IVFVision
Welcome to IVFVision.ai for Embryo Selection – a new artificial intelligence platform aimed at improving IVF success rates by helping embryologists select the best embryo for transfer.
About
IVFvision.ai helps identify embryos that will most likely lead to successful implantation with positive heart beat.
Quick and easy to use
- Upload an image of a blastocyst from your computer - this can be a standard microscope image or an image from a time-lapse system
- Select submit – it only takes seconds for our powerful algorithm to accurately predict the probability of successful implantation
- Read the results displayed on your screen e.g. Positive 90% or Negative 55%.

Using IVFVision.ai
IVFVision.ai is intended as a decision-support tool rather than a replacement for a skilled or experienced embryologist. It is particularly helpful in cases where clinicians struggle to differentiate between images. IVFVision.ai is also a highly effective training tool for new or less experienced staff - especially as it can be used without supervision.
Get Started Now



Why trust a machine for embryo selection?
Computers are capable of recognising structures which the naked eye cannot. They can also process larger data sets both faster and more accurately than humans. Our approach uses a combination of computer vision, machine learning and artificial intelligence to analyse the morphology of blastocyst images.
Advantages
- reliable – it can assess features invisible to the human eye
- accurate – machine learning reduces the scope for human error, guesswork and subjectivity
- scalable – it can be used by both experienced and inexperienced operators
- reproducible – automation means results are consistent between individual clinics and individual operators
- fast – a machine processes images faster than a manual operator
- low cost – it is an inexpensive method allowing all IVF clinics to implement AI technology
Advantages of using IVFVision.ai for Embryo Selection
IVFVision.ai for Embryo Selection will enable you to:
- more consistently and accurately identify the blastocysts that are most likely to implant, as well as those most suitable for cryopreservation
- reduce the need to transfer multiple embryos to achieve a successful pregnancy
- avoid the negative consequences of multiple pregnancies
- increase the chances your patients will get pregnant during their first treatment cycle



1 in 6 Couples faces infertility
Infertility is described as a disease affecting one in six couples worldwide, with a recent policy audit showing that more than 25 million EU citizens are infertile. We are here to improve In Vitro Fertilization (IVF) therapies with a really innovative way.

A second opinion for the Embryologists when they really need it.
IVFVision.ai is able to identify blastocysts that are most likely to implant with high accuracy, sensitivity and specificity. Our approach has high predictive power and offers a fast, non-invasive and inexpensive solution to IVF laboratories around the world, seeking to maximize their success rates. The system only requires the image of a blastocyst, and can be compatible with time-lapse systems, as well as with standard microscopy observations in laboratories without time-lapse. The application can be adapted to any type of equipment configuration, to suit all laboratory requirements.
Technology

Appying Convolutional Neural Networks (CNN)
CNNs have a set of filters working on localised regions that make connections in small two-dimensional areas of the input image, called the local receptive fields. CNNs use the same weights and biases for each of the hidden neurons. By sharing the weights, the network is forced to learn invariant features at different regions of the image. Thus, all the neurons in the layer detect the same feature but at different locations in the image.
Learn more
Pooling Layers
Pooling layers are a type of layer typically used after Convolutional layers. They summarise the information from the convolution layer by performing a statistical aggregate function, typically average or max, applied to each feature map and by producing a compressed feature map. Forward propagation evaluates the activations, and backward propagation computes the gradient from the above layer and the local gradient to calculate gradients on the layer parameters.
Learn more
Learn from the lab
We fed images to the AI System with a sequence of convolution and pooling layers; convolution to extract spatial invariant features from a subsample using the spatial average of maps and a multilayer Neural Network (MLP) as a final classifier (fully connected layers); and a sparse connection matrix between layers (weight sharing) to avoid a large computational cost and reduce overfitting.
Learn more