# Explainable concept mappings of MRI: Revealing the mechanisms underlying deep learning-based brain disease classification

arXiv: https://arxiv.org/abs/2404.10433 · HTML: https://mlsanity.com/paper/2404.10433/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 24 references that are in the map.
- First posted on arXiv 16 Apr 2024.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Explaining NonLinear Classification Decisions with Deep Taylor Decomposition](https://mlsanity.com/paper/1512.02479/) (2015)
- [Accounting for Variance in Machine Learning Benchmarks](https://mlsanity.com/paper/2103.03098/) (2021)
- [From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation](https://mlsanity.com/paper/2206.03208/) (2022)
- [Deep neural network heatmaps capture Alzheimer's disease patterns reported in a large meta-analysis of neuroimaging studies](https://mlsanity.com/paper/2207.11352/) (2022)

## Built on by (most cited first, 2 of 2)

- [Skull-stripping induces shortcut learning in MRI-based Alzheimer's disease classification](https://mlsanity.com/paper/2501.15831/) (2025)
- [Identifying Alzheimer's Disease Prediction Strategies of Convolutional Neural Network Classifiers using R2* Maps and Spectral Clustering](https://mlsanity.com/paper/2506.03890/) (2025)

## Abstract (arXiv)

Motivation. While recent studies show high accuracy in the classification of Alzheimer's disease using deep neural networks, the underlying learned concepts have not been investigated. Goals. To systematically identify changes in brain regions through concepts learned by the deep neural network for model validation. Approach. Using quantitative R2* maps we separated Alzheimer's patients (n=117) from normal controls (n=219) by using a convolutional neural network and systematically investigated the learned concepts using Concept Relevance Propagation and compared these results to a conventional region of interest-based analysis. Results. In line with established histological findings and the region of interest-based analyses, highly relevant concepts were primarily found in and adjacent to the basal ganglia. Impact. The identification of concepts learned by deep neural networks for disease classification enables validation of the models and could potentially improve reliability.