Segmentation of cell nuclei in 3D microscopy images based on level set deformable models and convex minimization

Abstract

Accurate and efficient segmentation of cell nuclei in 3D fluorescence microscopy images is important for the quantification of cellular processes. We propose a new 3D segmentation approach for cell nuclei which is based on level set deformable models and convex minimization. Our approach employs different convex energy functionals, uses an efficient numeric method for minimization, and integrates a scheme for cell splitting. Compared to previous level set approaches for 3D cell microscopy images, our approach determines global solutions. The performance of our approach has been evaluated using in vivo 3D fluorescence microscopy images. We have also performed a quantitative comparison with previous 3D segmentation approaches.