Fast, intuitive, vision-based: Performance metrics for visual registration, instrument guidance, and image fusion

Abstract

We characterize the performance of an ultrasound+ computed tomography image fusion and instrument guidance system on phantoms, animals, and patients. The system is based on a visual tracking approach. Using multi-modality markers, registration is unobtrusive, and standard instruments do not require any calibration. A novel deformation estimation algorithm shows externally-induced tissue displacements in real time.