Saved in:
Bibliographic Details
Main Authors: Xiao, Ruiqiang, Xing, Zhaohu, Yang, Yijun, Han, Zhenyan, Wang, Weiming, Wu, Kaishun, Zhu, Lei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.25944
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916044872876032
author Xiao, Ruiqiang
Xing, Zhaohu
Yang, Yijun
Han, Zhenyan
Wang, Weiming
Wu, Kaishun
Zhu, Lei
author_facet Xiao, Ruiqiang
Xing, Zhaohu
Yang, Yijun
Han, Zhenyan
Wang, Weiming
Wu, Kaishun
Zhu, Lei
contents Ultrasound video segmentation is clinically valuable yet difficult due to speckle noise, weak boundaries, and rapid anatomical deformation. Recent promptable foundation models enable point-guided segmentation, but their direct deployment in ultrasound remains unreliable: a single point provides insufficient spatial context to resolve scale ambiguity, and greedy memory updates amplify early errors into severe temporal drift. We present EchoPilot, a training-free framework for ultrasound video segmentation under sparse first-frame interaction, requiring only a single point click and an anatomical category name. EchoPilot orchestrates a frozen medical vision-language model (VLM) for semantic localization, a vision foundation model (VFM) for dense geometric feature extraction, and a promptable video segmentor for mask prediction and propagation. To resolve initialization ambiguity, we propose Scale-Space Semantic Prompting, which first selects an optimal contextual view via a parameter-free S.E.E.D. (Semantic Energy-Entropy Density) criterion, and then synthesizes geometrically precise auxiliary point prompts from dense foundation features without additional user interaction. To reduce propagation drift, a Reliability-Gated Memory update is further introduced to selectively freeze the segmentor's memory bank under uncertain predictions, preventing error accumulation. We also contribute the first dynamic fetal placenta ultrasound video segmentation dataset with 671 annotated frames. Across three ultrasound video datasets, EchoPilot achieves state-of-the-art performance under the sparse-interactive setting, consistently outperforming training-free baselines and finetuned specialists.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25944
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EchoPilot: Training-Free Ultrasound Video Segmentation via Scale-Space Semantic Prompting and Reliability-Gated Memory
Xiao, Ruiqiang
Xing, Zhaohu
Yang, Yijun
Han, Zhenyan
Wang, Weiming
Wu, Kaishun
Zhu, Lei
Computer Vision and Pattern Recognition
Artificial Intelligence
Ultrasound video segmentation is clinically valuable yet difficult due to speckle noise, weak boundaries, and rapid anatomical deformation. Recent promptable foundation models enable point-guided segmentation, but their direct deployment in ultrasound remains unreliable: a single point provides insufficient spatial context to resolve scale ambiguity, and greedy memory updates amplify early errors into severe temporal drift. We present EchoPilot, a training-free framework for ultrasound video segmentation under sparse first-frame interaction, requiring only a single point click and an anatomical category name. EchoPilot orchestrates a frozen medical vision-language model (VLM) for semantic localization, a vision foundation model (VFM) for dense geometric feature extraction, and a promptable video segmentor for mask prediction and propagation. To resolve initialization ambiguity, we propose Scale-Space Semantic Prompting, which first selects an optimal contextual view via a parameter-free S.E.E.D. (Semantic Energy-Entropy Density) criterion, and then synthesizes geometrically precise auxiliary point prompts from dense foundation features without additional user interaction. To reduce propagation drift, a Reliability-Gated Memory update is further introduced to selectively freeze the segmentor's memory bank under uncertain predictions, preventing error accumulation. We also contribute the first dynamic fetal placenta ultrasound video segmentation dataset with 671 annotated frames. Across three ultrasound video datasets, EchoPilot achieves state-of-the-art performance under the sparse-interactive setting, consistently outperforming training-free baselines and finetuned specialists.
title EchoPilot: Training-Free Ultrasound Video Segmentation via Scale-Space Semantic Prompting and Reliability-Gated Memory
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.25944