# Evaluating Visual Explanations of Attention Maps for Transformer-based Medical Imaging

arXiv: https://arxiv.org/abs/2503.09535 · HTML: https://mlsanity.com/paper/2503.09535/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Towards Expert-Level Medical Question Answering with Large Language Models](https://mlsanity.com/paper/2305.09617/) (2023)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Transformers in Medical Imaging: A Survey](https://mlsanity.com/paper/2201.09873/) (2022)
- [Is it Time to Replace CNNs with Transformers for Medical Images?](https://mlsanity.com/paper/2108.09038/) (2021)
- [Why Attentions May Not Be Interpretable?](https://mlsanity.com/paper/2006.05656/) (2020)
- [Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training](https://mlsanity.com/paper/2305.13689/) (2023)
- [Towards Evaluating Explanations of Vision Transformers for Medical Imaging](https://mlsanity.com/paper/2304.06133/) (2023)
- [The Intrinsic Manifolds of Radiological Images and their Role in Deep Learning](https://mlsanity.com/paper/2207.02797/) (2022)
- [Be Careful When Evaluating Explanations Regarding Ground Truth](https://mlsanity.com/paper/2311.04813/) (2023)
- [Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application](https://mlsanity.com/paper/2211.08543/) (2022)

## Built on by (most cited first, 7 of 7)

- [Generative Artificial Intelligence in Medical Imaging: Foundations, Progress, and Clinical Translation](https://mlsanity.com/paper/2508.09177/) (2025)
- [On the effectiveness of multimodal privileged knowledge distillation in two vision transformer based diagnostic applications](https://mlsanity.com/paper/2508.06558/) (2025)
- [Adaptive Diagnostic Reasoning Framework for Pathology with Multimodal Large Language Models](https://mlsanity.com/paper/2511.12008/) (2025)
- [Towards Affordable Tumor Segmentation and Visualization for 3D Breast MRI Using SAM2](https://mlsanity.com/paper/2507.23272/) (2025)
- [DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification](https://mlsanity.com/paper/2604.07166/) (2026)
- [MedConcept: Unsupervised Concept Discovery for Interpretability in Medical VLMs](https://mlsanity.com/paper/2604.11868/) (2026)
- [Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability](https://mlsanity.com/paper/2608.02238/) (2026)

## Abstract (arXiv)

Although Vision Transformers (ViTs) have recently demonstrated superior performance in medical imaging problems, they face explainability issues similar to previous architectures such as convolutional neural networks. Recent research efforts suggest that attention maps, which are part of decision-making process of ViTs can potentially address the explainability issue by identifying regions influencing predictions, especially in models pretrained with self-supervised learning. In this work, we compare the visual explanations of attention maps to other commonly used methods for medical imaging problems. To do so, we employ four distinct medical imaging datasets that involve the identification of (1) colonic polyps, (2) breast tumors, (3) esophageal inflammation, and (4) bone fractures and hardware implants. Through large-scale experiments on the aforementioned datasets using various supervised and self-supervised pretrained ViTs, we find that although attention maps show promise under certain conditions and generally surpass GradCAM in explainability, they are outperformed by transformer-specific interpretability methods. Our findings indicate that the efficacy of attention maps as a method of interpretability is context-dependent and may be limited as they do not consistently provide the comprehensive insights required for robust medical decision-making.