.  Deformable models in medical image analysis , 1996, Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis.

[10]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[11]  V. Caselles,et al.  A geometric model for active contours in image processing , 1993 .

[12]  John Porrill,et al.  Statistical Snakes: Active Region Models , 1994, BMVC.