Towards 3D ultrasound guided needle steering robust to uncertainties, noise and tissue heterogeneity
This paper presents robust flexible needle steering for robotized punctures guided by 3D ultrasound (US) images. Reaching a target in biological tissue involves being able to detect the inserted needle in the 3D image, to plan a path from its current position and to control motion, at each instant. The proposed approach is able to face the low quality of images, the high variability of biological tissue and the limited ability to capture needle-tissue interactions in a model. Experiments on multi-material phantoms and ex-vivo biological tissue demonstrated the system ability to reach, accurately, US-defined targets using generated 3D helical paths.
read more