Salvato in:
Dettagli Bibliografici
Autori principali: Alsinglawi, Belal, McCarthy, Chris, Webb, Sara, Fluke, Christopher, Saidy, Navid Toosy
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2504.05575
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909571219456000
author Alsinglawi, Belal
McCarthy, Chris
Webb, Sara
Fluke, Christopher
Saidy, Navid Toosy
author_facet Alsinglawi, Belal
McCarthy, Chris
Webb, Sara
Fluke, Christopher
Saidy, Navid Toosy
contents Medical Visual Question Answering (VQA) enhances clinical decision-making by enabling systems to interpret medical images and answer clinical queries. However, developing efficient, high-performance VQA models is challenging due to the complexity of medical imagery and diverse modalities. In this paper, we introduce a lightweight, multimodal VQA model integrating BiomedCLIP for image feature extraction and LLaMA-3 for text processing. Designed for medical VQA tasks, our model achieves state-of-the-art performance on the OmniMedVQA dataset. With approximately 8 billion parameters, it requires only two NVIDIA 40 GB A100 GPUs, demonstrating superior efficiency over larger models. Our results show 73.4% accuracy for open-end questions, surpassing existing models and validating its potential for real-world medical applications. Key contributions include a specialized multimodal VQA model, a resource-efficient architecture, and strong performance in answering open-ended clinical questions.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05575
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Lightweight Large Vision-language Model for Multimodal Medical Images
Alsinglawi, Belal
McCarthy, Chris
Webb, Sara
Fluke, Christopher
Saidy, Navid Toosy
Computer Vision and Pattern Recognition
Machine Learning
Medical Visual Question Answering (VQA) enhances clinical decision-making by enabling systems to interpret medical images and answer clinical queries. However, developing efficient, high-performance VQA models is challenging due to the complexity of medical imagery and diverse modalities. In this paper, we introduce a lightweight, multimodal VQA model integrating BiomedCLIP for image feature extraction and LLaMA-3 for text processing. Designed for medical VQA tasks, our model achieves state-of-the-art performance on the OmniMedVQA dataset. With approximately 8 billion parameters, it requires only two NVIDIA 40 GB A100 GPUs, demonstrating superior efficiency over larger models. Our results show 73.4% accuracy for open-end questions, surpassing existing models and validating its potential for real-world medical applications. Key contributions include a specialized multimodal VQA model, a resource-efficient architecture, and strong performance in answering open-ended clinical questions.
title A Lightweight Large Vision-language Model for Multimodal Medical Images
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2504.05575