Grounding DINO-US-SAM: Text-Prompted Multi-Organ Segmentation in Ultrasound with LoRA-Tuned Vision-Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916940132384768 |
|---|---|
| author | Rasaee, Hamza Koleilat, Taha Rivaz, Hassan |
| author_facet | Rasaee, Hamza Koleilat, Taha Rivaz, Hassan |
| contents | 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 (Segment Anything Model2) 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 3 were held out entirely for testing to evaluate performance in unseen distributions. Comprehensive experiments demonstrate that our approach outperforms state-of-the-art segmentation methods, including UniverSeg, MedSAM, MedCLIP-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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23903 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Grounding DINO-US-SAM: Text-Prompted Multi-Organ Segmentation in Ultrasound with LoRA-Tuned Vision-Language Models Rasaee, Hamza Koleilat, Taha Rivaz, Hassan Computer Vision and Pattern Recognition Artificial Intelligence 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 (Segment Anything Model2) 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 3 were held out entirely for testing to evaluate performance in unseen distributions. Comprehensive experiments demonstrate that our approach outperforms state-of-the-art segmentation methods, including UniverSeg, MedSAM, MedCLIP-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. |
| title | Grounding DINO-US-SAM: Text-Prompted Multi-Organ Segmentation in Ultrasound with LoRA-Tuned Vision-Language Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2506.23903 |