Marker-less tracking of brain surface deformations by non-rigid registration integrating surface and vessel/sulci features

Abstract

To compensate for brain shift in image-guided neurosurgery, we propose a new non-rigid registration method that integrates surface and vessel/sulci feature to noninvasively track the brain surface. Textured brain surfaces were acquired using phase-shift three-dimensional (3D) shape measurement, which offers 2D image pixels and their corresponding 3D points directly. Measured brain surfaces were noninvasively tracked using the proposed method by minimizing a new energy function, which is a weighted combination of 3D point corresponding estimation and surface deformation constraints. Initially, the measured surfaces were divided into featured and non-featured parts using a Frangi filter. The corresponding feature/non-feature points between intraoperative brain surfaces were estimated using the closest point algorithm. Subsequently, smoothness and rigidity constraints were introduced in the energy function for a smooth surface deformation and local surface detail conservation, respectively. Our 3D shape measurement accuracy was evaluated using 20 spheres for bias and precision errors. In addition, the proposed method was evaluated based on root mean square error (RMSE) and target registration error (TRE) with five porcine brains for which deformations were produced by gravity and pushing with different displacements in both the vertical and horizontal directions. The minimum and maximum bias errors were 0.32 and 0.61mm, respectively. The minimum and maximum precision errors were 0.025 and 0.30mm, respectively. Quantitative validation with porcine brains showed that the average RMSE and TRE were 0.1 and 0.9mm, respectively. The proposed method appeared to be advantageous in integrating vessels/sulci feature, robust to changes in deformation magnitude and integrated feature numbers, and feasible in compensating for brain shift deformation in surgeries.