# XAI-CLIP: ROI-Guided Perturbation Framework for Explainable Medical Image Segmentation in Multimodal Vision-Language Models

arXiv: https://arxiv.org/abs/2602.07017 · HTML: https://mlsanity.com/paper/2602.07017/

## 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 27 of its 48 references that are in the map.
- First posted on arXiv 1 Feb 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, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation](https://mlsanity.com/paper/2001.06535/) (2020)
- [Segment Anything Model for Medical Image Analysis: an Experimental Study](https://mlsanity.com/paper/2304.10517/) (2023)
- [VM-UNet: Vision Mamba UNet for Medical Image Segmentation](https://mlsanity.com/paper/2402.02491/) (2024)
- [Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practice](https://mlsanity.com/paper/1911.01685/) (2019)
- [VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge](https://mlsanity.com/paper/2411.12915/) (2024)
- [UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities](https://mlsanity.com/paper/2412.10372/) (2024)
- [Computer-Vision Benchmark Segment-Anything Model (SAM) in Medical Images: Accuracy in 12 Datasets](https://mlsanity.com/paper/2304.09324/) (2023)
- [UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentation](https://mlsanity.com/paper/2403.20035/) (2024)
- [CLIP in Medical Imaging: A Survey](https://mlsanity.com/paper/2312.07353/) (2023)
- [MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentation](https://mlsanity.com/paper/2409.19483/) (2024)
- [MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detection](https://mlsanity.com/paper/2405.11315/) (2024)
- [BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models](https://mlsanity.com/paper/2411.15232/) (2024)
- [Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation](https://mlsanity.com/paper/2404.06362/) (2024)
- [Learnable Prompting SAM-induced Knowledge Distillation for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2412.13742/) (2024)
- [Labeling instructions matter in biomedical image analysis](https://mlsanity.com/paper/2207.09899/) (2022)
- [Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks](https://mlsanity.com/paper/2410.02331/) (2024)
- [Refining CLIP's Spatial Awareness: A Visual-Centric Perspective](https://mlsanity.com/paper/2504.02328/) (2025)
- [Bi-VLGM : Bi-Level Class-Severity-Aware Vision-Language Graph Matching for Text Guided Medical Image Segmentation](https://mlsanity.com/paper/2305.12231/) (2023)
- [Multidimensional Contrast Limited Adaptive Histogram Equalization](https://mlsanity.com/paper/1906.11355/) (2019)
- [Contrast Limited Adaptive Histogram Equalization (CLAHE) Approach for Enhancement of the Microstructures of Friction Stir Welded Joints](https://mlsanity.com/paper/2109.00886/) (2021)
- [Towards a perturbation-based explanation for medical AI as differentiable programs](https://mlsanity.com/paper/2502.14001/) (2025)

## Abstract (arXiv)

Medical image segmentation is a critical component of clinical workflows, enabling accurate diagnosis, treatment planning, and disease monitoring. However, despite the superior performance of transformer-based models over convolutional architectures, their limited interpretability remains a major obstacle to clinical trust and deployment. Existing explainable artificial intelligence (XAI) techniques, including gradient-based saliency methods and perturbation-based approaches, are often computationally expensive, require numerous forward passes, and frequently produce noisy or anatomically irrelevant explanations. To address these limitations, we propose XAI-CLIP, an ROI-guided perturbation framework that leverages multimodal vision-language model embeddings to localize clinically meaningful anatomical regions and guide the explanation process. By integrating language-informed region localization with medical image segmentation and applying targeted, region-aware perturbations, the proposed method generates clearer, boundary-aware saliency maps while substantially reducing computational overhead. Experiments conducted on the FLARE22 and CHAOS datasets demonstrate that XAI-CLIP achieves up to a 60% reduction in runtime, a 44.6% improvement in dice score, and a 96.7% increase in Intersection-over-Union for occlusion-based explanations compared to conventional perturbation methods. Qualitative results further confirm cleaner and more anatomically consistent attribution maps with fewer artifacts, highlighting that the incorporation of multimodal vision-language representations into perturbation-based XAI frameworks significantly enhances both interpretability and efficiency, thereby enabling transparent and clinically deployable medical image segmentation systems.