A Convolutional Neural Network Model with Feature Fusion for Sperm Morphology Classification
Corresponding author: Firman Tempola
Abstract
Sperm morphology analysis is a key parameter in male fertility evaluation, but the manual process is subjective and time-consuming. Therefore, an automated deep learning classification system offers a potential solution. This study evaluates and compares MobileNetV2 and EfficientNetB0, individually and in combination via feature fusion, for sperm morphology image classification using the SMID dataset of 3000 images. MobileNetV2 and EfficientNetB0 models achieved accuracies of 62.75% and 33.06%, respectively, after 50 epochs, while the feature fusion model reached 85.04% in only 5 epochs. Thus, combining features from both architectures yields superior accuracy and efficiency for automated sperm analysis.
Keywords:
sperm morphology classification, deep learning, convolutional neural network, feature fusion, MobileNetV2, EfficientNetB0Downloads
References
G. M. Centola, "Semen Assessment,"Urologic Clinics of North America, vol. 41, no. 1, pp. 163–167, Feb. 2014. DOI: https://doi.org/10.1016/j.ucl.2013.08.007
A. Aykaç, C. Kaya, Ö. Çelik, M. E. Aydın, and M. Sungur, "The prediction of Semen Quality Based on Lifestyle Behaviours by the Machine Learning Based Models," Reproductive Biology and Endocrinology, vol. 22, no. 1, Aug. 2024, Art. no. 112. DOI: https://doi.org/10.1186/s12958-024-01268-w
H. E. Lyons, P. Gyawali, N. Mathews, P. Castleton, S. M. Mutuku, and N. O. McPherson, "The Influence of Lifestyle and Biological Factors on Semen Variability," Journal of Assisted Reproduction and Genetics, vol. 41, no. 4, pp. 1097–1109, Apr. 2024. DOI: https://doi.org/10.1007/s10815-024-03030-y
H.-H. Huang et al., "Machine Learning Predictive Models for Evaluating Risk Factors Affecting Sperm Count: Predictions Based on Health Screening Indicators," Journal of Clinical Medicine, vol. 12, no. 3, Feb. 2023, Art. no. 1220. DOI: https://doi.org/10.3390/jcm12031220
H. O. Ilhan, M. Yuzkat, and N. Aydin, "Sperm Motility Analysis by using Recursive Kalman Filters with the Smartphone-Based Data Acquisition and Reporting Approach," Expert Systems with Applications, vol. 186, Dec. 2021, Art. no. 115774. DOI: https://doi.org/10.1016/j.eswa.2021.115774
R. Marín and V. Chang, "Impact of Transfer Learning for Human Sperm Segmentation using Deep Learning," Computers in Biology and Medicine, vol. 136, Sept. 2021, Art. no. 104687. DOI: https://doi.org/10.1016/j.compbiomed.2021.104687
E. Lewandowska, D. Węsierski, M. Mazur-Milecka, J. Liss, and A. Jezierska, "Ensembling Noisy Segmentation Masks of Blurred Sperm Images," Computers in Biology and Medicine, vol. 166, Nov. 2023, Art. no. 107520. DOI: https://doi.org/10.1016/j.compbiomed.2023.107520
A. Mehrjerd, T. Dehghani, M. Jajroudi, S. Eslami, H. Rezaei, and N. K. Ghaebi, "Ensemble Machine Learning Models for Sperm Quality Evaluation Concerning Success Rate of Clinical Pregnancy in Assisted Reproductive Techniques," Scientific Reports, vol. 14, no. 1, Oct. 2024, Art. no. 24283. DOI: https://doi.org/10.1038/s41598-024-73326-7
Y. Guo et al., "Automated Deep Learning Model for Sperm Head Segmentation, Pose Correction, and Classification," Applied Sciences, vol. 14, no. 23, Dec. 2024, Art. no. 11303. DOI: https://doi.org/10.3390/app142311303
I. Iqbal, G. Mustafa, and J. Ma, "Deep Learning-Based Morphological Classification of Human Sperm Heads," Diagnostics, vol. 10, no. 5, May 2020, Art. no. 325. DOI: https://doi.org/10.3390/diagnostics10050325
H. Jabbari and N. Bigdeli, "New Conditional Generative Adversarial Capsule Network for Imbalanced Classification of Human Sperm Head Images," Neural Computing and Applications, vol. 35, no. 27, pp. 19919–19934, Sept. 2023. DOI: https://doi.org/10.1007/s00521-023-08742-3
V. Thambawita et al., "VISEM-Tracking, a Human Spermatozoa Tracking Dataset," Scientific Data, vol. 10, no. 1, May 2023, Art. no. 260. DOI: https://doi.org/10.1038/s41597-023-02173-4
G. Mendizabal-Ruiz et al., "Computer Software (SiD) Assisted Real-Time Single Sperm Selection Associated with Fertilization and Blastocyst Formation," Reproductive BioMedicine Online, vol. 45, no. 4, pp. 703–711, Oct. 2022. DOI: https://doi.org/10.1016/j.rbmo.2022.03.036
W. Dai et al., "Automated Non-Invasive Analysis of Motile Sperms using Sperm Feature-Correlated Network," IEEE Transactions on Automation Science and Engineering, vol. 22, pp. 3960–3970, 2025. DOI: https://doi.org/10.1109/TASE.2024.3404488
J. B. You, C. McCallum, Y. Wang, J. Riordon, R. Nosrati, and D. Sinton, "Machine Learning for Sperm Selection," Nature Reviews Urology, vol. 18, no. 7, pp. 387–403, July 2021. DOI: https://doi.org/10.1038/s41585-021-00465-1
M. Yüzkat, H. O. Ilhan, and N. Aydin, "Multi-model CNN Fusion for Sperm Morphology Analysis," Computers in Biology and Medicine, vol. 137, Oct. 2021, Art. no. 104790. DOI: https://doi.org/10.1016/j.compbiomed.2021.104790
S. Khandelwal, A. Raut, H. Vyawahare, D. Theng, and S. Dhande, "Optimizing Performance in Mango Plant Leaf Disease Classification through Advanced Machine Learning Techniques," Engineering, Technology & Applied Science Research, vol. 14, no. 6, pp. 18476–18480, Dec. 2024. DOI: https://doi.org/10.48084/etasr.8220
H. Ilhan, "Sperm Morphology Image Data Set (SMIDS)." Mendeley, Jan. 17, 2022, [Online]. Available: https://data.mendeley.com/datasets/6xvdhc9fyb/1.
H. O. Ilhan and N. Aydin, "A Novel Data Acquisition and Analyzing Approach to Spermiogram Tests," Biomedical Signal Processing and Control, vol. 41, pp. 129–139, Mar. 2018. DOI: https://doi.org/10.1016/j.bspc.2017.11.009
A. Nabipour, M. J. Shams Nejati, Y. Boreshban, and S. A. Mirroshandel, "Less-Supervised Learning with Knowledge Distillation for Sperm Morphology Analysis," Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, vol. 12, no. 1, Dec. 2024, Art. no. 2347978. DOI: https://doi.org/10.1080/21681163.2024.2347978
H. O. Ilhan, G. Serbes, and N. Aydin, "Dual Tree Complex Wavelet Transform Based Sperm Abnormality Classification," in 2018 41st International Conference on Telecommunications and Signal Processing, Athens, Greece, July 2018, pp. 1–5. DOI: https://doi.org/10.1109/TSP.2018.8441431
Downloads
How to Cite
License
Copyright (c) 2025 Firman Tempola, Ardiansyah, Munazat Salmin, Leonardo Petra Refialy
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
