Towards expert-level autonomous carotid ultrasonography with large-scale learning-based robotic system

Haojun Jiang, Andrew Zhao, Qian Yang, Xiangjie Yan, Teng Wang, Yulin Wang, Ning Jia, Jiangshan Wang, Guokun Wu, Yang Yue, Shaqi Luo, Huanqian Wang, Ling Ren, Siming Chen, Pan Liu, Guocai Yao, Wenming Yang, Shiji Song, Xiang Li, Kunlun He () and Gao Huang ()
Additional contact information
Haojun Jiang: Tsinghua University
Andrew Zhao: Tsinghua University
Qian Yang: Air Force Medical Center
Xiangjie Yan: Tsinghua University
Teng Wang: Tsinghua University
Yulin Wang: Tsinghua University
Ning Jia: LeadVision Ltd
Jiangshan Wang: Shenzhen International Graduate School, Tsinghua University
Guokun Wu: Shenzhen International Graduate School, Tsinghua University
Yang Yue: Tsinghua University
Shaqi Luo: Beijing Academy of Artificial Intelligence
Huanqian Wang: Tsinghua University
Ling Ren: Chinese PLA General Hospital
Siming Chen: Chinese PLA General Hospital
Pan Liu: Chinese PLA General Hospital
Guocai Yao: Beijing Academy of Artificial Intelligence
Wenming Yang: Shenzhen International Graduate School, Tsinghua University
Shiji Song: Tsinghua University
Xiang Li: Tsinghua University
Kunlun He: Chinese PLA General Hospital
Gao Huang: Tsinghua University

Nature Communications, 2025, vol. 16, issue 1, 1-21

Abstract: Abstract Carotid ultrasound requires skilled operators due to small vessel dimensions and high anatomical variability, exacerbating sonographer shortages and diagnostic inconsistencies. Prior automation attempts, including rule-based approaches with manual heuristics and reinforcement learning trained in simulated environments, demonstrate limited generalizability and fail to complete real-world clinical workflows. Here, we present UltraBot, a fully learning-based autonomous carotid ultrasound robot, achieving human-expert-level performance through four innovations: (1) A unified imitation learning framework for acquiring anatomical knowledge and scanning operational skills; (2) A large-scale expert demonstration dataset (247,000 samples, 100 × scale-up), enabling embodied foundation models with strong generalization; (3) A comprehensive scanning protocol ensuring full anatomical coverage for biometric measurement and plaque screening; (4) The clinical-oriented validation showing over 90% success rates, expert-level accuracy, up to 5.5 × higher reproducibility across diverse unseen populations. Overall, we show that large-scale deep learning offers a promising pathway toward autonomous, high-precision ultrasonography in clinical practice.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-62865-w Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-62865-w

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-62865-w

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().