A Sperm Cell Tracking Recognition and Classification Method

Computer-aided sperm analysis (CASA) can detect male infertility by classifying and counting sperm motility. However, a commonly used threshold segmentation method is prone to loss of sperm target when sperm and impurities collide, resulting in detection errors. In this regard, we propose a method based on the Gaussian mixture model for sperm cell tracking recognition and classification. Through background modeling, the motile sperm can be sensitively tracked, which can effectively avoid the loss of sperm target caused by a collision of sperm and impurities. Experimental results show that the accuracy of the algorithm for forward progressive motility sperm identification, sensitivity and specificity is 96%, 98%, and 95%, respectively. The accuracy of non-progressive motility sperm recognition, sensitivity, and specificity is 90%, 98%, and 92%, respectively. The accuracy of immotility sperm recognition, sensitivity, and specificity is 90%, 80%, and 87%, respectively.