Poisson inverse gradient approach to vascular myocyte detection and segmentation

This paper addresses the detection and segmentation of vascular myocytes. The detection and segmentation of these cells are critical to the investigation of atherosclerosis among other cardiovascular diseases. Our approach to detection is unique in that it attempts to compute the underlying external energy in an active contour model. Isolines in this computed external energy can be employed to localize boundaries of the cell nuclei. The process used to solve the inverse problem of obtaining the energy from the force vectors is called Poisson inverse gradient due to the Poisson-based solution. From the initial contours given by the isolines in the computed energy, parametric active contours are used to find the subtle cell boundaries. The results indicate that the Poisson inverse gradient improves detection accuracy and reduces false positives compared to existing morphological methods. Furthermore, the contour-based detection allows segmentation of the cell boundaries.