Generative Models in Medical Visual Question Answering: A Survey
Applied Sciences · 10.03.2025 · 15 (6) · 2983
DOI: 10.3390/app15062983 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 10.03.2025. Verfasst von Wenjie Dong und 5 weiteren Autor:innen. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Zhejiang Key R&D Program of China, Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence.
Abstract (Originalsprache)
Medical Visual Question Answering (MedVQA) is a crucial intersection of artificial intelligence and healthcare. It enables systems to interpret medical images—such as X-rays, MRIs, and pathology slides—and respond to clinical queries. Early approaches primarily relied on discriminative models, which select answers from predefined candidates. However, these methods struggle to effectively address open-ended, domain-specific, or complex queries. Recent advancements have shifted the focus toward generative models, leveraging autoregressive decoders, large language models (LLMs), and multimodal large language models (MLLMs) to generate more nuanced and free-form answers. This review comprehensively examines the paradigm shift from discriminative to generative systems, examining generative MedVQA works on their model architectures and training process, summarizing evaluation benchmarks and metrics, highlighting key advances and techniques that propels the development of generative MedVQA, such as concept alignment, instruction tuning, and parameter-efficient fine-tuning (PEFT), alongside strategies for data augmentation and automated dataset creation. Finally, we propose future directions to enhance clinical reasoning and intepretability, build robust evaluation benchmarks and metrics, and employ scalable training strategies and deployment solutions. By analyzing the strengths and limitations of existing generative MedVQA approaches, we aim to provide valuable insights for researchers and practitioners working in this domain.
Förderung
- National Natural Science Foundation of China
- Zhejiang Key R&D Program of China
- Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence
Zitieren
APA
Dong, W., Shen, S., Han, Y., Tan, T., Wu, J., & Xu, H. (2025). Generative Models in Medical Visual Question Answering: A Survey. Applied Sciences, 15(6), 2983. https://doi.org/10.3390/app15062983
Vancouver
Dong W, Shen S, Han Y, Tan T, Wu J, Xu H. Generative Models in Medical Visual Question Answering: A Survey. Applied Sciences. 2025;15(6):2983. doi:10.3390/app15062983
BibTeX
@article{Dong2025,
author = {Dong, Wenjie and Shen, Shuhao and Han, Yuqiang and Tan, Tao and Wu, Jian and Xu, Hongxia},
title = {Generative Models in Medical Visual Question Answering: A Survey},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {6},
pages = {2983},
doi = {10.3390/app15062983}
}
EUVIMED