Comparison of automatic seed generation methods for breast tumor detection using region growing technique

Abstract

Seeded Region Growing algorithm is observed to be successfully implemented as a segmentation technique of medical images. This algorithm starts by selecting a seed point and, growing seed area through the exploitation of the fact that pixels which are close to each other have similar features. To improve the accuracy and effectiveness of region growing segmentation, some works tend to automate seed selection step. In this paper, we present a comparative study of two automatic seed selection methods for breast tumor detection using seeded region growing segmentation. The first method is based on thresholding technique and the second method is based on features similarity. Each method is applied on two modalities of breast digital images. Our results show that seed selection method based on thresholding technique is better than seed selection method based on features similarity.