Correction of intensity nonuniformity in breast MR images

Abstract

Breast cancer is one of the most prevalent cancers among women. Mammography, as one of the primary studies, is used for diagnosis of breast disease. In addition, MR images can depict most of the significant changes of breast during the time. For the first step of breast disease detection, the density measurement of the breast on MR images may provide very useful information. MR images have some instinctive limitations like the strongly dependence of contrast upon the way the image is acquired, noise, partial volumes, intensity inhomogeneities (bias field), etc. For these reasons, an effective normalization on breast MR images is very important issue for detecting breast disease signs. The first important step for quantitative analysis of breast density on MRI is preprocessing step including noise reduction and bias field correction. In this study, N3 algorithm is used for correcting the field inhomogeneity in MR images. We used T1-weighted images, using a 1.5-T MRI scanner. The results demonstrate effectiveness and efficiency of the proposed method.