Publication Type:Journal Article
Source:Journal of biomedical optics, Volume 11, Issue 5, p.054009 (2006)
Keywords:Algorithms, Artificial Intelligence, Cells, Cultured, Humans, Image Enhancement, Image Interpretation, Computer-Assisted, Imaging, Three-Dimensional, Male, Microscopy, Video, Pattern Recognition, Automated, Reproducibility of Results, Sensitivity and Specificity, Sperm Motility, Spermatozoa
This paper describes a robust single sperm tracking algorithm (SSTA) that can be used in laser optical trapping and sperm motility studies. The algorithm creates a region of interest (ROI) centered about a sperm selected by the user. SSTA contrast enhances the ROI image and implements a modified four-class thresholding method to extract the tracked sperm as it transitions in and out of focus. The nearest neighbor method is complemented with a speed-check feature to aid tracking in the presence of additional sperm or other particles. SSTA has a collision-detection feature for real or perceived collision or near-miss cases between two sperm. Subsequent postcollision analysis employs three criteria to distinguish the tracked sperm in the image. The efficacy of SSTA is validated through examples and comparisons to commercially available computer-aided sperm tracking systems.