Prototype-Guided Zero-Shot Medical Image Segmentation with Large Vision-Language Models
Applied Sciences · 26.10.2025 · 15 (21) · 11441
DOI: 10.3390/app152111441 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 26.10.2025. Verfasst von Huong Pham und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Vice President for Research and Partnerhsips, the Data Institute for Societal Challenges, and the Stephenson Cancer Center at the University of Oklahoma.
Abstract (Originalsprache)
Building on advances in promptable segmentation models, this work introduces a framework that integrates Large Vision-Language Model (LVLM) bounding box priors with prototype-based region of interest (ROI) selection to improve zero-shot medical image segmentation. Unlike prior methods such as SaLIP, which often misidentify regions due to reliance on text–image CLIP similarity, the proposed approach leverages visual prototypes to mitigate language bias and enhance ROI ranking, resulting in more accurate segmentation. Bounding box estimation is further strengthened through systematic prompt engineering to optimize LVLM performance across diverse datasets and imaging modalities. Evaluation was conducted on three publicly available benchmark datasets—CC359 (brain MRI), HC18 (fetal head ultrasound), and CXRMAL (chest X-ray)—without any task-specific fine-tuning. The proposed method achieved substantial improvements over prior approaches. On CC359, it reached a Dice score of 0.95 ± 0.06 and a mean Intersection-over-Union (mIoU) of 0.91 ± 0.10. On HC18, it attained a Dice score of 0.82 ± 0.20 and mIoU of 0.74 ± 0.22. On CXRMAL, the model achieved a Dice score of 0.90 ± 0.08 and mIoU of 0.83 ± 0.12. These standard deviations reflect variability across test images within each dataset, indicating the robustness of the proposed zero-shot framework. These results demonstrate that integrating LVLM-derived bounding box priors with prototype-based selection substantially advances zero-shot medical image segmentation.
Förderung
- Vice President for Research and Partnerhsips, the Data Institute for Societal Challenges, and the Stephenson Cancer Center at the University of Oklahoma
Zitieren
APA
Pham, H., & Cheng, S. (2025). Prototype-Guided Zero-Shot Medical Image Segmentation with Large Vision-Language Models. Applied Sciences, 15(21), 11441. https://doi.org/10.3390/app152111441
Vancouver
Pham H, Cheng S. Prototype-Guided Zero-Shot Medical Image Segmentation with Large Vision-Language Models. Applied Sciences. 2025;15(21):11441. doi:10.3390/app152111441
BibTeX
@article{Pham2025,
author = {Pham, Huong and Cheng, Samuel},
title = {Prototype-Guided Zero-Shot Medical Image Segmentation with Large Vision-Language Models},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {21},
pages = {11441},
doi = {10.3390/app152111441}
}
EUVIMED