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

Accurate patient registration is a critical issue in medical image-guided interventions. The neurosurgical robotic system RObotic Neuro-NAvigation (RONNA) uses four retro-reflective spheres, on a marker attached to the patient's cranial bone, for patient registration in physical and image space. In this paper, the algorithm for automatic localization of spherical fiducials in CT scans is presented and clinically evaluated. The developed localization algorithm uses a unique approach, which combines machine vision algorithms, biomedical image filtration methods, and mathematical estimation methods. The performance of the localization algorithm was evaluated in comparison with four skilled human operators. The measurements were based on twelve patient and eight lab phantom CT scans. The localization error of the algorithm in comparison with the human readings was smaller by 49.29% according to the ground truth estimation and by 45.91% according to the intra-modal estimation. Localization processing time was reduced by 84.96%. Reliability in terms of successful localization of the fiducial marker was 100% for 20 different test samples containing a total of 116 spherical fiducials. Based on the tests carried out in clinical conditions, the localization algorithm has demonstrated reliability with a high degree of accuracy and short processing time. The developed algorithm provides fully automated and accurate machine vision-based patient localization for the neurosurgical clinical application of the robotic system RONNA.