Aarhus University Seal

Automatic Scoring and Selection of Embryos for Improving Standard IVF Treatment (ASSIST)

The core project client here is the company Vitrolife A/S, specializing in assisted reproductive technology. Our industrial postdoc Mikkel Fly Kragh, part of DIGIT team, is working on modern machine learning technologies applied on time-lapse microscopy imaging.

In vitro fertilization (IVF) treatment is a billion dollar industry. The treatment is performed by fertilizing a number of eggs by sperm (producing embryos) outside the body where they are cultured for 2-6 days. Finally, one or more embryos are transferred to the mother’s uterus with the aim of establishing a successful pregnancy. The main challenge is to maximize the probability of pregnancy by choosing the most viable embryo(s) for transfer and for potential cryopreservation (freezing). Today, this is done manually, resulting in tedious work and subjective assessments. The need appears for more digital options.

The current case investigates modern computer vision and deep learning technology on time-lapse Hoffman modulation contrast (HMC) microscopy imaging. The objectives of our potential provided solution are to improve clinical workflow and provide objective and possibly new and undiscovered measures of embryo viability directly related to the probability of pregnancy. Although HMC microscopy remains the preferred imaging modality among embryologists, there only exist a few prototype software systems for automated analysis of this type of image data. The project seeks to transfer recent breakthroughs within computer vision and deep learning to a promising but relatively unexplored field.

DIGIT has provided Vitrolife A/S access to powerful computer systems and servers, software and algorithms.

Contact: Henrik Karstoft, Aarhus University, hka@eng.au.dk.

Online reference: http://digit.au.dk/research-projects/assist/