top of page

Streamline Your Medical Imaging AI Research

Like GitHub for your medical imaging AI projects. Seeing your project through from start to finish, Datamint will help on day one - when you are making your data accessible by your team - all the way through until the day you are ready to deploy your model.

AI researchers spend 60-80% of their time managing data and the rest doing science. Datamint wants to invert that.

DataMint.png
Why Us

Features

01.

Data Ingestion and Pre-Processing.

Your imaging data is sent to your private Datamint library where it is accessible by your team. Before it gets there it will be de-identified and can have any number of pre-processing steps applied. Filter through thousands of images in your library to find the ones you need for your latest experiment.

02.

Data Annotation Online and Offline

Labelling and segmentation are critical for medical images, and Datamint streamlines the process. Save time and reduce frustration and errors while using familiar tools like ITK-Snap.

03.

Training data management 

Create immutable datasets containing images and annotations to train your models and share with other researchers. Once created they are accessible by your team, all the while ensuring data providence, experiment replicability, and governance.

04.

Model and artifact management

Your experimental results - each model, its accuracy, architecture, hyper parameters, and the road it took to get to where it is, can be automatically saved right from your python code and made accessible for you and your team. It's a zero-effort lab notebook that never gets lost.

05.

Model deployment

The true end goal - getting your model out of the lab and into the hands of end users. Datamint is built with that goal in mind.

How Researchers Use Datamint

JaremkoLab.jpg

Dr. Jacob Jaremko of NIDUS lab - a user of Datamint - at the University of Alberta. 

Conducting medical AI research involves team members with widely diverse skills. Field experts who acquire the images, experts who segment and label pictures, principle investigators or project managers who oversee the entire process, lab managers who maintain data libraries, and the researchers who train and test AI models all work with the same data, often at the same time.

Binding this team together is the data, the experimental results, and the models. But despite their pivotal role, images live on USB sticks and in multiple hard drives, experimental results in Excel spreadsheets and scribbled notes, and models get emailed back and forth for modification and evaluation.

 

Datamint is for those teams who want to do better.

How It Works

About Us

Team and Mission

We are a technology company located in Edmonton Alberta, founded by AI experts, seasoned entrepreneurs, and advised by senior AI leaders with expertise in medical imaging AI research. Our belief is that AI will revolutionize healthcare practice in ways we cannot yet imagine - but that AI researchers are the engine that will drive the revolution forward. We are supercharging their efforts by providing platforms and tools that will be at the core of research teams' daily work.

DataMint.png

Contact us 

Reach out to ask us to discuss how your project can start using Datamint

Thanks for reaching out! We will get back to you shortly.

Contact
bottom of page