Use of federated learning to develop an artificial intelligence model predicting usable blastocyst formation from pre-ICSI oocyte images.

Autor: Hall JMM; Life Whisperer Diagnostics (a subsidiary of Presagen), San Francisco, CA, USA, and Adelaide, Australia; Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, Adelaide, Australia; Adelaide Business School, The University of Adelaide, Adelaide, Australia., Nguyen TV; Life Whisperer Diagnostics (a subsidiary of Presagen), San Francisco, CA, USA, and Adelaide, Australia., Dinsmore AW; California Fertility Partners, Los Angeles, CA, USA., Perugini D; Life Whisperer Diagnostics (a subsidiary of Presagen), San Francisco, CA, USA, and Adelaide, Australia., Perugini M; Life Whisperer Diagnostics (a subsidiary of Presagen), San Francisco, CA, USA, and Adelaide, Australia; Adelaide Medical School, The University of Adelaide, Adelaide, Australia., Fukunaga N; Asada Institute for Reproductive Medicine, Nagoya, Japan., Asada Y; Asada Ladies Clinic, Nagoya, Japan., Schiewe M; California Fertility Partners, Los Angeles, CA, USA., Lim AYX; Alpha IVF and Women's Specialists, Petaling Jaya, Selangor, Malaysia., Lee C; Alpha IVF and Women's Specialists, Petaling Jaya, Selangor, Malaysia., Patel N; Akanksha Hospital and Research Institute, Anand, Gujarat, India., Bhadarka H; Akanksha Hospital and Research Institute, Anand, Gujarat, India., Chiang J; Kensington Green Specialist Centre, Iskandar Puteri, Johor, Malaysia., Bose DP; Indore Infertility Clinic, Indore, Madhya Pradesh, India., Mankee-Sookram S; Trinidad and Tobago IVF and Fertility Centre, Maraval, Trinidad, Trinidad and Tobago., Minto-Bain C; Trinidad and Tobago IVF and Fertility Centre, Maraval, Trinidad, Trinidad and Tobago., Bilen E; Dokuz Eylül University, Inciraltı, Balçova/İzmir, Turkey., Diakiw SM; Life Whisperer Diagnostics (a subsidiary of Presagen), San Francisco, CA, USA, and Adelaide, Australia. Electronic address: sonya@lifewhisperer.com.
Jazyk: angličtina
Zdroj: Reproductive biomedicine online [Reprod Biomed Online] 2024 Dec; Vol. 49 (6), pp. 104403. Date of Electronic Publication: 2024 Aug 13.
DOI: 10.1016/j.rbmo.2024.104403
Abstrakt: Research Question: Can federated learning be used to develop an artificial intelligence (AI) model for evaluating oocyte competence using two-dimensional images of denuded oocytes in metaphase II prior to intracytoplasmic sperm injection (ICSI)?
Results: The oocyte AI model demonstrated area under the curve (AUC) up to 0.65 on two blind test datasets. High sensitivity for predicting competent oocytes (83-88%) was offset by lower specificity (26-36%). Exclusion of confounding biological variables (male factor infertility and maternal age ≥35 years) improved AUC up to 14%, primarily due to increased specificity. AI score correlated with size of the zona pellucida and perivitelline space, and ooplasm appearance. AI score also correlated with blastocyst expansion grade and morphological quality. The sum of AI scores from oocytes in group culture images predicted the formation of two or more usable blastocysts (AUC 0.77).
Conclusion: An AI model to evaluate oocyte competence was developed using federated learning, representing an essential step in protecting patient data. The AI model was significantly predictive of oocyte competence, as defined by usable blastocyst formation, which is a critical factor for IVF success. Potential clinical utility ranges from selective oocyte fertilization to guiding treatment decisions regarding additional rounds of oocyte retrieval.
Design: 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).
(Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: