Red blood cell segmentation using guided contour tracing

Abstract

We present a model-based contour tracing approach to the problem of automatically segmenting a Scanning Electron Microscope image of red blood cells. These images characteristically have high numbers of overlapping cells and relatively smooth contours. We provide a brief look into what problems conventional algorithms encounter when attempting to segment these images, and go on to show that a model-based contour tracing approach attains high levels of accuracy and almost no false negatives.