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

Source: [XAI-CLIP: ROI-Guided Perturbation Framework for Explainable Medical Image Segmentation in Multimodal Vision-Language Models](<https://www.sota2.com/research/paper/698abba8c97a0b3e3b5ddfec>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-11T05:00:04.178Z

Authors: Thuraya Alzubaidi, Sana Ammar, Maryam Alsharqi, Islem Rekik, Muzammil Behzad

Published: 2026-02-01T00:27:06.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Medical Image Segmentation Explainability Evaluation on FLARE 2022](<https://www.sota2.com/research/sota/medical-image-segmentation-explainability-evaluation-on-flare-2022.md>): Medical Image Segmentation Explainability Evaluation; FLARE 2022; GFLOPs: 94431.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.07017>)

[PDF](<https://arxiv.org/pdf/2602.07017.pdf>)
