A-SEE2.0: Active-Sensing End-Effector for Robotic Ultrasound Systems with Dense Contact Surface Perception Enabled...

Area of Science:

• Robotics
• Medical Imaging
• Biomedical Engineering

Background:

• Freehand ultrasound (US) imaging relies heavily on operator skill, causing variability and strain.
• Robotic Ultrasound Systems (RUSS) offer standardized, automated solutions, crucial for areas with limited expertise.

Purpose of the Study:

• To develop and validate a novel Robotic Ultrasound System (RUSS) with an advanced end-effector, A-SEE2.0.
• To enable consistent and accurate ultrasound probe alignment on various surfaces using dual RGB-D cameras.

Main Methods:

• Development of the A-SEE2.0 end-effector with dual RGB-D depth cameras for probe orientation.
• Integration of RGB-D data with robotic control algorithms for maintaining probe-to-skin orthogonality.
• Validation using phantom models and in-vivo forearm examinations.

Main Results:

• A-SEE2.0 achieved low normal positioning errors: 2.47 ± 1.25 degrees on a flat surface and 12.19 ± 5.81 degrees on a mannequin.
• The system demonstrated robust probe alignment on uneven surfaces without needing preoperative data.
• In-vivo forearm scans produced image quality comparable to expert human sonographers.

Conclusions:

• The A-SEE2.0 robotic end-effector significantly improves ultrasound probe positioning accuracy and consistency.
• This RUSS technology holds substantial clinical potential for standardized ultrasound examinations.
• The system offers a viable solution for improving ultrasound accessibility and reliability in diverse healthcare settings.