multi class classification

What is it about?

This study proposes the use of multi-class classifiers instead of the traditional binary classifiers when the targeted disease may have an overlap with another know disease. We study this in a dementia dataset containing alzheimer disease, frontotemporal disease and healthy controls.

Featured Image

Why is it important?

This is the first study to shed light on the importance of, and the need for, multi-class prediction models in neuroimaging, and medical image analysis in general. We present how that can be conducted, and exhibit new technology to analyze classification performance of multi-class classifiers.