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

09/19/2019
by   Fabian Eitel, et al.
0

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.

READ FULL TEXT
research
04/13/2022

Baseline Computation for Attribution Methods Based on Interpolated Inputs

We discuss a way to find a well behaved baseline for attribution methods...
research
05/30/2022

CHALLENGER: Training with Attribution Maps

We show that utilizing attribution maps for training neural networks can...
research
01/17/2021

Generating Attribution Maps with Disentangled Masked Backpropagation

Attribution map visualization has arisen as one of the most effective te...
research
07/22/2022

Deep neural network heatmaps capture Alzheimer's disease patterns reported in a large meta-analysis of neuroimaging studies

Deep neural networks currently provide the most advanced and accurate ma...
research
10/28/2020

Attribution Preservation in Network Compression for Reliable Network Interpretation

Neural networks embedded in safety-sensitive applications such as self-d...
research
03/24/2022

Feature visualization for convolutional neural network models trained on neuroimaging data

A major prerequisite for the application of machine learning models in c...
research
06/14/2021

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

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

Please sign up or login with your details

Forgot password? Click here to reset