Smartphone based sperm counting-an alternative way to the visual assessment technique in sperm concentration analysis


MULTIMEDIA TOOLS AND APPLICATIONS, vol.79, pp.6409-6435, 2020 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 79
  • Publication Date: 2020
  • Doi Number: 10.1007/s11042-019-08421-3
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, FRANCIS, ABI/INFORM, Applied Science & Technology Source, Compendex, Computer & Applied Sciences, INSPEC, zbMATH
  • Page Numbers: pp.6409-6435
  • Keywords: Computerized sperm counting, Smartphone aided diagnosis systems, Sperm concentration analysis, Computer aided semen analysis, Biomedical image processing, AUTOMATIC DETECTION, ACROSOME INTEGRITY, SEMEN, SYSTEM, IMAGES, MOTILITY, SEGMENTATION, FRAMEWORK, CHAMBERS, CONTOURS
  • Yıldız Technical University Affiliated: Yes


Sperm Counting is the first phase of the infertility diagnosis. Computer Aided Sperm Analysis (CASA) and Visual Assessment (VA) are two evaluation techniques employed in analyses. VA is carried out by observing sperm on counting chambers. Therefore, diagnosis strongly depends on the skills and experiences. CASA isolates the human factor by utilizing the computer based techniques. However, it is more costly than VA and requires exhausted parameter settings. In this study, we present a novel approach that uses smartphone and computer for sperm counting analysis. Smartphone is used to obtain images similar to VA technique. Then, sample videos are transferred to the computer side where we developed the Computerized Sperm Counting Software (CSCS) to count the sperm using counting chambers and eliminate human effects. CSCS consists of four modules: (1) Data Acquisition and Organization, (2) Regions of Interest (ROI) detection, (3) Motile/Immotile Sperm Detection, (4) Counting. Smartphone based data acquisition provided less costly design contrary to CASA systems. ROI extraction was realized by a combinational approach of line detection and segmentation methods. Background and Foreground extractions were employed in immotile and motile sperm detection process, respectively. Additionally, active contour was implemented to enhance the segmentation of immotile sperm. As the final step, detected sperms were counted by pixel based blob analysis. According to experimental results, the proposed smartphone based sperm concentration analysis can be adapted in laboratories due to its modularity, functionality, accuracy and cost when compare to CASA and VA based sperm counting analysis.