An Effective Algorithm for Detection of Region-of-Interest(ROI) in Digital Mammograms

摘要

Breast cancer is one of the most common cancers among women and the number of patients tends to increase rapidly during the past ten years in many countries. Since detecting the early symptoms of the breast cancer can be very important to enhance the possibility of cure, there have been active researches to develop computer-aided diagnosis(CAD) systems to detect symptoms of breast cancer. In this paper, we present a method that effectively detects microcalcifications in digital mammograms including a set of variable-size mean filters. Most algorithms in other researches consist of high complexity feature extractors such as wavelet filters and fractals. The algorithm presented in this paper rather simple with minimized features so that it can be implemented easily and responds with low latency time.