Qualitative detection of breast cancer by morphological curvelet transform

Medical image segmentation is a very important issue in medical imaging. This paper presents an automatic image segmentation method for tumour detection. A Computer-Aided Diagnostic (CAD) system for the diagnosis of benign and malignant from Computed Tomography (CT) images is presented. Proposed paper describes the development of segmentation methodology in the processing of images obtained using curvelets and mathematical morphology. Curvelet transform is a multi scale transform that can represent the edges along curves much more efficiently. The reconstructed images illustrate improvement in identification of embedded malignant tumours over the delay-and sum algorithm. Successful detection and localization of tumours as small as 2.5 mm in diameter are also demonstrated.