A Model-based Algorithm for Mass Segmentation in Mammograms

A novel mass segmentation algorithm is proposed in this paper. It establishes two mass models to represent the various masses, uses iterative thresholding to extract the suspicious area, and applies a DWT-based approach to locate the masses. And then, a region growing process restricted by Canny edge detection is carried out to extract the rough mass regions, and finally active contour model is used to segment the masses accurately. The clinical experiment has demonstrated that our algorithm has higher performance than conventional methods

[1]  Milan Sonka,et al.  Image pre-processing , 1993 .

[2]  Rangaraj M. Rangayyan,et al.  Classification of tumors and masses in mammograms using neural networks with shape and texture features , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[3]  Martin P. DeSimio,et al.  Computer-aided breast cancer detection and diagnosis of masses using difference of Gaussians and derivative-based feature saliency , 1997, IEEE Transactions on Medical Imaging.

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

[5]  A. Chan,et al.  An artificial intelligent algorithm for tumor detection in screening mammogram , 2001, IEEE Transactions on Medical Imaging.

[6]  XU Wei-dong.  Study on model-based pectoral-muscle segment algorithmin mammograms , 2005 .

[7]  Charles K. Chui,et al.  An Introduction to Wavelets , 1992 .

[8]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.