Segmentation of Breast Ultrasound image using Regularized K-Means (ReKM) clustering

Breast cancer is a highly heterogeneous disease and very common among women worldwide. Inter-observer and intra-observer errors occur frequently in analyzing the lesion portion of medical images, giving high variability in results interpretations. Computer Aided Diagnosis system (CAD) plays a vital role to overcome this variability. Segmentation is the second critical stage in CAD system to extract the desired portion exactly for distinguishing benign tumor from malignant one. In this work, the traditional K-Means algorithm is incorporated with Ant Colony Optimization and Regularization parameter to segment the lesion portion with maximum boundary preservation. The PRI, VoI, GCE and BDE cluster validation measures are used to compare the segmented result with ground truth image delineated by the radiologist. The proposed work outperforms the traditional K-Means clustering method with 96% similarity (PRI) between segmented tumor image with referred tumor image.

[1]  R. Carlson,et al.  Breast Cancer in Limited‐Resource Countries: An Overview of the Breast Health Global Initiative 2005 Guidelines , 2006, The breast journal.

[2]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Krishnavir Singh,et al.  A Study Of Image Segmentation Algorithms For Different Types Of Images , 2012 .

[4]  E. Levina,et al.  Pairwise Variable Selection for High‐Dimensional Model‐Based Clustering , 2010, Biometrics.

[5]  Alessandro Verri,et al.  A Regularized Method for Selecting Nested Groups of Relevant Genes from Microarray Data , 2008, J. Comput. Biol..

[6]  Ali Ahsan,et al.  A New Approach to Image Segmentation for Brain Tumor detection using Pillar K-means Algorithm , 2013 .

[7]  Dar-Ren Chen,et al.  Breast cancer diagnosis using image retrieval for different ultrasonic systems , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[8]  Jean-Louis Deneubourg,et al.  The dynamics of collective sorting robot-like ants and ant-like robots , 1991 .

[9]  Geoffrey J. McLachlan,et al.  Regularised k-means clustering for dimension reduction applied to supervised classification , 2009, CIBB 2009.

[10]  P. Thirumoorthy,et al.  Combining Clustering, Morphology and Metaheuristic Optimization Technique for Segmentation of Breast Ultrasound Images to Detect Tumors , 2014 .

[11]  T. Tukeva,et al.  Comparison of breast structure and findings by X-ray mammography, ultrasound, cytology and histology: a retrospective study , 1995 .

[12]  Wei Sun,et al.  Regularized k-means clustering of high-dimensional data and its asymptotic consistency , 2012 .

[13]  S. V. KASMIR RAJA,et al.  REFINEMENT OF CLUSTERS FROM K-MEANS WITH ANT COLONY OPTIMIZATION , 2009 .

[14]  H. Zou.  The Adaptive Lasso and Its Oracle Properties , 2006 .

[15]  Shehroz S. Khan,et al.  Cluster center initialization algorithm for K-means clustering , 2004, Pattern Recognit. Lett..

[16]  E. S. Samundeeswari,et al.  M2 FILTER FOR SPECKLE NOISE SUPPRESSION IN BREAST ULTRASOUND IMAGES , 2015 .

[17]  M. Giger,et al.  Computerized lesion detection on breast ultrasound. , 2002, Medical physics.

[18]  Pg Scholar,et al.  BREAST TUMOR SEGMENTATION AND CLASSIFICATION USING SVM AND BAYESIAN FROM THERMOGRAM IMAGES , 2014 .