journal of biomedical informatics
All submissions of the EM system will be redirected to Online Manuscript Submission System. Authors are requested to submit articles directly to Online Manuscript Submission System of respective journal.
 

A Rapid and Reproducible Report on the Morphological and Functional Characteristics of Spermatozoa Using Digital Image Processing Technique

Author(s): Joseph Pushpa Innocent D, Suseela M.R, Priya Lakshmi N, Jesuchristopher

Background and Objectives: Semen analysis plays a vital role in understanding the healthy state of the sperm in men. The computer aided semen quantification technique quantifies the quality of the sperm from the semen sample which is digitally sampled and processed using digital image processing technique.

Methods: The semen samples were collected from 402 infertile men aged between 25-50 years. Similarly 25 samples were collected from the age matched healthy fertile men (control group) as per the diagnostic report from the physician. A total of 427 samples used in this study were analyzed using traditional manual method (ground truth) and the proposed automated method based on the image processing algorithm.

Results: Conventional semen analysis procedure was performed manually after liquefaction of the samples. The parameters such as morphology, sperm count and motility types were determined and compared between manual and automated methods. We have achieved a significant repeatability and reproducibility of the results using the automated method. Automated method has demonstrated to be computationally efficient and it required less amount of time to process any given field of view. It is also less susceptible to any rater bias for the analyzed field of view and the results were comparable with the manual method.

Conclusions: In this article we describe the developmental stages involved in the semen analysis, custom built automated image analysis protocol and the report generation based on the parameters involving sperm count and motility types.


PDF
Register