Diabetes type 1 is a serious disease causing long-term complications. IsletNet, an AI powered web app, assists doctors with its complicated and highly time-consuming treatment. The solution was developed in cooperation with the Institute for Clinical and Experimental Medicine (IKEM).

What is IsletNet for?

IsletNet is an automated web service designed to assist in the process of isolation of human pancreatic islets, which is an indispensable part of type 1 diabetes treatment.

IsletNet scans, analyses and evaluates uploaded microscopic images, and supplies the doctor with complete results, for both islets and non-islet exocrine tissue, such as an islet count, purity and volume.

Identification of pancreatic islets among other types of tissue and the estimation of their total mass is crucial for choosing the right donors and acceptors for islet surgical transplantation.

Accurate assessment of the islet mass is also vital for medical research in a variety of pancreas-related pursuits, beyond the search for a cure for diabetes. This process is cumbersome, time-consuming and prone to human error.

That is why we developed IsletNet, a deep learning neural network that segments and quickly identifies cells viable for a transplant. Images used to train the network were provided by doctors from all over the world.


Since 2017, IsletNet has been developed and tested during actual transplantations. The produced results are consistent, and the final reports are easy to process and save. As an open collaborative project, it helps to facilitate inter-laboratory standardization. Users are encouraged to share their images, which are then used for periodic training to continuously improve the service. An aggregated F1-score greater than 0.9 shows that the system has a human-like precision.

IsletNet is accessible through the web app and is free of charge at For an unlimited access and permanent links for uploaded batch collections, send us a request.


IsletNet uses AI/ML technologies including deep neural networks and advanced computer vision algorithms. This combination creates a unique, precise and reliable solution.

Tensor Flow
Open CV

Contact us

Fill out your details in the form and we will be in touch within 24 hours.

You can also visit us in our office located at Hybernska 1034/5, Nove Mesto, 110 00 Praha 1.

Or simply send us an email at

Your message has been received!
Oops! Something went wrong while submitting the form. Please try it again.