الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 155 |  |  |
| | | from | 155 | | |
Abstract
Breast cancer is one of the most common types of cancer in women worldwide and this is a disease can be most efficiently treated if detected at an early stage. Many studies proven that an early diagnosis of breast cancer can increase five year survival rate from 60% to 80+%.To enable early detection a regular checkup need to be done and mammography here is considered as a key diagnosing tool. But this is associated with frequent medical reviews especially for women above 40’s and nationwide screening campaigns especially in developing countries. Also for detecting tumors at early stages high resolution images are very essential to detect relatively small tumors and scanning data need to be stored for years to track the progress of each case. That made screening programs a mandatory step for females. As a result, this is more likely to lead to oversight errors because of an increase in the radiologist’s workload in image interpretation or not enough experience to detect cancer cells at early stages. This possibility can be reduced by using Computer-Aided-Diagnosis (CAD) systems.
Many image processing techniques developed over the past two decades to help radiologists in diagnosing breast cancer. CAD systems can be a powerful tool to overcome this problem by highlighting suspected lesions. However, this task is challenging also from CAD systems point of view due to difficulties in articulating and modeling patterns of abnormalities in a computational way as many pre¬processing steps need to be done to identify region of interest before pattern recognition algorithms can be applied. Another drawback of screening mammography is the large number of false positives that it generates. This is because mammography does not image cells, rather it is a 2D x-ray shadow cast by the compressed breast.
All of this leads to very large data storage needs which drives the need for more efficient lossless data compression tools to facilitate storage and exchange of images over wide area networks, especially in developing countries where WAN bandwidth is limited and relatively expensive. Lossless compression of mammograms will reduce storage capacity needed and at the same time will enable faster image transmission over W ANs, especially with limited bandwidth networks.