TH‐CD‐206‐10: Clinical Application of the MIND Demons Algorithm for Symmetric Diffeomorphic Deformable MR‐To‐CT Image Registration in Spinal Interventions

Abstract

Purpose.Accurate intraoperative localization of target anatomy (e.g., tumors and vertebral levels) and critical structures (e.g., nerves and vessels) is essential to safe, effective surgery. Preoperative CT/MR images can be used to identify such vital anatomy in intraoperative images through multimodality deformable registration. We proposed a deformable registration method to align preoperative MR to intraoperative CT using modality‐independent neighborhood descriptors (MIND) and a Huber metric for robust registration.Methods.The method, called MIND Demons, estimates time‐dependent diffeomorphisms between two images by optimizing a constrained symmetric energy functional incorporating priors on smoothness, conservation of momentum, geodesic length, invertibility, and closure under composition. Alternating optimization is performed using a regularized Gauss‐Newton (GN) method in a multiresolution scheme. Performance was measured in phantom experiments emulating image‐guided spine‐surgery and in a retrospective clinical study (N=15 patients) evaluated in terms of target registration error (TRE) and diffeomorphic properties of the resulting deformations.Results.The MIND Demons method outperformed free‐form deformation (FFD) methods and conventional Demons in phantom experiments (median TRE = 1.5 mm, compared to 10.2 mm for mutual information (MI) based FFD, 2.6 mm for local‐MI FFD, and 5.1 mm for normalized‐MI Demons). The resulting deformations resolved realistic deformation in clinical data with sub‐voxel TRE (<2 mm) in cases of cervical, thoracic, and lumbar spine and preserved topology with sub‐voxel invertibility (0.004 mm) and positive‐determinant nonsingular spatial‐Jacobians.Conclusion.A modality‐independent deformable registration method has been developed, incorporating the constrained symmetric energy functional and the Huber metric to yield stable and accurate registration, with computational efficiency improved using the GN optimization. The approach yielded registration accuracy suitable to application in image‐guided spine‐surgery across each region of the spine under realistic modes of deformation.S. Vogt and G. Kleinszig is with Siemens Healthcare XP.