Researchers develop a vision-based robotic system for 3D ultrasound imaging that allows gathering reliable anatomical data.
Ultrasound imaging techniques are one of the most widely used techniques for diagnostics in the biomedical field. These techniques are used to diagnose some of the most common health conditions, including peripheral artery disease (PAD). PAD is common among the elderly in which the peripheral blood vessel narrows and gets blocked, limiting the blood supply to specific parts of the body.
Ultrasound imaging is used for diagnosing this disease because this technique is non-invasive, low-cost and radiation-free. However, most ultrasound imaging techniques are designed to capture 2D images. Their inability to capture 3D information limits the reliability and accuracy of this technique.
Researchers from Technical University of Munich, Zhejiang University and Johns Hopkins University have developed a robotic system that can capture high quality 3D ultrasound images. This allows physicians and healthcare providers to gather more reliable anatomical data using ultrasound technology.
3D imaging techniques developed so far do not allow to capture the entire artery tree of individual human limbs, as the objects that are being examined cannot be adjusted while data is being collected. If an object or limb moves during data collection, the quality of 3D imaging decreases substantially.
“To address this challenge, we propose a vision-based robotic ultrasound system that can monitor an object’s motion and automatically update the sweep trajectory to provide 3D compounded images of the target anatomy seamlessly,” Zhongliang Jiang and his colleagues wrote in their arXiv preprint.
The robotic system developed by the researchers consists of an RGB-D depth camera, a robotic manipulator, a CPLA12875 linear probe, and an ultrasound B interface. The manipulator’s movement can be controlled by a system based on the robot operating system (ROS), a framework for writing robotic software.
The software consists of a vision-based sweep trajectory extraction technique, an automatic robotic ultrasound sweep and 3D ultrasound compounding method, as well as a movement-monitoring system. The team validated the performance of the system using a custom-designed and gel-based vascular phantom.
“The preliminary validation on a gel phantom demonstrates that the proposed approach can provide a promising 3D geometry, even when the scanned object is moved,” the researchers wrote in their paper. “Although the vascular application was used to demonstrate the proposed method, the method can also be used for other applications, such as ultrasound bone visualization.”