Aiforia Create feature: Annotation Assistant

The cloud-based active learning tool improves accuracy and reduces the amount of annotations it takes to develop successful AI models with Aiforia Create.
Written by Aiforia

Lightning fast AI training with Aiforia's patented method 

Aiforia’s cloud-based software, Aiforia Create, enables medical professionals to create AI models, without the need to code or use dedicated hardware, for any image analysis application. This is now made even easier with Annotation Assistant which increases the efficiency and accuracy of training AI models while decreasing the time and effort you need to spend in training AI. 

Annotation Assistant utilizes active learning, a highly sought-after technique in artificial intelligence, for which Aiforia holds a U.S. patent. 

The novel tool works by scanning images for areas that would provide the most useful training data during AI model development; suggesting these to the user to make the decision to accept, modify or reject.

This auto scanning technique therefore decreases training time, improves the quality of the AI model and is particularly useful in analyzing rare cases and large data sets with heavy variation. The same tool also provides an ideal method to rapidly adapt pre-validated AI models to a new laboratory. 

What are the benefits of using Annotation Assistant?

ic_clock-1       Decrease AI training time

ic_deep learning-1       Improve AI training quality

ic_discover-1       Particularly useful for rare cases and large data sets with heavy variation

Oncology case example

Accelerating AI training for PD-L1 analysis

 

“Annotation Assistant really saves you a lot of time. It also brings up the more difficult areas that I myself would not have realized to annotate. It really made the AI model better.”

Liesbeth Hondelink, Leiden University Medical Center

Annotation Assistant testimonial-1

Neuroscience case example

Automating AI training for neuron quantification

 

“The clear benefits, apart from speeding up the process, is that the new candidate objects that the Annotation Assistant suggests are well distributed throughout the whole slide."

Joan Compte Barrón, VHIR Vall d’Hebron Research Institute

image analysis annotation assistant

image analysis annotation assistant

Want to see high-speed AI in action?

Book a free demo!

 

Want to find out more about Aiforia?

Contact us