UniUltra: Interactive Parameter-Efficient SAM2 for Universal Ultrasound Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yue, Xu, Qing, Zhang, Yixuan, He, Xiangjian, Zhang, Qian, Yao, Yuan, Tesem, Fiseha B., Chen, Xin, Wang, Ruili, Chen, Zhen, Chen, Chang Wen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915627321524224
author Li, Yue
Xu, Qing
Zhang, Yixuan
He, Xiangjian
Zhang, Qian
Yao, Yuan
Tesem, Fiseha B.
Chen, Xin
Wang, Ruili
Chen, Zhen
Chen, Chang Wen
author_facet Li, Yue
Xu, Qing
Zhang, Yixuan
He, Xiangjian
Zhang, Qian
Yao, Yuan
Tesem, Fiseha B.
Chen, Xin
Wang, Ruili
Chen, Zhen
Chen, Chang Wen
contents The Segment Anything Model 2 (SAM2) demonstrates remarkable universal segmentation capabilities on natural images. However, its performance on ultrasound images is significantly degraded due to domain disparities. This limitation raises two critical challenges: how to efficiently adapt SAM2 to ultrasound imaging while maintaining parameter efficiency, and how to deploy the adapted model effectively in resource-constrained clinical environments. To address these issues, we propose UniUltra for universal ultrasound segmentation. Specifically, we first introduce a novel context-edge hybrid adapter (CH-Adapter) that enhances fine-grained perception across diverse ultrasound imaging modalities while achieving parameter-efficient fine-tuning. To further improve clinical applicability, we develop a deep-supervised knowledge distillation (DSKD) technique that transfers knowledge from the large image encoder of the fine-tuned SAM2 to a super lightweight encoder, substantially reducing computational requirements without compromising performance. Extensive experiments demonstrate that UniUltra outperforms state-of-the-arts with superior generalization capabilities. Notably, our framework achieves competitive performance using only 8.91% of SAM2's parameters during fine-tuning, and the final compressed model reduces the parameter count by 94.08% compared to the original SAM2, making it highly suitable for practical clinical deployment. The source code is available at https://github.com/xq141839/UniUltra.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15771
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniUltra: Interactive Parameter-Efficient SAM2 for Universal Ultrasound Segmentation
Li, Yue
Xu, Qing
Zhang, Yixuan
He, Xiangjian
Zhang, Qian
Yao, Yuan
Tesem, Fiseha B.
Chen, Xin
Wang, Ruili
Chen, Zhen
Chen, Chang Wen
Image and Video Processing
Computer Vision and Pattern Recognition
The Segment Anything Model 2 (SAM2) demonstrates remarkable universal segmentation capabilities on natural images. However, its performance on ultrasound images is significantly degraded due to domain disparities. This limitation raises two critical challenges: how to efficiently adapt SAM2 to ultrasound imaging while maintaining parameter efficiency, and how to deploy the adapted model effectively in resource-constrained clinical environments. To address these issues, we propose UniUltra for universal ultrasound segmentation. Specifically, we first introduce a novel context-edge hybrid adapter (CH-Adapter) that enhances fine-grained perception across diverse ultrasound imaging modalities while achieving parameter-efficient fine-tuning. To further improve clinical applicability, we develop a deep-supervised knowledge distillation (DSKD) technique that transfers knowledge from the large image encoder of the fine-tuned SAM2 to a super lightweight encoder, substantially reducing computational requirements without compromising performance. Extensive experiments demonstrate that UniUltra outperforms state-of-the-arts with superior generalization capabilities. Notably, our framework achieves competitive performance using only 8.91% of SAM2's parameters during fine-tuning, and the final compressed model reduces the parameter count by 94.08% compared to the original SAM2, making it highly suitable for practical clinical deployment. The source code is available at https://github.com/xq141839/UniUltra.
title UniUltra: Interactive Parameter-Efficient SAM2 for Universal Ultrasound Segmentation
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.15771