An algorithm for Morphological classification of motile human sperm

Lore E.M. Van Raemdonck, Ata-ur-rehman, M. Luisa Davila-garcia, Lyudmila Mihaylova, Robert F. Harrison, Allan Pacey
2015 2015 Sensor Data Fusion: Trends, Solutions, Applications (SDF)  
The analysis of human sperm as part of infertility investigations or assisted conception treatments is a labor intensive process reliant upon the skill of the observer and as such prone to human error. Therefore, there is a need to develop automated systems that can adequately assess the concentration, motility and morphology of live sperm. This paper presents an algorithm for analyzing the morphology of motile sperm. Techniques for eliminating the background, segmentation of the cells and
more » ... ate matching techniques are used to analyze the morphology in two stages: first stage eliminates the immotile cells and at the second stage the morphology of the motile cells is analyzed. Results are presented with real sperm samples recorded in the andrology lab at the University of Sheffield. The performance of the proposed algorithm is analyzed in terms of accuracy and complexity. The proposed algorithm demonstrates high accuracy under variable conditions.
doi:10.1109/sdf.2015.7347714 dblp:conf/sdf/RaemdonckuGMHP15 fatcat:4reicrwsnzglnel3ypvjr7qqpi