Optimising IVF Outcome with a Personalised Medicine Approach

Short Summary
We propose to develop a computational personalized medicine approach for egg collection during in vitro fertilization (IVF).
Goals
We propose to develop a software for clinical use that will provide better image analysis tools for clinicians, as well as data- and model-based guidance regarding the best IVF treatment schedule, based on the measured hormone levels and the ovarian response. Given our detailed understanding of ovarian follicle maturation, this personalized medicine approach can go beyond statistical correlation and can be based on a mechanistic understanding of the hormonal control of ovarian follicle maturation.
Significance
This project will enable personalized treatments for women undergoing IVF. Such an approach holds a lot of promise given the large differences between patients, and the dependence of the interpretation of the many data gathered before and during the treatment on the personal experience and dedication of the treating clinicians.
Background
First successfully used in 1978, in vitro fertilization (IVF) is now used routinely as a form of assisted reproductive technology (ART). While the cumulative likelihood of live birth by the fifth embryo transfer cycle is currently about 80%, there remains an urgent need to improve treatment protocols, considering the high financial and psychological burden of the many failed IVF cycles. The main determinants of live birth are age and ovarian reserve, but individual differences in hormone levels strongly affect IVF outcome.
  • Yamauchi, K., Biniasch, M., Franz, L., Gómez, H., De Geyter, C. and Iber, D. (2022). FollicleFinder: automated three-dimensional segmentation of human ovarian follicles. bioRxiv

iDoc

DagmarIber-Profile-Image

Prof. Dr. Dagmar Iber

ETH Zurich
Co-Investigators
  • Christian De Geyter

Related Posts