Systematic Evaluation of YOLOv8 Training Configurations for Detecting Bovine Sperm Head Abnormalities

Rizqy Khoirul Waritsin; I Gede Susrama Mas Diyasa; Eva Yulia Puspaningrum

doi:10.59934/jaiea.v6i1.2713

Authors

Rizqy Khoirul Waritsin UPN Veteran Jawa Timur
I Gede Susrama Mas Diyasa UPN Veteran Jawa Timur
Eva Yulia Puspaningrum UPN Veteran Jawa Timur

DOI:

https://doi.org/10.59934/jaiea.v6i1.2713

Keywords:

Bovine Sperm, CLAHE, Deep Learning, Object Detection, YOLOv8

Abstract

Bovine sperm morphology assessment is an important stage in evaluating semen quality for artificial insemination programs. Manual examination under a microscope is time-consuming and highly dependent on the observer's expertise, motivating the development of automated detection systems using deep learning. This study systematically evaluates the influence of YOLOv8 training configurations for detecting bovine sperm head abnormalities. A total of 27 experimental scenarios were designed by combining three optimizers (SGD, Adam, and RMSProp), three learning rates (0.0001, 0.001, and 0.01), and three training epochs (75, 100, and 125). Contrast Limited Adaptive Histogram Equalization (CLAHE) was applied to improve image quality before model training. Performance was evaluated using Precision, Recall, F1-score, and mAP@0.5. The experimental results indicate that the training configuration significantly affects detection performance. The best performance was achieved using the RMSProp optimizer with a learning rate of 0.01 and 75 training epochs, producing a Precision of 89.81%, Recall of 88.38%, F1-score of 89.08%, and mAP@0.5 of 91.76%. These findings demonstrate that systematic evaluation of training configurations provides practical guidance for improving YOLOv8-based bovine sperm abnormality detection without modifying the network architecture

Downloads

Download data is not yet available.

References

B. M. Tanga, A. Y. Qamar, S. Raza, S. Bang, X. Fang, K. Yoon, and J. Cho, “Semen Evaluation: Methodological Advancements in Sperm Quality-Specific Fertility Assessment—A Review,” Animal Bioscience, vol. 34, no. 8, pp. 1253–1270, 2021, doi: 10.5713/ab.21.0072.

H. C. Azevedo, H. D. Blackburn, E. A. Lozada-Soto, S. F. Spiller, and P. H. Purdy, “Enhancing Evaluation of Bull Fertility through Multivariate Analysis of Sperm,” Journal of Dairy Science, vol. 107, no. 12, pp. 11774–11784, 2024, doi: 10.3168/jds.2024-25079.

S. Urli, F. Corte Pause, T. Dreossi, M. Crociati, and G. Stradaioli, “Evaluation of an Artificial Intelligence System for Bull Sperm Morphology Evaluation,” Theriogenology, vol. 245, Art. no. 117504, 2025, doi: 10.1016/j.theriogenology.2025.117504.

P. Hidayatullah, X. Wang, T. Yamasaki, T. L. E. R. Mengko, R. Munir, A. Barlian, E. Sukmawati, and S. Supraptono, “DeepSperm: A Robust and Real-Time Bull Sperm-Cell Detection in Densely Populated Semen Videos,” Computer Methods and Programs in Biomedicine, vol. 209, Art. no. 106302, 2021, doi: 10.1016/j.cmpb.2021.106302.

C. Zhang, Y. Zhang, Z. Chang, and C. Li, “Sperm YOLOv8E-TrackEVD: A Novel Approach for Sperm Detection and Tracking,” Sensors, vol. 24, no. 11, Art. no. 3493, 2024, doi: 10.3390/s24113493.

F. Sevilla, I. Araya-Zúñiga, A. Méndez-Porras, J. Alfaro-Velasco, E. Jiménez-Delgado, M. A. Silvestre, R. Molina-Montero, E. R. S. Roldan, and A. Valverde, “Design and Implementation of a Deep Learning System to Analyze Bovine Sperm Morphology,” Veterinary Sciences, vol. 12, no. 10, Art. no. 1015, 2025, doi: 10.3390/vetsci12101015.

M. A. Albahar, “Skin Lesion Classification Using Convolutional Neural Network With Novel Regularizer,” IEEE Access, vol. 11, pp. 38307–38318, 2023, doi: 10.1109/ACCESS.2023.3268179.

S. Dash, S. Senapati, and S. Swain, “An Improved Medical Image Enhancement Method Using CLAHE and Deep Learning for Biomedical Image Analysis,” Biomedical Signal Processing and Control, vol. 84, Art. no. 104777, 2023, doi: 10.1016/j.bspc.2023.104777.

Y. Wang, N. Chen, H. Zhang, Z. Liu, X. Li, and J. Wang, “YOLOv8: A New Era of Real-Time Object Detection Algorithms,” IEEE Access, vol. 12, pp. 45891–45908, 2024, doi: 10.1109/ACCESS.2024.3372106.

L. Yang, J. Li, and X. Zhao, “Hyperparameter Optimization for Deep Learning-Based Object Detection Models,” Expert Systems with Applications, vol. 223, Art. no. 119951, 2023, doi: 10.1016/j.eswa.2023.119951.

M. K. Islam, A. Rahman, S. Rahman, M. S. Hossain, and M. A. Islam, “YOLO-Based Deep Learning Framework for Automated Sperm Cell Detection and Morphology Analysis,” Computers in Biology and Medicine, vol. 176, Art. no. 108624, 2024, doi: 10.1016/j.compbiomed.2024.108624.