@article { author = {Hazarika, Manasi and Mahanta, Lipi B}, title = {A New Breast Border Extraction and Contrast Enhancement Technique with Digital Mammogram Images for Improved Detection of Breast Cancer}, journal = {Asian Pacific Journal of Cancer Prevention}, volume = {19}, number = {8}, pages = {2141-2148}, year = {2018}, publisher = {West Asia Organization for Cancer Prevention (WAOCP), APOCP's West Asia Chapter.}, issn = {1513-7368}, eissn = {2476-762X}, doi = {10.22034/APJCP.2018.19.8.2141}, abstract = {Purpose: Breast cancer can be cured if diagnosed early, with digital mammography which is one of the mosteffective imaging modalities for early detection. However mammogram images often come with low contrast, highbackground noises and artifacts, making diagnosis difficult. The purpose of this research is to preprocess mammogramimages to improve results with a computer aided diagnosis system. The focus is on three preprocessing methods: a breastborder segmentation method; a contrast enhancement method; and a pectoral muscle removal method. Methods: Theproposed breast border extraction method employs a threshold based segmentation technique along with a combinationof morphological operations. The contrast enhancement method presented here is divided into two phages. In phaseI, a bi-level histogram modification technique is applied to enhance the image globally and in phase II a non-linearfilter based on local mean and local standard deviation for each pixel is applied to the histogram modified image. Thepectoral muscle removal method discussed here is implemented by applying a region growing algorithm. Results:The proposed techniques are tested with the Mini MIAS dataset. The breast border extraction method is applied to322 images and achieved 98.7% segmentation accuracy. The contrast enhancement method is evaluated based onquantitative measures like measure of enhancement, absolute mean brightness error, combined enhancement measureand discrete entropy. The proposed contrast enhancement method when applied to 14 images with different types ofmasses, the quantitative measures showed an optimum level of contrast enhancement compared to other enhancementmethods with preservation of local detail. Removal of the pectoral muscle from MLO mammogram images reducedthe search region while identifying abnormalities like masses and calcification. Conclusions: The preprocessing stepsproposed here show promising results in terms of both qualitative and quantitative analysis.}, keywords = {mammogram image,Histogram Equalization,Contrast Enhancement,breast border,pectoral muscle}, url = {https://journal.waocp.org/article_66158.html}, eprint = {https://journal.waocp.org/article_66158_a2fde9e95f583b188f59c17db3fbf87e.pdf} }