# MedConcept: Unsupervised Concept Discovery for Interpretability in Medical VLMs

arXiv: https://arxiv.org/abs/2604.11868 · HTML: https://mlsanity.com/paper/2604.11868/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 10 of 10)

- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)](https://mlsanity.com/paper/2402.10376/) (2024)
- [Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery](https://mlsanity.com/paper/2407.14499/) (2024)
- [Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods](https://mlsanity.com/paper/2111.02398/) (2021)
- [AbdomenAtlas: A Large-Scale, Detailed-Annotated, & Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarking](https://mlsanity.com/paper/2407.16697/) (2024)
- [Towards Evaluating Explanations of Vision Transformers for Medical Imaging](https://mlsanity.com/paper/2304.06133/) (2023)
- [Sparse Autoencoder Features for Classifications and Transferability](https://mlsanity.com/paper/2502.11367/) (2025)
- [Learning Segmentation from Radiology Reports](https://mlsanity.com/paper/2507.05582/) (2025)
- [CytoSAE: Interpretable Cell Embeddings for Hematology](https://mlsanity.com/paper/2507.12464/) (2025)
- [Evaluating Visual Explanations of Attention Maps for Transformer-based Medical Imaging](https://mlsanity.com/paper/2503.09535/) (2025)

## Abstract (arXiv)

While medical Vision-Language models (VLMs) achieve strong performance on tasks such as tumor or organ segmentation and diagnosis prediction, their opaque latent representations limit clinical trust and the ability to explain predictions. Interpretability of these multimodal representations are therefore essential for the trustworthy clinical deployment of pretrained medical VLMs. However, current interpretability methods, such as gradient- or attention-based visualizations, are often limited to specific tasks such as classification. Moreover, they do not provide concept-level explanations derived from shared pretrained representations that can be reused across downstream tasks. We introduce MedConcept, a framework that uncovers latent medical concepts in a fully unsupervised manner and grounds them in clinically verifiable textual semantics. MedConcept identifies sparse neuron-level concept activations from pretrained VLM representations and translates them into pseudo-report-style summaries, enabling physician-level inspection of internal model reasoning. To address the lack of quantitative evaluation in concept-based interpretability, we introduce a quantitative semantic verification protocol that leverages an independent pretrained medical LLM as a frozen external evaluator to assess concept alignment with radiology reports. We define three concept scores, Aligned, Unaligned, and Uncertain, to quantify semantic support, contradiction, or ambiguity relative to radiology reports and use them exclusively for post hoc evaluation. These scores provide a quantitative baseline for assessing interpretability in medical VLMs. All codes, prompt and data to be released on acceptance. Ke