# Visual Prompt Engineering for Vision Language Models in Radiology

arXiv: https://arxiv.org/abs/2408.15802 · HTML: https://mlsanity.com/paper/2408.15802/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 28 Aug 2024.

## Placed in

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

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations](https://mlsanity.com/paper/2012.15029/) (2020)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents](https://mlsanity.com/paper/2303.07240/) (2023)
- [Metrics reloaded: Recommendations for image analysis validation](https://mlsanity.com/paper/2206.01653/) (2022)
- [Alpha-CLIP: A CLIP Model Focusing on Wherever You Want](https://mlsanity.com/paper/2312.03818/) (2023)
- [Fine-Grained Visual Prompting](https://mlsanity.com/paper/2306.04356/) (2023)
- [MedICaT: A Dataset of Medical Images, Captions, and Textual References](https://mlsanity.com/paper/2010.06000/) (2020)
- [Multimodal Healthcare AI: Identifying and Designing Clinically Relevant Vision-Language Applications for Radiology](https://mlsanity.com/paper/2402.14252/) (2024)
- [LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity](https://mlsanity.com/paper/2404.03214/) (2024)
- [Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge](https://mlsanity.com/paper/2310.16112/) (2023)

## Built on by (most cited first, 6 of 6)

- [LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding](https://mlsanity.com/paper/2508.01617/) (2025)
- [MAIRA-Seg: Enhancing Radiology Report Generation with Segmentation-Aware Multimodal Large Language Models](https://mlsanity.com/paper/2411.11362/) (2024)
- [CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generation](https://mlsanity.com/paper/2604.10410/) (2026)
- [Data-Efficient Fine-Tuning of Vision-Language Models for Diagnosis of Alzheimer's Disease](https://mlsanity.com/paper/2509.07613/) (2025)
- [Med-VRAgent: A Framework for Medical Visual Reasoning-Enhanced Agents](https://mlsanity.com/paper/2510.18424/) (2025)
- [Improving Medical Visual Reinforcement Fine-Tuning via Perception and Reasoning Augmentation](https://mlsanity.com/paper/2602.10619/) (2026)

## Abstract (arXiv)

Medical image classification plays a crucial role in clinical decision-making, yet most models are constrained to a fixed set of predefined classes, limiting their adaptability to new conditions. Contrastive Language-Image Pretraining (CLIP) offers a promising solution by enabling zero-shot classification through multimodal large-scale pretraining. However, while CLIP effectively captures global image content, radiology requires a more localized focus on specific pathology regions to enhance both interpretability and diagnostic accuracy. To address this, we explore the potential of incorporating visual cues into zero-shot classification, embedding visual markers, such as arrows, bounding boxes, and circles, directly into radiological images to guide model attention. Evaluating across four public chest X-ray datasets, we demonstrate that visual markers improve AUROC by up to 0.185, highlighting their effectiveness in enhancing classification performance. Furthermore, attention map analysis confirms that visual cues help models focus on clinically relevant areas, leading to more interpretable predictions.To support further research, we use public datasets and provide our codebase and preprocessing pipeline under https://github.com/MIC-DKFZ/VPE-in-Radiology, serving as a reference point for future work on localized classification in medical imaging.