Automated labeling of neurites in fluorescence microscopy images

To investigate the intricate nervous processes involved in many biological activities by image analysis, accurate and reproducible labeling and measurement of neurites is a prerequisite. We have developed a fully automated neurite analysis method to assist this task. Unlike most of the previous reported manual or semiautomatic methods, our approach is fully automated. Single and connected centerlines along neurites are extracted. The computerized method can also output branching and end points. Due to its multi-scale nature, both thick and thin neurites are simultaneously detected. With the accurate and fully automated extraction of neurite centerlines and measurement of neurite lengths, the proposed method, which greatly reduces human labor and improves efficiency, can serve as a candidate tool for large-scale neurite analysis beyond the capability of manual tracing methods.