On the Robustness of Medical Vision-Language Models: Are they Truly Generalizable?

• URL: http://arxiv.org/abs/2505.15425v2
• Date: Fri, 23 May 2025 14:16:48 GMT
• Title: On the Robustness of Medical Vision-Language Models: Are they Truly Generalizable?
• Authors: Raza Imam, Rufael Marew, Mohammad Yaqub,
• Abstract summary: We introduce MediMeta-C, a corruption benchmark that applies several perturbations across multiple medical imaging datasets.<n>We propose RobustMedCLIP, a visual encoder adaptation of a pretrained MVLM that incorporates few-shot tuning to enhance resilience against corruptions.
• Score: 0.9626666671366837
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Medical Vision-Language Models (MVLMs) have achieved par excellence generalization in medical image analysis, yet their performance under noisy, corrupted conditions remains largely untested. Clinical imaging is inherently susceptible to acquisition artifacts and noise; however, existing evaluations predominantly assess generally clean datasets, overlooking robustness -- i.e., the model's ability to perform under real-world distortions. To address this gap, we first introduce MediMeta-C, a corruption benchmark that systematically applies several perturbations across multiple medical imaging datasets. Combined with MedMNIST-C, this establishes a comprehensive robustness evaluation framework for MVLMs. We further propose RobustMedCLIP, a visual encoder adaptation of a pretrained MVLM that incorporates few-shot tuning to enhance resilience against corruptions. Through extensive experiments, we benchmark 5 major MVLMs across 5 medical imaging modalities, revealing that existing models exhibit severe degradation under corruption and struggle with domain-modality tradeoffs. Our findings highlight the necessity of diverse training and robust adaptation strategies, demonstrating that efficient low-rank adaptation when paired with few-shot tuning, improves robustness while preserving generalization across modalities.

Related papers

• Multimodal Causal-Driven Representation Learning for Generalizable Medical Image Segmentation [56.52520416420957]
  We propose Multimodal Causal-Driven Representation Learning (MCDRL) to tackle domain generalization in medical image segmentation.<n>MCDRL consistently outperforms competing methods, yielding superior segmentation accuracy and exhibiting robust generalizability.
  arXiv  Detail & Related papers  (2025-08-07T03:41:41Z)
• Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models [52.2001050216955]
  Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning.<n>We propose an expert-in-the-loop framework named Expert-Controlled-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training.
  arXiv  Detail & Related papers  (2025-07-12T09:03:30Z)
• PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation Learning [3.771396977579353]
  PRETI is a retinal foundation model that integrates metadata-aware learning with robust self-supervised representation learning.<n>We construct patient-level data pairs, associating images from the same individual to improve robustness against non-clinical variations.<n>Experiments demonstrate PRETI achieves state-of-the-art results across diverse diseases and biomarker predictions.
  arXiv  Detail & Related papers  (2025-05-18T04:59:03Z)
• Metrics that matter: Evaluating image quality metrics for medical image generation [48.85783422900129]
  This study comprehensively assesses commonly used no-reference image quality metrics using brain MRI data.<n>We evaluate metric sensitivity to a range of challenges, including noise, distribution shifts, and, critically, morphological alterations designed to mimic clinically relevant inaccuracies.
  arXiv  Detail & Related papers  (2025-05-12T01:57:25Z)
• Benchmarking Robustness of Contrastive Learning Models for Medical Image-Report Retrieval [2.9801426627439453]
  This study benchmarks the robustness of four state-of-the-art contrastive learning models: CLIP, CXR-RePaiR, MedCLIP, and CXR-CLIP.<n>Our findings reveal that all evaluated models are highly sensitive to out-of-distribution data.<n>By addressing these limitations, we can develop more reliable cross-domain retrieval models for medical applications.
  arXiv  Detail & Related papers  (2025-01-15T20:37:04Z)
• Scalable Drift Monitoring in Medical Imaging AI [37.1899538374058]
  We develop MMC+, an enhanced framework for scalable drift monitoring. It builds upon the CheXstray framework that introduced real-time drift detection for medical imaging AI models. MMC+ offers a reliable and cost-effective alternative to continuous performance monitoring.
  arXiv  Detail & Related papers  (2024-10-17T02:57:35Z)
• MedMNIST-C: Comprehensive benchmark and improved classifier robustness by simulating realistic image corruptions [0.13108652488669734]
  integration of neural-network-based systems into clinical practice is limited by challenges related to domain generalization and robustness. We create and open-source MedMNIST-C, a benchmark dataset based on the MedMNIST+ collection covering 12 datasets and 9 imaging modalities.
  arXiv  Detail & Related papers  (2024-06-25T13:20:39Z)
• Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images [68.42215385041114]
  This paper introduces a novel lightweight multi-level adaptation and comparison framework to repurpose the CLIP model for medical anomaly detection. Our approach integrates multiple residual adapters into the pre-trained visual encoder, enabling a stepwise enhancement of visual features across different levels. Our experiments on medical anomaly detection benchmarks demonstrate that our method significantly surpasses current state-of-the-art models.
  arXiv  Detail & Related papers  (2024-03-19T09:28:19Z)
• COMPRER: A Multimodal Multi-Objective Pretraining Framework for Enhanced Medical Image Representation [1.5749416770494706]
  COMPRER is a novel multi-modal, multi-objective pretraining framework. It enhances medical-image representation, diagnostic inferences, and prognosis of diseases.
  arXiv  Detail & Related papers  (2024-02-04T08:05:58Z)
• C^2M-DoT: Cross-modal consistent multi-view medical report generation with domain transfer network [67.97926983664676]
  We propose a cross-modal consistent multi-view medical report generation with a domain transfer network (C2M-DoT) C2M-DoT substantially outperforms state-of-the-art baselines in all metrics.
  arXiv  Detail & Related papers  (2023-10-09T02:31:36Z)
• On Sensitivity and Robustness of Normalization Schemes to Input Distribution Shifts in Automatic MR Image Diagnosis [58.634791552376235]
  Deep Learning (DL) models have achieved state-of-the-art performance in diagnosing multiple diseases using reconstructed images as input. DL models are sensitive to varying artifacts as it leads to changes in the input data distribution between the training and testing phases. We propose to use other normalization techniques, such as Group Normalization and Layer Normalization, to inject robustness into model performance against varying image artifacts.
  arXiv  Detail & Related papers  (2023-06-23T03:09:03Z)
• LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching [59.01894976615714]
  We introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets. We have collected approximately 1.3 million medical images from 55 publicly available datasets. LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models.
  arXiv  Detail & Related papers  (2023-06-20T22:21:34Z)
• Malignancy Prediction and Lesion Identification from Clinical Dermatological Images [65.1629311281062]
  We consider machine-learning-based malignancy prediction and lesion identification from clinical dermatological images. We first identify all lesions present in the image regardless of sub-type or likelihood of malignancy, then it estimates their likelihood of malignancy, and through aggregation, it also generates an image-level likelihood of malignancy.
  arXiv  Detail & Related papers  (2021-04-02T20:52:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.