Effects of Enhancement Methods on Diagnostic Quality of Digital Mammogram Images

Mostafa  Langarizadeh; R  Mahmud; AR Ramli; S  Napis; MR  Beikzadeh; WEZ Wan Abdul Rahman

International Journal of Cancer Management

The Official Journal of Cancer Research Center (CRC), Shahid Beheshti University of Medical Sciences

Outlines

Abstract
Copyright

Effects of Enhancement Methods on Diagnostic Quality of Digital Mammogram Images

Author(s):

Mostafa Langarizadeh^1,*,

R Mahmud¹,

AR Ramli²,

S Napis³,

MR Beikzadeh⁴,

WEZ Wan Abdul Rahman⁵

1Faculty of Medicine and Health Science, University Putra Malaysia, Malaysia

2Faculty of Engineering, University Putra Malaysia, Malaysia

3Information and Communication Development Center, University Putra Malaysia, Malaysia

4Malaysian Institute of Microelectronic Systems, Malaysia

5Faculty of Mathematics and Quantitative Research, University Technology Mara, Malaysia

International Journal of Cancer Management:Vol. 3, issue 1; e80655

Published online:Mar 31, 2010

Article type:Research Article

Received:Oct 23, 2009

Accepted:Dec 30, 2009

How to Cite:Mostafa LangarizadehR MahmudAR RamliS NapisMR BeikzadehWEZ Wan Abdul Rahmanet al.Effects of Enhancement Methods on Diagnostic Quality of Digital Mammogram Images.Int J Cancer Manag.3(1):e80655.

Abstract

Background: Breast cancer is one of the most important diseases in females. Malaysian women have not excluded. According to the Malaysian Oncology Society [1], about 4% of women (who are 40 years old and above) have involved by breast cancer. Masses and microcalcifications are two important signs for breast cancer diagnosis on mammography. According to our estimation, radiologists could diagnose breast cancer on mammogram screening program, with approximately 75% accuracy. About 25% of breast cancers have missed on mammograms. This study aimed to explore the effects of enhancement methods on digital mammograms.

Methods: SPSS software have used for data analysis. Wilcox on ranked test and ROC have used to compare the original and manipulated images. In this study, 60 digital mammogram images which include 20 normal and 40 confirmed diagnosed cases of breast cancer (masses), have selected and manipulated by using histogram equation, histogram stretching and median filter.

Results: The results have shown that the histogram stretching and median filter methods could improve image quality for detection of masses with increased sensitivity and specificity by 5%.

Conclusion: The sensitivity and specificity have improved by using histogram stretching and median filter. The results of this study have shown results as below ; the histogram equation have improved the sensitivity up to 97.5% ,while the median filter could improve sensitivity (97.5%) and specificity (85.5%). It means that the median filter could be more effective than the other enhancement methods

Keywords

Fulltext

Full text is available in PDF.

comments