Online citations, reference lists, and bibliographies.
Please confirm you are human
(Sign Up for free to never see this)
← Back to Search

Deformable MRI-Ultrasound Registration Using Correlation-based Attribute Matching For Brain Shift Correction: Accuracy And Generality In Multi-site Data

Inês Machado, M. Toews, E. George, P. Unadkat, Walid Essayed, Jie Luo, P. Teodoro, H. Carvalho, J. Martins, P. Golland, S. Pieper, S. Frisken, A. Golby, W. Wells, Yangming Ou
Published 2019 · Medicine, Computer Science

Save to my Library
Download PDF
Analyze on Scholarcy
Share
Intraoperative tissue deformation, known as brain shift, decreases the benefit of using preoperative images to guide neurosurgery. Non-rigid registration of preoperative magnetic resonance (MR) to intraoperative ultrasound (US) has been proposed as a means to compensate for brain shift. We focus on the initial registration from MR to predurotomy US. We present a method that builds on previous work to address the need for accuracy and generality of MR-iUS registration algorithms in multi-site clinical data. To improve accuracy of registration, we use high-dimensional texture attributes instead of image intensities and propose to replace the standard difference-based attribute matching with correlation-based attribute matching. We also present a strategy that deals explicitly with the large field-of-view mismatch between MR and iUS images. We optimize key parameters across independent MR-iUS brain tumor datasets acquired at three different institutions, with a total of 43 tumor patients and 758 corresponding landmarks to validate the registration algorithm. Despite differences in imaging protocols, patient demographics and landmark distributions, our algorithm was able to reduce landmark errors prior to registration in three data sets (5.37 ± 4.27, 4.18 ± 1.97 and 6.18 ± 3.38 mm, respectively) to a consistently low level (2.28 ± 0.71, 2.08 ± 0.37 and 2.24 ± 0.78 mm, respectively). Our algorithm is compared to 15 other algorithms that have been previously tested on MR-iUS registration and it is competitive with the state-of-the-art on multiple datasets. We show that our algorithm has one of the lowest errors in all datasets (accuracy), and this is achieved while sticking to a fixed set of parameters for multi-site data (generality). In contrast, other algorithms/tools of similar performance need per-dataset parameter tuning (high accuracy but lower generality), and those that stick to fixed parameters have larger errors or inconsistent performance (generality but not the top accuracy). We further characterized landmark errors according to brain regions and tumor types, a topic so far missing in the literature. We found that landmark errors were higher in high-grade than low-grade glioma patients, and higher in tumor regions than in other brain regions.
This paper references
10.1155/2012/531319
3D Rigid Registration of Intraoperative Ultrasound and Preoperative MR Brain Images Based on Hyperechogenic Structures
P. Coupé (2012)
10.1109/TPAMI.2012.196
Simultaneous Registration of Multiple Images: Similarity Metrics and Efficient Optimization
C. Wachinger (2013)
10.1007/978-3-540-40899-4_58
Generalized Correlation Ratio for Rigid Registration of 3D Ultrasound with MR Images
A. Roche (2000)
10.1007/978-3-030-01045-4_16
Non-linear Approach for MRI to intra-operative US Registration Using Structural Skeleton
Jisu Hong (2018)
10.1007/s11548-010-0535-3
New prototype neuronavigation system based on preoperative imaging and intraoperative freehand ultrasound: system description and validation
L. Mercier (2010)
10.1016/j.media.2014.04.008
Automatic ultrasound-MRI registration for neurosurgery using the 2D and 3D LC2 Metric
B. Fuerst (2014)
10.1118/1.4709600
Online database of clinical MR and ultrasound images of brain tumors.
L. Mercier (2012)
10.1016/j.media.2010.07.002
DRAMMS: Deformable registration via attribute matching and mutual-saliency weighting
Y. Ou (2011)
10.1007/s11548-015-1292-0
CustusX: an open-source research platform for image-guided therapy
C. Askeland (2015)
10.1227/01.neu.0000317377.15196.45
A COMPARATIVE ANALYSIS OF COREGISTERED ULTRASOUND AND MAGNETIC RESONANCE IMAGING IN NEUROSURGERY
A. Hartov (2008)
10.1007/s11548-018-1840-5
Using the variogram for vector outlier screening: application to feature-based image registration
Jie Luo (2018)
10.1007/s00701-008-0017-3
Comparison of navigated 3D ultrasound findings with histopathology in subsequent phases of glioblastoma resection
O. Rygh (2008)
10.1109/TMI.2014.2354352
Automatic Deformable MR-Ultrasound Registration for Image-Guided Neurosurgery
H. Rivaz (2015)
10.1007/s11548-013-0826-6
Fast rigid registration of pre-operative magnetic resonance images to intra-operative ultrasound for neurosurgery based on high confidence gradient orientations
Dante De Nigris (2013)
10.1007/s12021-018-9359-z
Field of View Normalization in Multi-Site Brain MRI
Yangming Ou (2018)
10.1016/j.media.2009.05.002
Sampling the spatial patterns of cancer: Optimized biopsy procedures for estimating prostate cancer volume and Gleason Score
Y. Ou (2009)
10.1093/neuros/nyx392
Tumor Volume Assessment in Low‐Grade Gliomas: A Comparison of Preoperative Magnetic Resonance Imaging to Coregistered Intraoperative 3‐Dimensional Ultrasound Recordings
Bodil Karoline Ravn Munkvold (2018)
10.1007/978-3-030-01045-4_15
Resolve Intraoperative Brain Shift as Imitation Game
Xia Zhong (2018)
10.1109/EMBC.2014.6944887
A hybrid method for non-rigid registration of intra-operative ultrasound images with pre-operative MR images
P. Farnia (2014)
10.1016/J.INFFUS.2018.09.009
Multimodal image registration using Laplacian commutators
V. Zimmer (2019)
10.1109/ICCV.2003.1238464
Entropy-of-likelihood feature selection for image correspondence
M. Toews (2003)
10.1016/j.media.2007.06.008
Clinical validation of vessel-based registration for correction of brain-shift
I. Reinertsen (2007)
10.1109/TMI.2010.2053043
Intensity-Based Image Registration by Minimizing Residual Complexity
A. Myronenko (2010)
10.1007/978-3-319-75238-9_5
MARCEL (Inter-Modality Affine Registration with CorrELation Ratio): An Application for Brain Shift Correction in Ultrasound-Guided Brain Tumor Resection
Nima Masoumi (2017)
10.1007/978-3-030-01045-4_21
Registration of MRI and iUS Data to Compensate Brain Shift Using a Symmetric Block-Matching Based Approach
David Drobny (2018)
10.1109/EMBC.2016.7590912
Curvelet based residual complexity objective function for non-rigid registration of pre-operative MRI with intra-operative ultrasound images
P. Farnia (2016)
10.1007/s00701-014-2052-6
Intra-operative correction of brain-shift
I. Reinertsen (2014)
10.1002/mp.12268
REtroSpective Evaluation of Cerebral Tumors (RESECT): A clinical database of pre-operative MRI and intra-operative ultrasound in low-grade glioma surgeries.
Y. Xiao (2017)
10.1109/TMI.2013.2294630
Nonrigid Registration of Ultrasound and MRI Using Contextual Conditioned Mutual Information
H. Rivaz (2014)
10.1016/j.patcog.2006.08.012
Image registration by local histogram matching
Dinggang Shen (2007)
10.1109/34.24792
Principal Warps: Thin-Plate Splines and the Decomposition of Deformations
F. Bookstein (1989)
10.1016/j.media.2007.06.004
Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain
B. Avants (2008)
10.3109/10929080309146040
Multimodal Image Fusion in Ultrasound-Based Neuronavigation: Improving Overview and Interpretation by Integrating Preoperative MRI with Intraoperative 3D Ultrasound
F. Lindseth (2003)
10.1016/j.media.2011.03.001
Entropy and Laplacian images: Structural representations for multi-modal registration
C. Wachinger (2012)
10.1016/S0531-5131(03)00305-4
Rigid registration of 3D ultrasound data of brain tumours
M. Letteboer (2003)
10.1016/j.media.2012.05.008
MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration
M. Heinrich (2012)
10.1016/J.JMIR.2017.06.005
Image-Guided Neurosurgery.
R. Miner (2017)
10.1016/j.jneumeth.2004.07.014
Quantitative comparison of algorithms for inter-subject registration of 3D volumetric brain MRI scans
B. Ardekani (2005)
10.1007/s11548-016-1407-2
miLBP: a robust and fast modality-independent 3D LBP for multimodal deformable registration
Dongsheng Jiang (2016)
10.1109/TIP.2011.2159615
Nonrigid Brain MR Image Registration Using Uniform Spherical Region Descriptor
S. Liao (2012)
10.1016/j.neuroimage.2008.12.037
Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration
A. Klein (2009)
10.1016/j.neuroimage.2008.10.040
Diffeomorphic demons: Efficient non-parametric image registration
T. Vercauteren (2009)
10.1109/MEMB.2006.1705749
Image-guided neurosurgery at Brigham and Women's Hospital
S. Dimaio (2006)
10.1007/s11548-018-1786-7
Non-rigid registration of 3D ultrasound for neurosurgery using automatic feature detection and matching
Inês Machado (2018)
10.1007/978-3-642-40811-3_24
Towards Realtime Multimodal Fusion for Image-Guided Interventions Using Self-similarities
M. Heinrich (2013)
10.1016/j.media.2016.08.007
Brain shift in neuronavigation of brain tumors: A review
I. Gerard (2017)
10.1016/j.cviu.2008.06.007
Performance vs computational efficiency for optimizing single and dynamic MRFs: Setting the state of the art with primal-dual strategies
Nikos Komodakis (2008)
10.1016/j.wneu.2018.09.012
Automatic Intraoperative Correction of Brain Shift for Accurate Neuronavigation.
D. H. Iversen (2018)
10.1002/cncr.29012
Multimodal imaging for improved diagnosis and treatment of cancers
C. Tempany (2015)
10.1109/42.796284
Nonrigid registration using free-form deformations: application to breast MR images
D. Rueckert (1999)
10.1109/TMI.2013.2265603
Deformable Medical Image Registration: A Survey
Aristeidis Sotiras (2013)
10.1016/j.neuroimage.2009.10.065
TPS-HAMMER: Improving HAMMER registration algorithm by soft correspondence matching and thin-plate splines based deformation interpolation
G. Wu (2010)
10.1109/ISBI.2007.357103
A PROBABILISTIC OBJECTIVE FUNCTION FOR 3D RIGID REGISTRATION OF INTRAOPERATIVE US AND PREOPERATIVE MR BRAIN IMAGES
P. Coupé (2007)
10.1109/TPAMI.2008.233
Detection, Localization, and Sex Classification of Faces from Arbitrary Viewpoints and under Occlusion
M. Toews (2009)
10.1007/978-3-030-01045-4_20
Deformable MRI-Ultrasound Registration via Attribute Matching and Mutual-Saliency Weighting for Image-Guided Neurosurgery
Inês Machado (2018)
10.1016/j.media.2017.06.003
Brain‐shift compensation using intraoperative ultrasound and constraint‐based biomechanical simulation
F. Morin (2017)
10.1007/s12021-013-9216-z
Intensity Based Methods for Brain MRI Longitudinal Registration. A Study on Multiple Sclerosis Patients
Y. Diez (2013)
10.1117/12.813601
Fiducial registration error and target registration error are uncorrelated
J. Fitzpatrick (2009)
10.1109/TMI.2006.886812
COMPARE: Classification of Morphological Patterns Using Adaptive Regional Elements
Y. Fan (2007)
10.1016/j.neuroimage.2017.07.008
Quicksilver: Fast predictive image registration – A deep learning approach
X. Yang (2017)
10.1007/978-3-030-01045-4_17
Brain-Shift Correction with Image-Based Registration and Landmark Accuracy Evaluation
W. Wein (2018)
10.1007/978-3-642-40811-3_5
Global Registration of Ultrasound to MRI Using the LC2 Metric for Enabling Neurosurgical Guidance
W. Wein (2013)
Improved Mixture Representation in Real-Time Particle Filters for Robot Localization
Dario Lodi Rizzini (2007)
10.1007/978-3-319-67558-9_24
End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network
B. D. Vos (2017)
10.1007/978-3-030-01045-4_18
Deformable MRI-Ultrasound Registration Using 3D Convolutional Neural Network
Li Sun (2018)
10.1007/978-3-540-75759-7_39
Non-parametric Diffeomorphic Image Registration with the Demons Algorithm
Tom Kamiel Magda Vercauteren (2007)
10.1109/TBME.2015.2496253
Scalable High-Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning
G. Wu (2016)
10.1109/TMI.2011.2163944
Image Similarity and Tissue Overlaps as Surrogates for Image Registration Accuracy: Widely Used but Unreliable
T. Rohlfing (2012)
10.1109/TMI.2009.2028078
Feature Based Nonrigid Brain MR Image Registration With Symmetric Alpha Stable Filters
S. Liao (2010)
10.1007/s11548-014-1099-4
Deformable registration of preoperative MR, pre-resection ultrasound, and post-resection ultrasound images of neurosurgery
H. Rivaz (2014)
10.1007/s11548-014-1098-5
Brain-shift compensation by non-rigid registration of intra-operative ultrasound images with preoperative MR images based on residual complexity
P. Farnia (2014)
10.1109/TMI.2014.2330355
Comparative Evaluation of Registration Algorithms in Different Brain Databases With Varying Difficulty: Results and Insights
Y. Ou (2014)
10.1109/TMI.2005.862744
Deformable segmentation of 3-D ultrasound prostate images using statistical texture matching method
Y. Zhan (2006)
10.1007/s10143-011-0314-9
Stand-alone 3D-ultrasound navigation after failure of conventional image guidance for deep-seated lesions
D. Miller (2011)
10.1109/42.921484
3D Registration and Fusion of Ultrasound and MRI Using Major Vessels as Fiducial Markers
B. Porter (2001)
10.1016/j.media.2008.03.006
Dense image registration through MRFs and efficient linear programming
Ben Glocker (2008)
10.1109/TMI.2002.803111
HAMMER: hierarchical attribute matching mechanism for elastic registration
Dinggang Shen (2002)
10.1118/1.2977728
Mutual-information-based image to patient re-registration using intraoperative ultrasound in image-guided neurosurgery.
S. Ji (2008)
10.1109/TMI.2019.2935060
Evaluation of MRI to Ultrasound Registration Methods for Brain Shift Correction: The CuRIOUS2018 Challenge
Y. Xiao (2020)
10.1016/j.media.2013.12.003
Self-similarity weighted mutual information: A new nonrigid image registration metric
H. Rivaz (2014)
10.1007/s11548-018-1897-1
ARENA: Inter-modality affine registration using evolutionary strategy
Nima Masoumi (2018)
10.1007/11866763_86
Diffeomorphic Registration Using B-Splines
D. Rueckert (2006)
10.1016/j.media.2012.11.002
Efficient and robust model-to-image alignment using 3D scale-invariant features
M. Toews (2013)
10.1007/s00701-005-0624-1
Ability of navigated 3D ultrasound to delineate gliomas and metastases – comparison of image interpretations with histopathology
G. Unsgaard (2005)
10.1117/1.JMI.1.2.024003
Global image registration using a symmetric block-matching approach
M. Modat (2014)
10.1007/978-3-030-01045-4_19
Intra-operative Ultrasound to MRI Fusion with a Public Multimodal Discrete Registration Tool
M. Heinrich (2018)
10.1109/EMBC.2018.8512375
Co-Sparse Analysis Model Based Image Registration to Compensate Brain Shift by Using Intra-Operative Ultrasound Imaging
P. Farnia (2018)



This paper is referenced by
Semantic Scholar Logo Some data provided by SemanticScholar