Proceedings of the 5th International Conference on Applied Sciences, Mathematics, and Informatics (ICASMI 2024)

<Previous Article In Volume
Next Article In Volume>

Classification of Human Sperm Based on Morphology Using Densely Connected Convolutional Networks

Authors
Aristoteles Aristoteles1, 2, *, Admi Syarif2, Dewi Asiah Shofiana2, Irma Azizah2
1Doctoral Program of Mathematics and Natural Sciences, Lampung University, Bandar Lampung, Indonesia
2Department of Computer Science, Faculty of Mathematics and Natural Sciences, University of Lampung, Bandar Lampung, Indonesia
*Corresponding author. Email: aristoteles.1981@fmipa.unila.ac.id
Corresponding Author
Aristoteles Aristoteles
Available Online 27 May 2025.
DOI
10.2991/978-94-6463-730-4_6How to use a DOI?
Keywords
Densenet; Male infertility; Sperm morphology
Abstract

Male infertility, which accounts for about 50% of all infertility cases, is assessed through sperm morphology analysis. However, the complex variation of sperm shapes often complicates the diagnosis process. Automated systems offer a more accurate solution than manual selection. This study aims to implement the DenseNet169 CNN architecture for sperm classification based on morphology and to test its performance with different data sharing schemes. On the HuSHem dataset, the highest accuracy of 97.78% was obtained with a data sharing ratio of 70:25:5, while the SCIAN dataset achieved an accuracy of 78.79% at the same ratio. DenseNet169, with its dense connectivity, is proven to be effective in overcoming the gradient vanishing problem and improving feature efficiency, resulting in high performance in sperm morphology classification.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 5th International Conference on Applied Sciences, Mathematics, and Informatics (ICASMI 2024)
Series
Advances in Physics Research
Publication Date
27 May 2025
ISBN
978-94-6463-730-4
ISSN
2352-541X
DOI
10.2991/978-94-6463-730-4_6How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Aristoteles Aristoteles
AU  - Admi Syarif
AU  - Dewi Asiah Shofiana
AU  - Irma Azizah
PY  - 2025
DA  - 2025/05/27
TI  - Classification of Human Sperm Based on Morphology Using Densely Connected Convolutional Networks
BT  - Proceedings of the 5th International Conference on Applied Sciences, Mathematics, and Informatics (ICASMI 2024)
PB  - Atlantis Press
SP  - 59
EP  - 68
SN  - 2352-541X
UR  - https://doi.org/10.2991/978-94-6463-730-4_6
DO  - 10.2991/978-94-6463-730-4_6
ID  - Aristoteles2025
ER  -