Use of federated learning to develop an artificial intelligence model predicting usable blastocyst formation from pre-ICSI oocyte images
In total, 10,677 oocyte images with associated metadata were collected prospectively by eight IVF clinics across six countries. AI training used federated learning, where data were retained on regional servers to comply with data privacy laws. The final AI model required a single image as input to evaluate oocyte competence, which was defined by the formation of a usable blastocyst (≥expansion grade 3 by day 5 or 6 post ICSI).
Authors
- Monia Perugini (ORCID: https://orcid.org/0000-0003-4294-9866)
- Don Perugini
- Jonathan M. M. Hall (ORCID: https://orcid.org/0000-0002-7719-1103)
- Yoshimasa Asada (ORCID: https://orcid.org/0000-0002-0448-9953)
- M.C. Schiewe (ORCID: https://orcid.org/0000-0002-2979-2932)
- Jason Chiang (ORCID: https://orcid.org/0000-0003-2896-1930)
- S. Mankee-Sookram
- Sonya M. Diakiw (ORCID: https://orcid.org/0000-0002-4554-7224)
- Trung Van Nguyen (ORCID: https://orcid.org/0000-0003-3363-5064)
- Nayana Patel (ORCID: https://orcid.org/0000-0003-2650-2458)
- Andrew W. Dinsmore
- Erdal Bilen
- A Y X Lim
- Charles Lee
- C. Minto-Bain
- Dirk Böse
- N. Fukunaga
- HarshaKarsan Bhadarka
Institutions
- Australian Research Council (AU)
- University of Trinidad and Tobago (TT)
- Dokuz Eylül University (TR)
- CS Diagnostics (DE)
- ARC Centre for Nanoscale BioPhotonics
- The University of Adelaide (AU)
Publication Details
- Journal
- Reproductive BioMedicine Online
- Published
- 2024-08-13
- DOI
- https://doi.org/10.1016/j.rbmo.2024.104403
- Citations
- 5
- Primary Topic
- Reproductive Biology and Fertility
- Type
- article
- Field-Weighted Citation Impact
- 2.71