Sperm Identification Using Elliptic Model and Tail Detection

The conventional assessment of human semen is a highly subjective assessment, with considerable intra- and interlaboratory variability. Computer-Assisted Sperm Analysis (CASA) systems provide a rapid and automated assessment of the sperm characteristics, together with improved standardization and quality control. However, the outcome of CASA systems is sensitive to the method of experimentation. While conventional CASA systems use digital microscopes with phase-contrast accessories, producing higher contrast images, we have used raw semen samples (no staining materials) and a regular light microscope, with a digital camera directly attached to its eyepiece, to insure cost benefits and simple assembling of the system. However, since the accurate finding of sperms in the semen image is the first step in the examination and analysis of the semen, any error in this step can affect the outcome of the analysis. This article introduces and explains an algorithm for finding sperms in low contrast images: First, an image enhancement algorithm is applied to remove extra particles from the image. Then, the foreground particles (including sperms and round cells) are segmented form the background. Finally, based on certain features and criteria, sperms are separated from other cells.

Authors:

• Vahid Reza Nafisi
• Mohammad Hasan Moradi
• Mohammad Hosain Nasr-Esfahani

Keywords:

• Computer-Assisted Sperm Analysis (CASA)
• Sperm identification
• Tail detection
• Elliptic shape model.

References:

[1] Domar AD, Broome A, Zuttermeister PC, Seibel M, Friedman R (1992),
The prevalence and predictability of depression in infertile women,
Fertil. & Steril, 58, 1158-1163.
[2] Acosta AA, Kruger TF (1996), Human spermatozoa in assisted
reproduction, 2nd edition, The Partheon Publishing Group, Chapter 6,
53-71.
[3] WHO (1999), Laboratory Manual for the Examination of Human Semen
and Sperm-Cervical Mucus Interaction, The press Syndicate of the
University of Cambridge, Cambridge, United Kingdom.
[4] ESHRE Andrology Special Interest Group (1998), Guidelines on the
Application of CASA Technology in the Analysis of Spermatozoa,
Human Reproduction, Vol. 13, No. 1, pp. 142-145.
[5] Wijchman JG, de Wolf BT, Jager S (1995), Evaluation of a computeraided
semen analysis system with sperm tail detection, Human
Reproduction, 10, 2090-2095.
[6] Zinaman MJ, et al (1996), Evaluation of computer-assisted semen
analysis (CASA) with IDENT stain to determine sperm concentration,
Journal of Andrology, 17, 288-292.
[7] Nafisi VR, Moradi MH, Nasr-esfahani MH (2005), A Template
Matching Algorithm for Sperm Tracking and Classification, accepted in
Physiological Measurement.
[8] Pitas I. (2000), Digital image processing algorithms and applications,
published by John Wiley & Sons, New York, USA, chapter 7, 361-372.
[9] Teifoory N, Moradi MH, Nafisi VR (2002), A new method for sperm
segmentation in microscopic image, proceeding of 11th Iranian
biomedical engineering conference, Amirkabir University of
Technology, Tehran, Iran.