DeepAI AI Chat
Log In Sign Up

Testing the robustness of attribution methods for convolutional neural networks in MRI-based Alzheimer's disease classification

by   Fabian Eitel, et al.

Attribution methods are an easy to use tool for investigating and validating machine learning models. Multiple methods have been suggested in the literature and it is not yet clear which method is most suitable for a given task. In this study, we tested the robustness of four attribution methods, namely gradient*input, guided backpropagation, layer-wise relevance propagation and occlusion, for the task of Alzheimer's disease classification. We have repeatedly trained a convolutional neural network (CNN) with identical training settings in order to separate structural MRI data of patients with Alzheimer's disease and healthy controls. Afterwards, we produced attribution maps for each subject in the test data and quantitatively compared them across models and attribution methods. We show that visual comparison is not sufficient and that some widely used attribution methods produce highly inconsistent outcomes.


Baseline Computation for Attribution Methods Based on Interpolated Inputs

We discuss a way to find a well behaved baseline for attribution methods...

CHALLENGER: Training with Attribution Maps

We show that utilizing attribution maps for training neural networks can...

Generating Attribution Maps with Disentangled Masked Backpropagation

Attribution map visualization has arisen as one of the most effective te...

Attribution Preservation in Network Compression for Reliable Network Interpretation

Neural networks embedded in safety-sensitive applications such as self-d...

Feature visualization for convolutional neural network models trained on neuroimaging data

A major prerequisite for the application of machine learning models in c...

Discerning the painter's hand: machine learning on surface topography

Attribution of paintings is a critical problem in art history. This stud...