I.J.Modern Education and Computer Science, 2012, 3, 57-65 Published Online April 2012 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijmecs.2012.03.08 Copyright © 2012 MECS I.J. Modern Education and Computer Science, 2012, 3, 57-65 Detection of Tumours in Digital Mammograms Using Wavelet Based Adaptive Windowing Method G.Bharatha Sreeja PG Communication Systems, Cape Institute of Technology, Levengipuram, India Email: bharathasreeja@yahoo.com Dr. P. Rathika Professor, ECE Dept., Cape Institute of Technology, Levengipuram, India Email: rathikasakthikumar@yahoo.co.in Dr. D. Devaraj DEAN, R&D, Kalasalingam University, Krishnankoil, India Email: deva230@yahoo.com Abstract—Mammography is the most effective procedure for the early detection of breast diseases. Mammogram analysis refers the processing of mammograms with the goal of finding abnormality presented in the mammogram. In this paper, the tumour can be detected by using wavelet based adaptive windowing technique. Coarse segmentation is the first step which can be done by using wavelet based histogram thresholding where, the thereshold value is chosen by performing 1-D wavelet based analysis of PDFs of wavelet transformed images at different channels. Fine segmentation can be done by partitioning the image into fixed number of large and small windows. By calculating the mean, maximum and minimum pixel values for the windows a threshold value has been obtained. Depending upon the threshold values the suspicious areas have been segmented. Intensity adjustment is applied as a preprocessing step to improve the quality of an image before applying the proposed technique. The algorithm is validated with mammograms in Mammographic Image Analysis Society Mini Mammographic database which shows that the proposed technique is capable of detecting lesions of very different sizes. Index Terms— wavelet based Thresholding, breast cancer, mammography, window based Thresholding, segmentation. I. INTRODUCTION Currently, breast cancer is a leading cause of death among women and second major cause of death after lung cancer [1]-[5]. Breast cancer is the second most common cancer in Indian women. The incidence is more in urban than rural women. It is more prevalent in the higher socio-economic groups. The average incidence rate varies from 22-28 per 1,00,000 women per year in urban settings to 6 per 100,000 women per year in rural areas. Due to rapid urbanization and westernization of lifestyles, there is a rising incidence of breast cancer in India. According to The International Agency for Research on Cancer, which is part of the World Health Organization, there were approximately 79,000 women per year affected by breast cancer in India. It is thought that it takes about 10 years for a tumour to become 1 cm in size starting from a single cell. Earlier diagnoses of breast cancer are of great importance in modern medicine. At present, mammography is the method of choice for early breast cancer detection [6]-[8]. Although automatic analysis of mammograms cannot fully replace radiologists, an accurate computer-aided analysis method can help radiologists to make more reliable and efficient decisions [9]. Tumors and other abnormalities present in the mammograms are of basic interests that need to be segmented and extracted in mammograms [10]-[11]. Some of the grayscale based segmentation methods are quite effective to extract the exact edges of homogeneous grayscale regions. They are often not so effective to extract the desired affected areas in mammograms with complex structure because of the complex distribution of the grayscale. However, the appearances of breast cancers are very subtle and unstable in their early stages. Therefore, doctors and radiologists can miss the abnormality easily if they only diagnose by experience. The computer aided detection technology can help doctors and radiologists in getting a more reliable and effective diagnosis. There are numerous tumour detection techniques have