Sperm-cell detection using YOLOv5 architecture
Infertility has become a severe health issue in recent years. Sperm morphology, sperm motility, and sperm density are the most critical factors in male infertility. As a result, sperm motility, density, and morphology are examined in semen analysis carried out by laboratory professionals. However, a...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Book Section |
| Published: |
Springer Science and Business Media Deutschland GmbH
2022
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/100501/ http://dx.doi.org/10.1007/978-3-031-07802-6_27 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Infertility has become a severe health issue in recent years. Sperm morphology, sperm motility, and sperm density are the most critical factors in male infertility. As a result, sperm motility, density, and morphology are examined in semen analysis carried out by laboratory professionals. However, applying a subjective analysis based on laboratory observation is easy to make a mistake. To reduce the effect of specialists in semen analysis, a computer-aided sperm count estimation approach is proposed in this work. The quantity of active sperm in the semen is determined using object detection methods focusing on sperm motility. The proposed strategy was tested using data from the Visem dataset provided by Association for Computing Machinery. We created a small sample custom dataset to prove that our network will be able to detect sperms in images. The best not-super tuned result is mAP 72.15. |
|---|