Related Experiment Video
Updated: Aug 5, 2026
08:02
A High-Throughput Image-Guided Stereotactic Neuronavigation and Focused Ultrasound System for Blood-Brain Barrier Opening in Rodents
Published on: July 16, 2020
Robotic ultrasound scanning platform with autonomous control, multimodal human-machine interface and real-time image
Rafael Benito1,2, Laura Pérez Sánchez3, Amaia Iribar-Zabala3,4
1Vicomtech Foundation, Basque Research and Technology Alliance (BRTA), San Sebastian, Spain. rafael.benito01@estudiant.upf.edu.
Summary
This study introduces an autonomous robotic platform for ultrasound scanning, utilizing AI for precise tumor localization. The system offers intuitive multimodal control and achieves real-time performance on specialized hardware.
Area of Science:
- Robotics
- Artificial Intelligence
- Medical Imaging
Background:
- Surgical tasks like ultrasound scanning are time-consuming.
- Clinical acceptance of autonomous robots requires predictable movement, intuitive interaction, and low latency on medical hardware.
Purpose of the Study:
- To develop an integral robotic platform for autonomous ultrasound scanning.
- To enable AI-driven surgical task automation with user-friendly interfaces.
Main Methods:
- Developed a robotic platform with manual and autonomous modes.
- Combined AI for target segmentation with geometric motion algorithms.
- Optimized image processing for real-time performance on specialized hardware.
- Integrated natural language voice commands (via LLM) and AR visualization.
Main Results:
- Successfully localized hepatic tumors in a synthetic phantom with 84% accuracy.
- Achieved an average autonomous localization time of 5.75 seconds.
Conclusions:
- The system automates ultrasound tasks with an intuitive, multimodal interface.
- Optimized AI and specialized hardware enabled low-latency, real-time adaptability.
- Future plans include adaptation for neurosurgical and urological procedures.
