Improving Cancer Diagnostics with Machine Learning

We provide completely automated solutions for recognition and analysis of tissue patterns based on the latest generation of Deep Learning visual recognition technology.

Machine Learning algorithms learn to recognize images and patterns in the same way humans do – by example, rather than by human-derived "handcrafted features" such as shape, size, brightness etc. Since 2012 , the latest visual recognition technologies based on Deep Learning methods can achieve pattern recognition accuracy comparable or superior to human observers.

Using Machine Learning methods to image analysis has number of benefits:

  • No need to formalize complex "handcrafted features" , pathologist can just point to patterns they need to recognize
  • No dependency on image analysis engineers (almost)
  • System can be trained on variety of samples to achieve robust recognition
  • New data samples can easily be added to the model to increase accuracy


In USA IVD applications are labeled "For Research Use Only. Not for use in diagnostic procedures" in accordance with FDA product labeling regulations

Ready to get started?
See details and
sign up

Need Custom Analysis?

If you need custom image analysis application for your digital slides our application development team can help. We use our extensive image analysis libraries and scientific expertise to package and deploy custom application for you, often in a matter of days.

To start the process simply upload images to your web workspace, add markers and annotations explaining the analysis, and send us a link to support[at]simagis.us along with a problem statement. Our experts will review the image and give you development estimate. Once application is ready, it will be added to your web workspace on server so you can apply and test it on your images. You only pay if it works. 

Got Algorithms?

If you are a developer and have great image analysis application that you want the whole world to use, we can make it happen. We can run your Java, C++, or Python application code, "webinaze" the interface with our API and deliver your web application to all our users around the world via App Store. Contact us to discuss opportunities.