noCNN

Neuronavigation refers to the set of computer-aided technologies used by neurosurgeons to guide surgery on the nervous system. Existing solutions suffer from several shortcomings, e.g. no compensation for brain-shift, no temporal tracking of data.

The aim of the noCNN project is to (i) accurately, automatically and continuously reconstruct the brain volume exposed by craniotomy during neurosurgery, and (ii) reposition this volume deformed by reduced intracranial pressure and resection in standard imaging (MRI, PET-Scan). The proposed approach is to combine deep learning tools in computer vision and biomechanical models to achieve a corrected, complete neuronavigation better suited to research.