Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Dec 24;21(1):72.
doi: 10.3390/s21010072.

Deep Learning Based Evaluation of Spermatozoid Motility for Artificial Insemination

Viktorija Valiuškaitė  1 , Vidas Raudonis  1 , Rytis Maskeliūnas  2 , Robertas Damaševičius  3   4 , Tomas Krilavičius  3
Affiliations

Deep Learning Based Evaluation of Spermatozoid Motility for Artificial Insemination

Viktorija Valiuškaitė et al. Sensors (Basel). .

Abstract

We propose a deep learning method based on the Region Based Convolutional Neural Networks (R-CNN) architecture for the evaluation of sperm head motility in human semen videos. The neural network performs the segmentation of sperm heads, while the proposed central coordinate tracking algorithm allows us to calculate the movement speed of sperm heads. We have achieved 91.77% (95% CI, 91.11-92.43%) accuracy of sperm head detection on the VISEM (A Multimodal Video Dataset of Human Spermatozoa) sperm sample video dataset. The mean absolute error (MAE) of sperm head vitality prediction was 2.92 (95% CI, 2.46-3.37), while the Pearson correlation between actual and predicted sperm head vitality was 0.969. The results of the experiments presented below will show the applicability of the proposed method to be used in automated artificial insemination workflow.

Keywords: convolutional neural network (CNN); deep learning; sperm head detection; sperm quality.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Visual illustration of good and poor motility of a sperm head.
Figure 2
Figure 2
Still image from the sperm sample video.
Figure 3
Figure 3
Spermatozoid annotation using LabelImg application.
Figure 4
Figure 4
Faster Region Based Convolutional Neural Networks (R-CNN) network architecture.
Figure 5
Figure 5
Principle of operation of the Inception model.
Figure 6
Figure 6
Proposed spermatozoid tracking algorithm.
Figure 7
Figure 7
Basic scheme of frame processing: (a) sperm sample image, (b) segmented images of spermatozoa, (c) coordinates of bounding boxes of spermatozoa.
Figure 8
Figure 8
Illustration of the search for the least distant point in the neighborhood of a sperm head.
Figure 9
Figure 9
Results of applying different learning speeds: (a) learning_rate = 0.00002, (b) learning_rate = 0.0002, (c) learning_rate = 0.002.
Figure 10
Figure 10
Neural network loss during training.
Figure 11
Figure 11
Correlation study of predicted sperm vitality vs. actual sperm vitality. The regression line is plotted (R2 = 0.94).
Figure 12
Figure 12
Difference between motile and non-motile sperm heads as determined by the proposed algorithm.
Figure 13
Figure 13
The histogram of mean absolute error (MAE) value distribution.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Agarwal A., Mulgund A., Hamada A., Chyatte M.R. A unique view on male infertility around the globe. Reprod. Biol. Endocrinol. 2015;13:37. doi: 10.1186/s12958-015-0032-1. - DOI - PMC - PubMed
    1. Nachtigall R.D., Faure N., Glass R.H. Artificial insemination of husband’s sperm. Fertil. Steril. 1979;32:141–147. doi: 10.1016/s0015-0282(16)44169-5. - DOI - PubMed
    1. Kumar N., Singh A.K. Trends of male factor infertility, an important cause of infertility: A review of literature. J. Hum. Reprod. Sci. 2015;8:191–196. doi: 10.4103/0974-1208.170370. - DOI - PMC - PubMed
    1. Cooper T.G., Noonan E., von Eckardstein S., Auger J., Baker H.W.G., Behre H.M., Haugen T.B., Kruger T., Wang C., Mbizvo M.T., et al. World Health Organization reference values for human semen characteristics. Hum. Reprod. Update. 2009;16:231–245. doi: 10.1093/humupd/dmp048. - DOI - PubMed
    1. Guzick D.S., Overstreet J.W., Factor-Litvak P., Brazil C.K., Nakajima S.T., Coutifaris C., Vogel D.L. Sperm morphology, motility, and concentration in fertile and infertile men. N. Engl. J. Med. 2001;345:1388–1393. doi: 10.1056/NEJMoa003005. - DOI - PubMed

LinkOut - more resources