Affiliations: [a] Department of Radio Physics and Electronics, University of Calcutta, Kolkata, India | [b] Indian Institute of Information Technology and Management, Gwalior, India
Corresponding author: Arpita Das, Department of Radio Physics and Electronics, University of Calcutta, Kolkata, India. E-mail: [email protected]
Abstract: Computer-aided diagnosis (CAD) of mammograms has received great attention because of its speed and consistency and could provide a promising solution. However, poor visibility of mammographic features addresses the necessity of accurate contrast enhancement technique. In the present study, we have examined the problem of fuzziness/impreciseness of mammograms such as inhomogeneous background, indistinct borders, ill-defined shapes, varying intensities of the suspicious region and low distinguishability from surroundings. Though fuzzy logic based contrast enhancement technique has good potential to handle the problem of impreciseness in mammograms, more generalized and flexible Vague Set approach is proposed here to capture the vagueness of mammograms. Performance of the proposed contrast enhancement technique is compared and evaluated with other two techniques using CAD based classification approach.
Keywords: Contrast enhancement, fuzzy logic, vague set approach, median membership function, CAD system