Breast Cancer Segmentation Method in Ultrasound Images

The most common type of cancer among women is breast cancer. The early diagnosis is crucial in a treatment process. The radiology support system in the diagnostic process allows faster and more accurate radiographic contouring. The aim of the paper is to present a new method for ultrasound image segmentation of breast lesions. The segmentation technique is based on active contour models whereas anisotropic diffusion is used for preprocessing. The Dice Index calculated in most of analyzed cases was greater than 80%. Delineation of the tumor can also be used to calculate the size and volume automatically, and shortened the time of the diagnosis.

[1]  A. Stavros,et al.  Breast biopsy avoidance: the value of normal mammograms and normal sonograms in the setting of a palpable lump. , 2001, Radiology.

[2]  N.R.S. Parveen,et al.  Segmenting tumors in ultrasound images , 2008, 2008 International Conference on Computing, Communication and Networking.

[3]  S. Sasikala,et al.  Feature Extraction and Analysis of Breast Lesion in Ultrasound B Mode and Elastography , 2014 .

[4]  Woo Kyung Moon,et al.  Segmentation of breast tumor in three-dimensional ultrasound images using three-dimensional discrete active contour model. , 2003, Ultrasound in medicine & biology.

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

[6]  Heng-Da Cheng,et al.  Detection and classification of masses in breast ultrasound images , 2010, Digit. Signal Process..

[7]  Dar-Ren Chen,et al.  Watershed segmentation for breast tumor in 2-D sonography. , 2004, Ultrasound in medicine & biology.

[8]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Ruey-Feng Chang,et al.  Multi-Dimensional Tumor Detection in Automated Whole Breast Ultrasound Using Topographic Watershed , 2014, IEEE Transactions on Medical Imaging.

[10]  Scott T. Acton,et al.  Speckle reducing anisotropic diffusion , 2002, IEEE Trans. Image Process..

[11]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Anil F. Ramlackhansingh,et al.  Lesion identification using unified segmentation-normalisation models and fuzzy clustering , 2008, NeuroImage.

[13]  W. C. A. Pereira,et al.  Feature selection and classifier performance in computer-aided diagnosis for breast ultrasound , 2013, 2013 10th International Conference and Expo on Emerging Technologies for a Smarter World (CEWIT).

[14]  R. Hendrick,et al.  Imaging of the radiographically dense breast. , 1993, Radiology.

[15]  Jacques Ferlay,et al.  Global Burden of Breast Cancer , 2010 .