Micro-CT and machine learning: a high-throughput alternative to histology for follicle reserve assessment in cryopreserved ovarian tissue
Micro-CT scanning combined with machine learning analysis represents a novel high-throughput and automated approach for estimating oocyte count in cryopreserved ovarian cortical samples. In addition, three-dimensional analysis offers valuable insights into oocyte localization and spatial distribution within the ovarian cortex, presenting a promising alternative to conventional histology for future clinical and research applications.
Authors
- Katri Knuus (ORCID: https://orcid.org/0000-0002-4725-9728)
- Atte Lahtinen (ORCID: https://orcid.org/0000-0002-2019-897X)
- M. Hannula
- Jari Hyttinen (ORCID: https://orcid.org/0000-0003-1850-3055)
- Timo Tuuri (ORCID: https://orcid.org/0000-0003-0734-3244)
- Marjut Otala (ORCID: https://orcid.org/0000-0002-7914-8897)
- Karolina Lundin (ORCID: https://orcid.org/0000-0003-1679-5349)
- Jasmin Hassan (ORCID: https://orcid.org/0000-0002-5583-3291)
- Pauliina Damdimopoulou
- Mai Nguyen
- Kirsi Jahnukainen
Institutions
- Karolinska University Hospital (SE)
- University of Helsinki (FI)
- Tampere University (FI)
- Helsinki Institute of Physics (FI)
- Helsinki University Hospital (FI)
- Karolinska Institutet (SE)
Publication Details
- Journal
- Journal of Ovarian Research
- Published
- 2025-12-23
- DOI
- https://doi.org/10.1186/s13048-025-01897-8
- Primary Topic
- Reproductive Biology and Fertility
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Helsingin Yliopisto
- Helsingin ja Uudenmaan Sairaanhoitopiiri
- Lastentautien Tutkimussäätiö