Comparison of thresholding methods for breast tumor cell segmentation

Abstract

Breast cancer was the most commonly occurring malignancy among women, so study of breast cancer are important. This paper is preprocessing of breast tumor research for segmentation method. There are many thresholding methods. Many thresholding methods developed but they have different result in each image. So we need automatic thresholding method because manual operating is tedious, time-consuming. This study compared result of 6 automatic thresholding method and 1 semi-supervised thresholding method in breast tumor image. Otsu's method and Iterative selection are good result in breast tumor cell images. So we expected results using Otsu's method and Iterative Selection to help for determining and diagnosing the breast tumor.