The evaluation of a human embryo is among the biggest challenges in human infertility treatments, specifically in the In-Vitro Fertilization method. Evaluating the viability of a fertilized egg and embryo is a complex process, which calls for extensive manual labor while demanding high amounts of concentration, sometimes lasting up to several hours per day. To determine which eggs can be utilized, embryologists use a set of 400 markers that indicate the quality of an embryo and ensure an objective evaluation. However, such a vast pool of data can quickly become problematic. Furthermore, clinics have lately experienced an increased number of IVF chains, which intensifies the need for a unification of treatment procedures and continuous quality of treatments.
Cognexa developed and automated & cognitive human embryo annotation and evaluation system that provides embryologists with additional, objective, consistent and interpretable clinical data to assist them in efficient decision-making and the improvement of IVF treatment results. This leads to fewer cycles needed to successfully conceive, which not only decrease the emotional stress patients experience during the IVF process as well as the level of health risks, but also decreased the financial burden put on patients and health insurances.
Our solution is based on an expert system and 6 DNNs which determine:
It took 6 weeks to develop the first prototype and 6 additional months to develop an MVP. Additionally, the system works with 5 days of embryo images taken with the Primovision time-lapse system.
Our program delivers results for one patient in as few as 45 seconds - as opposed to 1-2 hours when evaluated manually - and achieves a 91 - 99% rate of precision (depending of the feature). The system is currently going through clinical tests and runs on the client's premises. A cloud-based solution is planned to be released in the beginning of 2018.
Our embryo evaluation system was presented at the ESHRE 2016 and 2017 conferences and received extensive, positive feedback. To our knowledge, there is no comparable system currently available on the global market.
Deep-learning automated cognitive human embryo annotation and evaluation system to assesses the quality of embryos.
6 weeks to prototype
6 months to MVP
TensorFlow, Python, C++, CxFlow
91-99% precision (better than human)
45 sec instead of 1-2 hrs,
decreased emotional stress, lower health risk
significant financial savings (thousands of USD per couple)