RobUSt–An Autonomous Robotic Ultrasound System for Medical Imaging

Medical ultrasound (US) systems are widely used for the diagnosis of internal tissues. However, there challenges associated with acquiring and interpreting US images, such as incorrect probe placement limited available spatial information. In this study, we expand capabilities medical imaging using a robotic framework high level autonomy. A 3D camera is to capture surface an anthropomorphic phantom point cloud, which then path planning navigation probe. Robotic positioning realised impedance controller, maintains stable contact during scanning compensates uneven moving surfaces. accuracy measured be 1.19± 0.76mm. The mean force along z-direction 6.11±1.18N on static surfaces 6.63±2.18N Overall lowest 1.58N demonstrates constant probe-to-surface scanning. Acquired images reconstruction multi-modal visualization inner anatomical structures phantom. Finally, K-means clustering segment different Best segmentation jugular vein according Jaccard similarity coefficient 0.89. With accuracy, system could substantially improve autonomous acquisition enhance diagnostic confidence clinicians.