Segmentation of sperm's Acrosome, nucleus and mid-piece in microscopic images of stained human semen smear

The measurement or evaluation and clinical significance of human sperm morphology has always been and still is a controversial aspect of the semen analysis for the determination of a male's fertility potential. The evaluation of sperm size, shape and morphological smear characteristics should be assesed by carefully observing a stained sperm sample under a microscope. In order to avoid subjectivity, numerous studies that incorporate image analysis techniques in the assessment of sperm morphology have been proposed. The primary step of all these methods is segmentation of sperm's parts. In this paper, we have proposed a new method for segmentation of sperm's Acrosome, Nucleus and Mid-piece. Sperm's Acrosome, Nucleus and Midpiece are segmented through a method based on a Bayesian classifier which utilizes the adaptive mixtures method (AMM) and Markov random field (MRF) model to obtain and upgrade the class conditional probability density function (CCPDF) and the apriori probability of each class. To compare the performance of the proposed approach with those of previous approaches including manual segmentation, the Accuracy, Sensitivity and Specificity were calculated.