International Journal of Computer Applications (0975 – 8887) International Conference on Information and Communication Technologies (ICICT- 2014) 18 Review of Mammogram Enhancement Techniques for Detecting Breast Cancer Inam ul Islam Wani Department of ISE, DSCE Bangalore, Karnataka, 560078 M. C Hanumantharaju Department of ECE, BMSIT Bangalore, Karnataka, 560078 M. T Gopalakrishna Department of ISE, DSCE Bangalore, Karnataka, 560078 ABSTRACT Breast cancer is ranked second among the leading causes of death affecting females. Statistics have shown that one out of eight (12 %) women are affected by breast cancer in their lifetime. Mammography is the most effective strategy for breast cancer screening and can be used for the early detection of masses or abnormalities. Small clusters of micro calcifications appearing as a collection of white spots on mammograms show an early sign of breast cancer. In digital mammography, electronic image of the breast is taken and is stored directly in a computer. However, early detection of breast cancer is dependent on both the radiologist’s ability to read mammograms and the quality of mammogram images. The aim of this paper is to conduct a review of existing mammogram enhancement techniques. Each method will be discussed in brief and compared against other approaches. Keywords Mammogram Enhancement, Image Calcification, Breast Mass Detection, Segmentation, Microcalcification Detection, Morphology, Wavelet Transform. 1. INTRODUCTION Breast cancer is the second leading cause of cancer affecting females in women, exceeded only by lung cancer. Earlier detection and diagnosis of breast cancer increases the chances for successful treatment and complete recovery of the patient. There are several ways in which breast cancer is diagnosed, including Breast Self-Examination (BSE), Clinical Breast Examination (CBE), imaging or mammography, and surgery. Mammography is the most effective technique for breast cancer screening and earlier identification of masses or abnormalities; it can detect 85% to 90% of all breast cancers. To diagnose breast cancer we need to find abnormalities like masses and calcifications that indicate breast cancer. Because of the small size of microcalcification, visualization is lacking in mammograms. Therefore, to improve visibility of the abnormalities to detect breast cancer in mammograms to assist analysts as well as automatic breast cancer detection systems, mammogram contrast needs to be enhanced. Removal of noise is essential for enhancement of contrast of an image, specifically for mammograms the microcalcification size is close to noises. Noise should be reduced whereas microcalcification need to be enhanced. One more reason for enhancement is that mammograms that show abnormalities, such as masses, Microcalcification and their surrounding tissues may be possessing low contrast. Mammogram image enhancement is the process of manipulating mammogram images to increase their contrast and reduce the noise present to facilitate radiologists in the detection of abnormalities. The methods used to manipulate mammogram images are divided into four main categories; the conventional enhancement techniques, the region-based enhancement techniques, the feature-based enhancement techniques, and the fuzzy enhancement techniques as shown in Figure 1. Fig. 1. Mammogram Image Enhancement Techniques The conventional enhancement techniques are generally used to improve masses in mammogram images, as An example, histogram equalization can be used to enhance the mammogram images before segmentation and mass detection. However, Schiabel et al. [1] used the histogram equalization technique accompanied with other techniques and as a part of a pre-processing step for mammogram enhancement. Region-based enhancement techniques are similar to the conventional enhancement methods that are typically used for the enhancement of masses. Sampat and Bovik [2] proposed a filtering algorithm that enhances speculations (linear features of masses) in mammograms as a part of a speculated mass detection technique of image to obtain the enhanced image. Feature-based enhancement methods can be used to enhance both masses and micro-calcifications. Dabour [3] introduced an algorithm based on wavelet analysis and mathematical morphology for digital mammograms enhancement. The authors tested this algorithm on several mammograms from the MIAS database. Fuzzy enhancement methods are used to enhance masses and micro-calcifications. Mohanalin et al., [4] presented fuzzy algorithm based on Normalized Tsallis entropy to enhance the contrast of micro-classifications in mammograms. Jiang et al., [5] enhances micro-calcifications in digital mammograms by using the combined approach of fuzzy logic and structure tensors. This survey addresses these issues. Among different mammogram enhancement algorithms, traditional methods such as histogram equalization, CLAHE increases the contrast of mammogram but at the same time they enhance noise in mammogram. In this paper, section 2 presents some of the enhancement techniques and section III presents the conclusion of survey.