Multiresolution analysis for computer-aided mass detection in mammogram using pixel based segmentation method

Abstract

Mammography is an X-ray imaging technique for diagnosing breast tumour. Segmentation of tumour in the mammogram images are difficult task because they are poor in contrast and the lesions are surrounded by tissue with similar characteristics. In this paper, an automatic detection algorithm is proposed to segment the suspicious masses or lesions. Mammogram images are analyzed by wavelet and the algorithm utilizes combination of region based segmentation and pixel based segmentation to detect the masses. The performance of the system is then evaluated using a dataset containing 60 images. From the experimental results the relative error calculated for each image is less than 15% and exhibits a sensitivity of 90%.