Development and validation of a deep learning model based on cascade mask regional convolutional neural network to noninvasively and accurately identify human round spermatids
The deep learning AI model based on a cascade R-CNN has the ability to accurately identify hRSs among spermatogenic cells. The application of this noninvasive method, which requires no additional procedures in clinical practice, is able to facilitate the widespread implementation of ROSI technique. Therefore, it can provide patients with spermatogenic arrest the opportunity to become biological fathers.
Authors
- Jie Qiao (ORCID: https://orcid.org/0000-0003-2126-1376)
- Shihao Shao
- Jing Huang (ORCID: https://orcid.org/0000-0001-8250-1535)
- Liying Yan (ORCID: https://orcid.org/0000-0001-9572-9440)
- Ping Liu (ORCID: https://orcid.org/0000-0002-4259-3436)
- Li Zhang (ORCID: https://orcid.org/0000-0001-7914-0679)
- Yujiao Sun
- Yongjie Lu
- Hao Shi (ORCID: https://orcid.org/0000-0002-4935-4147)
- Yuqiang Jiang
Institutions
- Chinese Academy of Sciences (CN)
- Institute of Genetics and Developmental Biology (CN)
Publication Details
- Journal
- Journal of Advanced Research
- Published
- 2025-04-04
- DOI
- https://doi.org/10.1016/j.jare.2025.03.059
- Primary Topic
- Healthcare and Venom Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Natural Science Foundation of Beijing Municipality
- Peking University
- Peking University Third Hospital