Abstract
Methods for automatic analysis of clinical data are usually targeted towards a specific modality and do not make use of all relevant data available. In the field of male human reproduction, clinical and biological data are not used to its fullest potential. Manual evaluation of a semen sample using a microscope is time-consuming and requires extensive training. Furthermore, the validity of manual semen analysis has been questioned due to limited reproducibility, and often high inter-personnel variation. The existing computer-aided sperm analyzer systems are not recommended for routine clinical use due to methodological challenges caused by the consistency of the semen sample. Thus, there is a need for an improved methodology. We use modern and classical machine learning techniques together with a dataset consisting of 85 videos of human semen samples and related participant data to automatically predict sperm motility. Used techniques include simple linear regression and more sophisticated methods using convolutional neural networks. Our results indicate that sperm motility prediction based on deep learning using sperm motility videos is rapid to perform and consistent. Adding participant data did not improve the algorithms performance. In conclusion, machine learning-based automatic analysis may become a valuable tool in male infertility investigation and research.
Highlights
Automatic analysis of clinical data may open new avenues in medicine, though often limited to one modality, usually images[1]
We aim to contribute to the field of automated semen analysis in the following three ways: (i) to develop a rapid and consistent method for analyzing sperm motility automatically, (ii) to explore the potential of multimodal analysis methods combining video data with participant data to improve the results of the automatic analysis, and (iii) to compare different methods for predicting sperm motility using algorithms based on deep learning and classical machine learning
Our results indicate that deep learning algorithms have the potential to predict sperm motility consistently and time efficiently
Summary
Automatic analysis of clinical data may open new avenues in medicine, though often limited to one modality, usually images[1]. Standard semen analysis should be performed according to the recommendations made by the WHO, which includes methods of assessing semen volume, sperm concentration, total sperm count, sperm motility, sperm morphology, and sperm vitality[11]. Concerning automatic semen analysis in general, Urbano et al.[16] present a fully automated multi-sperm tracking algorithm, which can track hundreds of individual spermatozoa simultaneously. Similar to CASA, object proposals are generated through a greyscale edge detection algorithm, which is tracked to generate object trajectories These trajectories are classified into “sperm” or “non-sperm” entities using a CNN, of which the “sperm” entities are used to estimate three quality measurements for motility (progressive, non-progressive, and immotile), and the concentration of spermatozoa per unit volume of semen. The results seem promising but since the method was evaluated on a closed dataset, it is not possible to directly compare this approach with other methods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
