# Uncovering convolutional neural network decisions for diagnosing multiple sclerosis on conventional MRI using layer-wise relevance propagation

arXiv: https://arxiv.org/abs/1904.08771 · HTML: https://mlsanity.com/paper/1904.08771/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2019.

## Built on by (most cited first, 21 of 21)

- [Explainable artificial intelligence (XAI) in deep learning-based medical image analysis](https://mlsanity.com/paper/2107.10912/) (2021)
- [Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods](https://mlsanity.com/paper/2111.02398/) (2021)
- [Transfer Learning in Magnetic Resonance Brain Imaging: a Systematic Review](https://mlsanity.com/paper/2102.01530/) (2021)
- [ICAM-reg: Interpretable Classification and Regression with Feature Attribution for Mapping Neurological Phenotypes in Individual Scans](https://mlsanity.com/paper/2103.02561/) (2021)
- [Comparison of fine-tuning strategies for transfer learning in medical image classification](https://mlsanity.com/paper/2406.10050/) (2024)
- [Attention-based Saliency Maps Improve Interpretability of Pneumothorax Classification](https://mlsanity.com/paper/2303.01871/) (2023)
- [Applications of Deep Learning Techniques for Automated Multiple Sclerosis Detection Using Magnetic Resonance Imaging: A Review](https://mlsanity.com/paper/2105.04881/) (2021)
- [Interpretability of Machine Learning Methods Applied to Neuroimaging](https://mlsanity.com/paper/2204.07005/) (2022)
- [Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research](https://mlsanity.com/paper/2301.08525/) (2023)
- [Interpretable Deep Learning for the Remote Characterisation of Ambulation in Multiple Sclerosis using Smartphones](https://mlsanity.com/paper/2103.09171/) (2021)
- [Evaluating saliency methods on artificial data with different background types](https://mlsanity.com/paper/2112.04882/) (2021)
- [A review of handcrafted and deep radiomics in neurological diseases: transitioning from oncology to clinical neuroimaging](https://mlsanity.com/paper/2407.13813/) (2024)
- [Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions](https://mlsanity.com/paper/2602.02560/) (2026)
- [Cortical lesions, central vein sign, and paramagnetic rim lesions in multiple sclerosis: emerging machine learning techniques and future avenues](https://mlsanity.com/paper/2201.07463/) (2022)
- [Brain Structural Saliency Over The Ages](https://mlsanity.com/paper/2202.11690/) (2022)
- [From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP](https://mlsanity.com/paper/2605.11885/) (2026)
- [Deep Joint Learning of Pathological Region Localization and Alzheimer's Disease Diagnosis](https://mlsanity.com/paper/2108.04555/) (2021)
- [Feature visualization for convolutional neural network models trained on neuroimaging data](https://mlsanity.com/paper/2203.13120/) (2022)
- [Unlocking Layer-wise Relevance Propagation for Autoencoders](https://mlsanity.com/paper/2303.11734/) (2023)
- [GAMER-MRIL identifies Disability-Related Brain Changes in Multiple Sclerosis](https://mlsanity.com/paper/2308.07611/) (2023)
- [Skull-stripping induces shortcut learning in MRI-based Alzheimer's disease classification](https://mlsanity.com/paper/2501.15831/) (2025)

## Abstract (arXiv)

Machine learning-based imaging diagnostics has recently reached or even superseded the level of clinical experts in several clinical domains. However, classification decisions of a trained machine learning system are typically non-transparent, a major hindrance for clinical integration, error tracking or knowledge discovery. In this study, we present a transparent deep learning framework relying on convolutional neural networks (CNNs) and layer-wise relevance propagation (LRP) for diagnosing multiple sclerosis (MS). MS is commonly diagnosed utilizing a combination of clinical presentation and conventional magnetic resonance imaging (MRI), specifically the occurrence and presentation of white matter lesions in T2-weighted images. We hypothesized that using LRP in a naive predictive model would enable us to uncover relevant image features that a trained CNN uses for decision-making. Since imaging markers in MS are well-established this would enable us to validate the respective CNN model. First, we pre-trained a CNN on MRI data from the Alzheimer's Disease Neuroimaging Initiative (n = 921), afterwards specializing the CNN to discriminate between MS patients and healthy controls (n = 147). Using LRP, we then produced a heatmap for each subject in the holdout set depicting the voxel-wise relevance for a particular classification decision. The resulting CNN model resulted in a balanced accuracy of 87.04% and an area under the curve of 96.08% in a receiver operating characteristic curve. The subsequent LRP visualization revealed that the CNN model focuses indeed on individual lesions, but also incorporates additional information such as lesion location, non-lesional white matter or gray matter areas such as the thalamus, which are established conventional and advanced MRI markers in MS. We conclude that LRP and the proposed framework have the capability to make diagnostic decisions of...