Welcome to Huang's page

Title:Automatic 3D Imaging and Measurement of Human Spines with a Robotic Ultrasound System

Abstract：

Comparing with X-ray, ultrasound imaging has the advantages of no radiation and easy operation, etc., which is expected to be an effective alternative in clinical assessment for human spine. At present, freehand scanning is mainly used in ultrasound imaging field, and recently robot-assisted scanning has emerged as a promising way to gradually reduce the human intervention. However, the automatical recognition and scanning, as well as the control strategy of robots that guarantees the tight coupling between a probe and human skin, are still challenges. Moveover, the current measurement method of the spine is usually conducted based on plain radiographs, which lacks of spatial structure information of spine. In this paper, a new radiation-free robotic ultrasound system for 3D imaging and a measurement method of spine based on 3D imaging are presented. A fully convolutional network named fuse-Unet based on RGB and depth images captured by a RGB-Depth(RGB-D) sensor Kinect, is proposed to realize the automatical recognition of human spine area and scanning path pre-planning. Then a six-degree-of-freedom robotic arm plays the role of a doctor to complete the automatical scanning along the pre-planning path, during which a normal-vector-based method and two force sensors are used to ensure that the probe well fits the spine area. Finally, 3D ultrasound reconstruction and visualization of spine is realized, based on which cobb angles are calculated for assessing the morphological structure of the spine. Phantom and in vivo experiments are conducted for evaluating the performance of the proposed system. Experimental results validate the practicability and accuracy of the system, indicating its potential for clinical application.

Our contribute：

◆ intelligent recognition of the spine area and pre-planning of the scan path for the robot system without user-participation.

◆ considering the complexity of scanning the spine area, two robot control strategies are adopted to guarantee the effective coupling of ultrasonic signal.

◆ comparing with traditional 2D radiography, 3D ultrasound visualization of spine and a measurement method based on 3D volume for scoliosis are offered to realize the spatial structure display and non-radiation examination.

Dataset and code:Code Download

video demo: VideoDemo

Home