Language-Guided Segmentation of Medical Images: A Review of Foundation Models
Bioengineering · 13.07.2026 · 13 (7) · 803
DOI: 10.3390/bioengineering13070803 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Bioengineering, online erschienen am 13.07.2026. Verfasst von Saqib Qamar. Beteiligte Einrichtung: Department of Intelligent Systems, KTH Royal Institute of Technology, 10044 Stockholm, Sweden. Die Arbeit nennt 194 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Vision-language foundation models have transformed medical image segmentation over the past three years. These models pair large image encoders with text prompts, so a single model can segment many anatomical structures, lesion types, and imaging modalities through natural language. This survey reviews vision-language foundation models designed for medical image segmentation. We describe the technical background from contrastive vision-language pretraining to the Segment Anything Model and its medical variants. We propose a three-part taxonomy that covers text-prompt-guided models, large-language-model-embedded architectures, and hybrid frameworks. We examine adaptation strategies such as full fine-tuning, Low-Rank Adaptation, adapters, and prompt engineering. We organize the literature by modality and cover computed tomography, magnetic resonance imaging, pathology, chest radiography, and ultrasound. We discuss clinical uses such as organ segmentation, tumor delineation, and radiotherapy planning. We summarize evaluation metrics and benchmark datasets. We identify four open challenges: prompt dependence, mask hallucination, slow volumetric inference, and limited annotated data. We close with a research roadmap for trustworthy deployment, multimodal pretraining, and clinical integration.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Intelligent Systems, KTH Royal Institute of Technology, 10044 Stockholm, Sweden.
- Faculty of Computing and Information Technology (FCIT), Sohar University, Sohar 311, Oman.
ORCID-Profile: Saqib Qamar
Zitieren
APA
Qamar, S. (2026). Language-Guided Segmentation of Medical Images: A Review of Foundation Models. Bioengineering, 13(7), 803. https://doi.org/10.3390/bioengineering13070803
Vancouver
Qamar S. Language-Guided Segmentation of Medical Images: A Review of Foundation Models. Bioengineering. 2026;13(7):803. doi:10.3390/bioengineering13070803
BibTeX
@article{Qamar2026,
author = {Qamar, Saqib},
title = {Language-Guided Segmentation of Medical Images: A Review of Foundation Models},
journal = {Bioengineering},
year = {2026},
volume = {13},
number = {7},
pages = {803},
doi = {10.3390/bioengineering13070803}
}
EUVIMED