Article

Vision-Language Foundation Models Do Not Transfer to Medical Imaging Classification: A Negative Result on Chest X-ray Diagnosis

2025-12-08

Abstract excerpt

Vision-language models (VLMs) pretrained on web-scale data have achieved remarkable performance across diverse tasks, leading to widespread adoption in industry. A natural question is whether these powerful representations transfer to specialized medical imaging domains, and whether domain-specific medical pretraining improves transfer. We tested these hypotheses using two VLMs on the NIH ChestX-ray14 benchmark: Q...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: a8fff097-6a15-58bb-87bc-ac57326d9bf1
DOI: 10.64898/2025.12.06.25341759

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Vision-Language Foundation Models Do Not Transfer to Medical Imaging Classification: A Negative Result on Chest X-ray DiagnosisDOI 10.64898/2025.12.06.25341759Read

The NLP-to-Expert Gap in Chest X-ray AISemantic proximity Read

AI-Assisted Pneumonia Detection, Localisation and Report Generation from Chest X-raysSemantic proximity Read

Developing Deep Learning Models for Classifying Medical Imaging DataSemantic proximity Read

Generalizable CT Vision-Language Modeling for Population Health and Disease RiskSemantic proximity Read

A Multimodal Large Language Modelling Deep Learning Framework for the Future PandemicSemantic proximity Read

Merlin: A Vision Language Foundation Model for 3D Computed TomographySemantic proximity Read

Comparative Analysis of Deep Learning Architectures for Multi-Disease Classification of Chest X-raysSemantic proximity Read

Pillar-0: A New Frontier for Radiology Foundation ModelsSemantic proximity Read

Assessing the Impact of Pretraining Domain Relevance on Large Language Models Across Various Pathology Reporting TasksSemantic proximity Read

Self-Supervised Pretraining Enables High-Performance Chest X-Ray Interpretation Across Clinical DistributionsSemantic proximity Read

Pretraining Diversity and Clinical Metric Optimization Achieve State-of-the-Art Performance on ChestX-ray14Semantic proximity Read

An Empirical Evaluation of Low-Rank Adapted Vision–Language Models for Radiology Medical Image CaptioningSemantic proximity Read