A Novel Hybrid Image Segmentation Method for Detection of Suspicious Regions in Mammograms Based on Adaptive Multi-Thresholding (HCOW)

Suspicious region segmentation is one of the most important parts CAD systems that are used for breast cancer detection in mammograms. In a system, there can be so many suspicious regions determined mammogram because complex structure breast. This study proposes hybrid thresholding method to use efficient mammograms and reducing number regions. The proposed provides fully-automatic based on determining an adaptive multi-threshold value by using three different techniques together. These Otsu multilevel thresholding, Havrda & Charvat entropy, w-BSAFCM algorithm was developed authors this paper image clustering applications. method, performed two sub-images obtained from mammogram, pectoral muscle prevent any information loss. tested 55 mass-mammograms 210 non-mass mini-MIAS database, it compared with Shannon, Renyi, Kapur entropy methods some related studies literature. results tests were evaluated terms regions, correctly detected masses, performance measure parameters, accuracy, false-positive rate, specificity, volumetric overlap, dice similarity coefficient. According evaluations, shown both successfully locate mass significantly reduce