New performance metric for quantitative evaluation of enhancement in mammograms

The second leading cause of cancer related death in women is breast cancer, mostly diagnosed in the age group of 40-60. Breast cancer is the formation of lump in the breast, this the initial stage which is further followed by abnormal cell division and growth of malignant tumour. Mammography is the most powerful detector of breast cancer that can easily diagnose masses and micro-calcifications. Early detection of masses with minimal false detection is distant reality with mammographic images due to poor contrast (i.e. superimposition of salt tissues of the breast with the mass) and presence of noise. For this purpose different enhancement techniques are applied, but any single technique is not best for all images. In this paper, a performance metric is developed that is applied on each enhancement technique to quantitatively evaluate the degree of enhancement applied on a mammogram. This also evaluates that, which technique is best suited for any particular mammogram.

[1]  Vikrant Bhateja,et al.  An improved non-linear transformation function for enhancement of mammographic breast masses , 2011, 2011 3rd International Conference on Electronics Computer Technology.

[2]  S. Lai,et al.  On techniques for detecting circumscribed masses in mammograms. , 1989, IEEE transactions on medical imaging.

[3]  Sarbjeet Singh,et al.  Review: On Performance Metrics for Quantitative Evaluation of Contrast Enhancement in Mammograms , 2013 .

[4]  Berkman Sahiner,et al.  An adaptive density-weighted contrast enhancement filter for mammographic breast mass detection , 1996, IEEE Trans. Medical Imaging.

[5]  Sameer Singh,et al.  An evaluation of contrast enhancement techniques for mammographic breast masses , 2005, IEEE Transactions on Information Technology in Biomedicine.

[6]  Sos S. Agaian,et al.  Nonlinear Unsharp Masking for Mammogram Enhancement , 2011, IEEE Transactions on Information Technology in Biomedicine.

[7]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.