Automatic breast DCE-MRI segmentation using compound morphological operations

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is an evolving tool for determining breast diseases. Assisted with computer-aided methods (CAD), DCE-MRI demonstrates its efficiency on breast cancer diagnosis. A crucial step for automatic DCE-MRI analysis is to separate breast regions from the noise-corrupted background on DCE-MRI images. In this paper, we presented an automatic algorithm for breast segmentation of sagittal DCE-MRI sequences. To separate the background, the images were converted into binary images. Multiple morphological operations were then applied to remove the undesired noise and artifacts. To separate the breast regions from the chests, a chest contour mask was generated based on the overlap of the whole sequences. The mask was applied on each frame to exclude the chest region. The method was validated against manual segmentation and evaluated with different performance indexes. Our results demonstrate a high accuracy of the method compared with the manual segmentations.