Published Paper Details:

Ultrasound has been one of the most powerful techniques for imaging organs and soft tissue structure in the human body. It has been used for breast cancer detection because of its non-invasive, sensitive to dense breast, low positive rate and cheap cost. But due to the nature of ultrasound image, the image suffers from poor quality caused by speckle noise, low contrast and blurred edges. These make the automatic segmentation and classification of interested lesion difficult. One of the frequently used segmentation method is region growing method. A seed point is the starting point for region growing and its selection is very important for the segmentation and classification result. If this seed point is selected outside the region of interest, final segmentation and classification would be definitely incorrect. So, mostly the seed point is manually selected in order to avoid incorrect segmentation and classification. And also, most of the past works have concentrated only on automatic seed point location and segmentation of single lesion in U.S breast images. Proposing a method which was able to locate the seed point automatically within the multiple lesion regions by using the tan function, textural features of the lesion regions and Support Vector Machine and also able to automatically segment the lesion regions properly. Using this proposed method, able to located seed point within multiple lesion regions automatically. The results show that the proposed method was able to automatically locate the seed points within lesion region automatically for 98.42 % of images in our data set.