EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Medical Vision-Language Models: Existing Technologies, Clinical Applications and Future Directions

Le Zou iD, Mengyu Ma iD, Jun Li, Hao Chen iD, Shuang Peng iD

Sensors · 24.06.2026 · 26 (13) · 3998

DOI: 10.3390/s26133998 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 24.06.2026. Verfasst von Le Zou und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronic Science and Technology, National University of Defense Technology, No. 109 Deya Road, Kaifu District, Changsha 410073, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Language. Die Arbeit nennt 167 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Medical image analysis is a cornerstone of modern healthcare, yet conventional single-modal deep learning often struggles with the unique physical constraints and structural variability inherent in data acquired from diverse medical sensors. Recently, Vision-Language Models (VLMs) have sparked a paradigm shift by bridging the semantic gap between visual sensor signals and clinical narratives. Following the PRISMA guidelines, 167 representative studies are systematically synthesized in this review to provide a comprehensive roadmap of VLM technological evolution and clinical utility. First, rather than treating VLMs as generic feature extractors, their underlying mechanisms are uniquely distilled into seven core operational principles, which are then explicitly mapped to downstream applications such as few-shot diagnosis, prompt-driven segmentation, and multi-task foundation models. To facilitate intuitive evaluation, a rigorous quantitative cross-comparison of current benchmark architectures is presented. Crucially, this review goes beyond highlighting successes by critically assessing prevalent clinical bottlenecks, including zero-shot segmentation failures, multi-modal hallucinations in diagnosing rare diseases, and the prohibitive computational complexity associated with 3D volumes and gigapixel whole slide images. Finally, a novel, forward-looking framework is proposed: the transition from static “image-text alignment” to dynamic “multi-source sensor-driven intelligence”. By addressing both physical sensor constraints and algorithmic limitations, this survey offers actionable insights for developing trustworthy, sensor-aware clinical diagnostic agents.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedLanguageHumansDeep Learning

Stichwörter der Autor:innen

artificial intelligenceclinical applicationmedical image analysismulti-modal learningvision-language model

Autor:innen und Institutionen

  • College of Electronic Science and Technology, National University of Defense Technology, No. 109 Deya Road, Kaifu District, Changsha 410073, China.

ORCID-Profile: Le Zou, Mengyu Ma, Hao Chen, Shuang Peng

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zou, L., Ma, M., Li, J., Chen, H., & Peng, S. (2026). Medical Vision-Language Models: Existing Technologies, Clinical Applications and Future Directions. Sensors, 26(13), 3998. https://doi.org/10.3390/s26133998

Vancouver

Zou L, Ma M, Li J, Chen H, Peng S. Medical Vision-Language Models: Existing Technologies, Clinical Applications and Future Directions. Sensors. 2026;26(13):3998. doi:10.3390/s26133998

BibTeX
@article{Zou2026,
  author = {Zou, Le and Ma, Mengyu and Li, Jun and Chen, Hao and Peng, Shuang},
  title = {Medical Vision-Language Models: Existing Technologies, Clinical Applications and Future Directions},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {13},
  pages = {3998},
  doi = {10.3390/s26133998}
}
Kostenlos starten →