# What are You Looking at? Modality Contribution in Multimodal Medical Deep Learning

arXiv: https://arxiv.org/abs/2503.01904 · HTML: https://mlsanity.com/paper/2503.01904/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [Multimodal Deep Learning](https://mlsanity.com/paper/2301.04856/) (2023)
- [MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks](https://mlsanity.com/paper/2212.08158/) (2022)
- [Perceptual Score: What Data Modalities Does Your Model Perceive?](https://mlsanity.com/paper/2110.14375/) (2021)
- [Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?](https://mlsanity.com/paper/2203.06487/) (2022)
- [SHAPE: An Unified Approach to Evaluate the Contribution and Cooperation of Individual Modalities](https://mlsanity.com/paper/2205.00302/) (2022)
- [Defoiling Foiled Image Captions](https://mlsanity.com/paper/1805.06549/) (2018)
- [Multimodal Learning for Cardiovascular Risk Prediction using EHR Data](https://mlsanity.com/paper/2008.11979/) (2020)
- [Multimodal Medical Disease Classification with LLaMA II](https://mlsanity.com/paper/2412.01306/) (2024)

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

- [XSRD-Net: EXplainable Stroke Relapse Detection](https://mlsanity.com/paper/2509.07772/) (2025)
- [Enabling Vision and Cross-Modal Learning for Multimodal Stroke Recurrence Prediction: An Interpretable Two-Step Framework](https://mlsanity.com/paper/2609.22271/) (2026)

## Abstract (arXiv)

Purpose High dimensional, multimodal data can nowadays be analyzed by huge deep neural networks with little effort. Several fusion methods for bringing together different modalities have been developed. Given the prevalence of high-dimensional, multimodal patient data in medicine, the development of multimodal models marks a significant advancement. However, how these models process information from individual sources in detail is still underexplored. Methods To this end, we implemented an occlusion-based modality contribution method that is both model- and performance-agnostic. This method quantitatively measures the importance of each modality in the dataset for the model to fulfill its task. We applied our method to three different multimodal medical problems for experimental purposes. Results Herein we found that some networks have modality preferences that tend to unimodal collapses, while some datasets are imbalanced from the ground up. Moreover, we provide fine-grained quantitative and visual attribute importance for each modality. Conclusion Our metric offers valuable insights that can support the advancement of multimodal model development and dataset creation. By introducing this method, we contribute to the growing field of interpretability in deep learning for multimodal research. This approach helps to facilitate the integration of multimodal AI into clinical practice. Our code is publicly available at https://github.com/ChristianGappGit/MC_MMD.