Abstract #0460

Explainable MRI: Revealing the mechanisms underlying deep learning brain disease classification

Christian Tinauer¹, Lukas Pirpamer¹, Marc Masana², Stefan Heber¹, Anna Damulina¹, Maximilian Sackl¹, Martin Soellradl³, Reinhold Schmidt¹, Stefan Ropele¹, and Christian Langkammer¹

¹Department of Neurology, Medical University of Graz, Graz, Austria, ²Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria, ³Institute of Medical Engineering, Graz University of Technology, Graz, Austria

Synopsis

Increased iron deposition in the basal ganglia is a frequent finding in patients with AD. Using R2* maps we separated Alzheimer's patients (n=115) from healthy controls (n=169) by using a deep neural network and systematically investigated the influence of the learned features using an attached relevance map generator. The highest relevances were found in and adjacent to the basal ganglia, which is in line with established histological findings and additionally confirmed by the conventional ROI-based analysis. This study demonstrates the validity of heat mapping as a means to identify novel areas of pathological tissue changes.

This abstract and the presentation materials are available to members only; a login is required.

Join Here