Towards Estimating MRI-Ultrasound Registration Error in Image-Guided Neurosurgery.

Abstract

Image-guided neurosurgery allows surgeons to view their tools in relation to pre-operatively acquired patient images and models. To continue using neuronavigation systems throughout operations, image registration between pre-operative images (typically MRI) and intra-operative images (e.g., ultrasound) are common to account for brain shift (deformations of the brain during surgery). We implemented a method to estimate MRI-ultrasound registration errors, with the goal of enabling surgeons to quantitatively assess the performance of linear or nonlinear registrations. To the best of our knowledge, this is the first dense error estimating algorithm applied to multimodal image registrations. The algorithm is based on a previously proposed sliding-window convolutional neural network that operates on a voxel-wise basis. To create training data where the true registration error is known, simulated ultrasound images were created from pre-operative MRI images and artificially deformed. The model was evaluated on artificially deformed simulated ultrasound data as well as real ultrasound data with manually annotated landmark points. The model achieved a mean absolute error of 0.977 ± 0.988 mm and correlation of 0.8 ± 0.062 on the simulated ultrasound data, and a mean absolute error of 2.24 ± 1.89 mm and a correlation of 0.246 on the real ultrasound data. We discuss concrete areas to improve the results on real ultrasound data. Our progress lays the foundation for future developments and ultimately implementation on clinical neuronavigation systems.