Grounding DINO-US-SAM: Text-Prompted Multiorgan Segmentation in Ultrasound With LoRA-Tuned Vision–Language Models
IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control · 2025-10 · 72 (10) · 1414-1425
DOI: 10.1109/tuffc.2025.3605285 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2025-10. Verfasst von Hamza Rasaee und 2 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery and Government of Canada’s New Frontiers in Research Fund.
Abstract (Originalsprache)
Accurate and generalizable object segmentation in ultrasound imaging remains a significant challenge due to anatomical variability, diverse imaging protocols, and limited annotated data. In this study, we propose a prompt-driven vision-language model (VLM) that integrates grounding DINO with SAM2 to enable object segmentation across multiple ultrasound organs. A total of 18 public ultrasound datasets, encompassing the breast, thyroid, liver, prostate, kidney, and paraspinal muscle, were utilized. These datasets were divided into 15 for fine-tuning and validation of grounding DINO using low-rank adaptation (LoRA) to the ultrasound domain, and three were held out entirely for testing to evaluate performance in unseen distributions. Comprehensive experiments demonstrate that our approach outperforms state-of-the-art (SOTA) segmentation methods, including UniverSeg, MedSAM, MedCLIP-segment anything model (SAM), BiomedParse, and SAMUS on most seen datasets while maintaining strong performance on unseen datasets without additional fine-tuning. These results underscore the promise of VLMs in scalable and robust ultrasound image analysis, reducing dependence on large, organ-specific annotated datasets. We will publish our code on code.sonography.ai after acceptance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery and Government of Canada’s New Frontiers in Research Fund
Zitieren
APA
Rasaee, H., Koleilat, T., & Rivaz, H. (2025). Grounding DINO-US-SAM: Text-Prompted Multiorgan Segmentation in Ultrasound With LoRA-Tuned Vision–Language Models. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 72(10), 1414-1425. https://doi.org/10.1109/tuffc.2025.3605285
Vancouver
Rasaee H, Koleilat T, Rivaz H. Grounding DINO-US-SAM: Text-Prompted Multiorgan Segmentation in Ultrasound With LoRA-Tuned Vision–Language Models. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control. 2025;72(10):1414-1425. doi:10.1109/tuffc.2025.3605285
BibTeX
@article{Rasaee2025,
author = {Rasaee, Hamza and Koleilat, Taha and Rivaz, Hassan},
title = {Grounding DINO-US-SAM: Text-Prompted Multiorgan Segmentation in Ultrasound With LoRA-Tuned Vision–Language Models},
journal = {IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control},
year = {2025},
volume = {72},
number = {10},
pages = {1414--1425},
doi = {10.1109/tuffc.2025.3605285}
}
EUVIMED