EUVIMEDEUVIMED entdecken
Crossref

Tissue-View Map for Robotic Carotid Artery Ultrasound Scanning Using Reinforcement Learning

Kang Su, Guanglong Du, Xueqian Wang, Quanlong Guan

IEEE Robotics and Automation Letters · 2025-05 · 10 (5) · 5178-5185

DOI: 10.1109/lra.2025.3555865 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Robotics and Automation Letters, 2025-05. Verfasst von Kang Su und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: National Key R&D Program of China, Natural Science Foundation of Guangdong Province, TCL Charity Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ultrasound is an important diagnostic modality in medicine, offering real-time imaging, no radiation and low cost. However, ultrasound is currently highly dependent on the operator's experience and technical skills. Robotic autonomous ultrasound scanning (RAUS) is a sequential decision-making problem, requiring continuous decisions based on the current state and environment. Recently, reinforcement learning (RL) has made significant progress in solving such challenges across various domains. Nevertheless, most studies directly use raw ultrasound images as input to end-to-end networks. The noise and high-dimensional features in these images increase both network complexity and the number of parameters. In this letter, we propose a tissue-view map representation to facilitate model-free deep reinforcement learning for robotic carotid artery scanning. The tissue-view map captures the interaction between the probe and the skin, highlighting the scanned object while considering the surrounding tissues. A variational autoencoder is then employed to encode the features of the tissue-view map and further reduce dimensionality. Finally, we adopted proximal policy optimization to learn the policy for probe adjustment in carotid artery scanning. Our experiments demonstrate that the proposed method outperforms existing approaches and effectively handles the tasks of object search, contact control, and image quality optimization in real-world scenarios.

Förderung

  • National Key R&D Program of China
  • Natural Science Foundation of Guangdong Province
  • TCL Charity Foundation
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Dreams Foundation of Jianghuai Advance Technology Center
  • Open Foundation of Jiangxi Province Key Laboratory of Military-Civilian Integration

Zitieren

APA

Su, K., Du, G., Wang, X., & Guan, Q. (2025). Tissue-View Map for Robotic Carotid Artery Ultrasound Scanning Using Reinforcement Learning. IEEE Robotics and Automation Letters, 10(5), 5178-5185. https://doi.org/10.1109/lra.2025.3555865

Vancouver

Su K, Du G, Wang X, Guan Q. Tissue-View Map for Robotic Carotid Artery Ultrasound Scanning Using Reinforcement Learning. IEEE Robotics and Automation Letters. 2025;10(5):5178-5185. doi:10.1109/lra.2025.3555865

BibTeX
@article{Su2025,
  author = {Su, Kang and Du, Guanglong and Wang, Xueqian and Guan, Quanlong},
  title = {Tissue-View Map for Robotic Carotid Artery Ultrasound Scanning Using Reinforcement Learning},
  journal = {IEEE Robotics and Automation Letters},
  year = {2025},
  volume = {10},
  number = {5},
  pages = {5178--5185},
  doi = {10.1109/lra.2025.3555865}
}
Kostenlos starten →