Dobrovolny, Michal and Benes, Jakub and Krejcar, Ondrej and Selamat, Ali (2022) Sperm-cell detection using YOLOv5 architecture. In: Bioinformatics and Biomedical Engineering 9th International Work-Conference, IWBBIO 2022, Maspalomas, Gran Canaria, Spain, June 27–30, 2022, Proceedings, Part II. Lecture Notes in Computer Science, 13347 (NA). Springer Science and Business Media Deutschland GmbH, Cham, Switzerland, pp. 319-330. ISBN 978-303107801-9
Full text not available from this repository.
Official URL: http://dx.doi.org/10.1007/978-3-031-07802-6_27
Abstract
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.
| Item Type: | Book Section |
|---|---|
| Uncontrolled Keywords: | Computer-aided sperm analysis, Small-object detection, Sperm-cell detection, Yolo |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Malaysia-Japan International Institute of Technology |
| ID Code: | 100501 |
| Deposited By: | Widya Wahid |
| Deposited On: | 14 Apr 2023 02:17 |
| Last Modified: | 14 Apr 2023 02:17 |
Repository Staff Only: item control page
