Deep Learning Models for Multi-Part Morphological Segmentation and Evaluation of Live Unstained Human Sperm
Sensors · 14.05.2025 · 25 (10) · 3093
DOI: 10.3390/s25103093 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 14.05.2025. Verfasst von Peiran Lei und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, School of Engineering, University of Birmingham, Birmingham B15 2TT, UK. Hauptthemen laut MEDLINE: Deep Learning, Spermatozoa, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
To perform accurate computer vision quality assessments of sperm used within reproductive medicine, a clear separation of each sperm component from the background is critical. This study systematically evaluates and compares the performance of Mask R-CNN, YOLOv8, YOLO11, and U-Net in multi-part sperm segmentation, focusing on the head, acrosome, nucleus, neck, and tail. This study conducts a quantitative analysis using a dataset of live, unstained human sperm, employing multiple metrics, including IoU, Dice, Precision, Recall, and F1 Score. The results indicate that Mask R-CNN outperforms other models in segmenting smaller and more regular structures (head, nucleus, and acrosome). In particular, it achieves a slightly higher IoU than YOLOv8 for the nucleus and surpasses YOLO11 for the acrosome, highlighting its robustness. For the neck, YOLOv8 performs comparably to or slightly better than Mask R-CNN, suggesting that single-stage models can rival two-stage models under certain conditions. For the morphologically complex tail, U-Net achieves the highest IoU, demonstrating the advantage of global perception and multi-scale feature extraction. These findings provide insights into model selection for sperm segmentation tasks, facilitating the optimization of segmentation architectures and advancing applications in assisted reproduction and biological image analysis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mechanical Engineering, School of Engineering, University of Birmingham, Birmingham B15 2TT, UK.
ORCID-Profile: Mahdieh Gol Hassani
Zitieren
APA
Lei, P., Saadat, M., Hassani, M. G., & Shu, C. (2025). Deep Learning Models for Multi-Part Morphological Segmentation and Evaluation of Live Unstained Human Sperm. Sensors, 25(10), 3093. https://doi.org/10.3390/s25103093
Vancouver
Lei P, Saadat M, Hassani MG, Shu C. Deep Learning Models for Multi-Part Morphological Segmentation and Evaluation of Live Unstained Human Sperm. Sensors. 2025;25(10):3093. doi:10.3390/s25103093
BibTeX
@article{Lei2025,
author = {Lei, Peiran and Saadat, Mozafar and Hassani, Mahdieh Gol and Shu, Chang},
title = {Deep Learning Models for Multi-Part Morphological Segmentation and Evaluation of Live Unstained Human Sperm},
journal = {Sensors},
year = {2025},
volume = {25},
number = {10},
pages = {3093},
doi = {10.3390/s25103093}
}
EUVIMED