PGVF-ACM automatic segmentation of PET images for breast cancer characterization

Medical imaging research became an important field of investigation that could be very useful for clinical exploration, particularly for serious pathological cases such as cancer. In this proposed clinical aided tool, we were interested at the moment in analysis and exploration for standard segmentation of Positron Emission Tomography (PET) images for the breast cancer characterization. This research was hence established between technological team and clinical team in order to design a convivial platform, flexible and directly usable by clinicians for tumor tissue diagnosis and exploration. Particular attention will be given to breast cancer that threatens an important number of patients in the world. Such serious pathology could be carefully imaged by PET technology. The work was based on two proposed and combined approaches for the automatic segmentation of PET images: Poisson Gradient Vector Flow Active Contour Model <; PGVF-ACM > with and without implanting one dedicated Genetic Algorithm. Our objective in this research was mainly to compare these two approaches for this proposed application that could be very useful for clinical exploration. Experimental results for our PGVFACM automatic segmentation for several PET images were significant and demonstrate the effectiveness of the Genetic Algorithm that was applied to optimize automatically both threshold and sigma parameters.