An Iterative Mammographic Image Thresholding Algorithm For Breast Cancer Detection

Breast cancer is the most prevalent cancer among women and affects approximately one million women worldwide. If breast cancer is found at an early stage, this improves the chances of recovery. Mammograms are a good way of identifying abnormalities in the breast in its early stages. Several image processingalgorithms have been developed to assist physicians in detecting tumors in mammographic images.The segmentation of these images performs as an important antecedent step for advanced medical application, such as computer-aided diagnosis (CAD). Brink and Pendock (1996) proposed a sequential method to improve version of Li and Lee (1993) to find optimal threshold using minimum cross entropy thresholding technique (MCET) based on Gaussian distribution. In this paper, we improve the previous works by developing a fast iterative algorithm for MCET. Our proposed method is applied on mammographic images and results obtained are encouraging. Keywords-Breast cancer, Mammograms, CAD, Minimum Cross Entropy Thresholding, Gaussian Distribution, Iterative algorithm.

[1]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Chun-hung Li,et al.  Minimum cross entropy thresholding , 1993, Pattern Recognit..

[3]  T. Akai.  Applied numerical methods for engineers , 1994 .

[4]  A. D. Brink,et al.  Minimum cross-entropy threshold selection , 1996, Pattern Recognit..

[5]  C. H. Li,et al.  An iterative algorithm for minimum cross entropy thresholding , 1998, Pattern Recognit. Lett..

[6]  Mohammad Sameti,et al.  Detection of soft tissue abnormalities in mammographic images for early diagnosis of breast cancer , 1998 .

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

[8]  Shengrui Wang,et al.  Segmentation of SAR images , 2002, Pattern Recognit..

[9]  Bülent Sankur,et al.  Survey over image thresholding techniques and quantitative performance evaluation , 2004, J. Electronic Imaging.

[10]  Per Christian Henden.  Exercise in Computer Vision A Comparison of Thresholding Methods – NTNU – , 2004 .

[11]  Wen Gao,et al.  Thresholding technique with adaptive window selection for uneven lighting image , 2005, Pattern Recognit. Lett..

[12]  P. D. Thouin,et al.  Survey and comparative analysis of entropy and relative entropy thresholding techniques , 2006 .

[13]  Ali El-Zaart,et al.  Thresholding of Medical Images Using Minimum Cross Entropy , 2007 .

[14]  Liang Chen,et al.  Multi-Level Image Thresholding Based on Histogram Voting , 2009, 2009 2nd International Congress on Image and Signal Processing.

[15]  Liana Stanescu,et al.  Comparison of Two Image Segmentation Algorithms , 2010, 2010 Second International Conferences on Advances in Multimedia.

[16]  Ming-Huwi Horng,et al.  Multilevel minimum cross entropy threshold selection based on the firefly algorithm , 2011, Expert Syst. Appl..

[17]  Ahmed Bouridane,et al.  Minimum Cross Entropy Thresholding Using Entropy-Li Based on Log-normal Distribution for Skin Cancer Images , 2011, 2011 Seventh International Conference on Signal Image Technology & Internet-Based Systems.

[18]  H. Mathkour,et al.  Segmentation of Fibro-Glandular Discs in Digital Mammograms Using Log-Normal Distribution , 2013 .

[19]  Mohamed Heshmat,et al.  Minimum Cross Entropy Thresholding , 2014 .

[20]  Reem Alattas.  Multi-Level Minimum Cross Entropy Thresholding Using Gamma Distribution , 2014 .