Abstract:
Breast cancer is the most common cause of death among patients and one of the main reasons is the lesion is not identified in proper time to seek medical facility. The situation is Bangladesh is alarming as there is a huge female population in the rural areas who don’t have proper medical access to detect the early stage of breast cancer.
We have developed a Computer Aided Diagnosis (CAD) system that will detect the cancerous lesion in the BUS (breast ultrasound) image automatically. The algorithm can come up with a Region of Interest (ROI), which not only eliminates human intervention but also highly accurate. Entropy information along with a rule based approach called ‘rule of third’ is used to obtain the ROI. For edge detection the algorithm uses external energy filtering and thresholding
