Review of Recent Advances in Segmentation of Lesion in the Breast DCE-MR images

Abstract

Breast tumor detection and segmentation in dynamic contrast enhanced magnetic resonance images (DCE-MRI) is important in medical diagnosis because it provides information related to the lesion or abnormal tissues necessary for diagnosis of the disease and treatment planning. The segmentation of breast tumors can also be helpful for general modelling of pathological breasts and the construction of pathological breast atlases. Despite numerous efforts and promising results in the medical imaging community, accurate segmentation for description of abnormalities are still a difficult and challenging task because of the diversity of shapes and image intensities of various types of tumors. Some of them may also deform the surrounding structures or may be associated to edema or necrosis that changes the image intensity around the tumor. Existing methods provides significant scope for increased automation, robustness, sensitivity and accuracy. In general there is a necessity to design robust and fast segmentation algorithms. However, there is no generic method for solving all segmentation problems. Instead, the segmentation algorithms developed are highly adapted to the application in order to achieve better performance. In this paper, the review of recent developments in segmentation methods for lesion detection in breast DCE-MR Images is presented.

Keywords: Breast DCE-MR images, Segmentation methods.