Spermatozoon Segmentation Towards an Objective Analysis of Human Sperm Morphology

摘要

Sperm morphology has a key role in the determination of fertility in men. Nowadays assessments of sperm morphology are mostly done based on subjective criteria. This article discusses details of the image processing algorithms implemented in a computer aided tool for the objective analysis of human sperm morphology, commonly known as Automated Sperm Morphology Analyzer (ASMA). The first stage described is the detection and extraction of individual spermatozoon of an image containing multiple spermatozoa and biological rests as well. A novel method for segmenting acrosome, nucleus and mid-piece of a spermatozoon is proposed. The method called nth-fusion introduced in this paper is the framework of the segmentation algorithm implemented in this computer aided tool, this algorithm has been tested with a 250 spermatozoon images database and the results are quite accurate.