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

Joint Registration And Synthesis Using A Probabilistic Model For Alignment Of MRI And Histological Sections

J. Iglesias, M. Modat, L. Peter, A. Stevens, R. Annunziata, Tom Kamiel Magda Vercauteren, Ed Lein, B. Fischl, S. Ourselin
Published 2018 · Computer Science, Mathematics, Medicine

Save to my Library
Download PDF
Analyze on Scholarcy
Share
&NA; Nonlinear registration of 2D histological sections with corresponding slices of MRI data is a critical step of 3D histology reconstruction algorithms. This registration is difficult due to the large differences in image contrast and resolution, as well as the complex nonrigid deformations and artefacts produced when sectioning the sample and mounting it on the glass slide. It has been shown in brain MRI registration that better spatial alignment across modalities can be obtained by synthesising one modality from the other and then using intra‐modality registration metrics, rather than by using information theory based metrics to solve the problem directly. However, such an approach typically requires a database of aligned images from the two modalities, which is very difficult to obtain for histology and MRI. Here, we overcome this limitation with a probabilistic method that simultaneously solves for deformable registration and synthesis directly on the target images, without requiring any training data. The method is based on a probabilistic model in which the MRI slice is assumed to be a contrast‐warped, spatially deformed version of the histological section. We use approximate Bayesian inference to iteratively refine the probabilistic estimate of the synthesis and the registration, while accounting for each other's uncertainty. Moreover, manually placed landmarks can be seamlessly integrated in the framework for increased performance and robustness. Experiments on a synthetic dataset of MRI slices show that, compared with mutual information based registration, the proposed method makes it possible to use a much more flexible deformation model in the registration to improve its accuracy, without compromising robustness. Moreover, our framework also exploits information in manually placed landmarks more efficiently than mutual information: landmarks constrain the deformation field in both methods, but in our algorithm, it also has a positive effect on the synthesis – which further improves the registration. We also show results on two real, publicly available datasets: the Allen and BigBrain atlases. In both of them, the proposed method provides a clear improvement over mutual information based registration, both qualitatively (visual inspection) and quantitatively (registration error measured with pairs of manually annotated landmarks).
This paper references
10.1016/j.neuroimage.2018.08.012
A probabilistic atlas of the human thalamic nuclei combining ex vivo MRI and histology
J. Iglesias (2018)
10.1117/12.2043954
MR to CT registration of brains using image synthesis
Snehashis Roy (2014)
10.1016/j.neuroimage.2007.09.031
Construction of a 3D probabilistic atlas of human cortical structures
D. Shattuck (2008)
10.1073/pnas.1801093115
Characterizing the human hippocampus in aging and Alzheimer’s disease using a computational atlas derived from ex vivo MRI and histology
D. Adler (2018)
Nineteen dubious ways to compute the expo20
C. Moler (2003)
10.1109/42.796284
Nonrigid registration using free-form deformations: application to breast MR images
D. Rueckert (1999)
Multi-modal volume registration by maximization of mutual information
F. Maes (1997)
hippocampal subfields in postmortem MRI
R. K. Ahuja (1993)
10.1016/j.neuroimage.2009.10.042
A mean three-dimensional atlas of the human thalamus: Generation from multiple histological data
A. Krauth (2010)
10.1007/978-3-030-00934-2_17
Model-Based Refinement of Nonlinear Registrations in 3D Histology Reconstruction
J. Iglesias (2018)
10.1007/s11263-006-9780-x
Image Registration of Sectioned Brains
O. Schmitt (2006)
10.1109/NSSMIC.1993.373602
3D statistical neuroanatomical models from 305 MRI volumes
Alan C. Evans (1993)
10.1097/00004728-199403000-00005
Automatic 3D Intersubject Registration of MR Volumetric Data in Standardized Talairach Space
D. L. Collins (1994)
A probabilistic atlas of the thalamic nuclei combining ex vivo MRI and histology. Organization for Human Brain Mapping (OHBM)
J. E. Iglesias (2017)
10.1016/0165-0270(88)90129-X
Objective image alignment for three-dimensional reconstruction of digital autoradiograms
L. Hibbard (1988)
10.1016/j.neuroimage.2012.01.021
FreeSurfer
B. Fischl (2012)
10.1118/1.4931417
Technical Note: MRI only prostate radiotherapy planning using the statistical decomposition algorithm.
C. Siversson (2015)
10.1007/978-3-319-24553-9_65
Why Does Synthesized Data Improve Multi-sequence Classification?
G. V. Tulder (2015)
10.1117/1.JMI.1.2.024003
Global image registration using a symmetric block-matching approach
M. Modat (2014)
High-resolution magnetic resonance imaging reveals nuclei of the human amygdala : manual segmentation to automatic atlas
Z. M. Saygina (2017)
10.1118/1.1600738
A stereotactic method for the three-dimensional registration of multi-modality biologic images in animals: NMR, PET, histology, and autoradiography.
J. Humm (2003)
Nonrigid registration using freeform deformations: application to breast
D Rueckert (1999)
10.1006/nimg.1996.0251
Mutual Information for Automated Unwarping of Rat Brain Autoradiographs
B. Kim (1997)
Decision Forests for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning
A. Criminisi (2011)
10.1016/S0262-8856(00)00052-4
Reconstructing a 3D structure from serial histological sections
S. Ourselin (2001)
Fast approximate energy minimiza
Y. Boykov (2001)
Fast freeform deformation using graphics processing units
M Modat (2010)
A log-euclidean
V. Arsigny (2006)
Characterizing the human hippocampus in aging and alzheimers disease using a computational
D. H. Adler (2018)
10.1109/TMI.2014.2340135
Attenuation Correction Synthesis for Hybrid PET-MR Scanners: Application to Brain Studies
N. Burgos (2014)
10.1016/j.jneumeth.2006.02.020
3D volume reconstruction of a mouse brain from histological sections using warp filtering
T. Ju (2006)
10.1006/nimg.1995.1012
A Probabilistic Atlas of the Human Brain: Theory and Rationale for Its Development: The International Consortium for Brain Mapping (ICBM)
J. Mazziotta (1995)
10.1007/978-3-319-68127-6_1
Adversarial Image Synthesis for Unpaired Multi-modal Cardiac Data
Agisilaos Chartsias (2017)
Volumetric reconstruction from printed films
S. Ourselin (2017)
10.2307/2583863
Network flows - theory, algorithms and applications
R. Ahuja (1993)
Bigbrain: an ultrahighresolution 3d human brain
K. Amunts (2013)
10.1063/1.2811677
Statistical Field Theory
G. Parisi (1988)
10.1016/S0896-6273(02)00569-X
Whole Brain Segmentation Automated Labeling of Neuroanatomical Structures in the Human Brain
B. Fischl (2002)
10.1007/978-3-540-75759-7_39
Non-parametric Diffeomorphic Image Registration with the Demons Algorithm
Tom Kamiel Magda Vercauteren (2007)
10.1016/j.jneumeth.2007.04.017
Three-dimensional reconstruction of stained histological slices and 3D non-linear registration with in-vivo MRI for whole baboon brain
Julien Dauguet (2007)
10.1007/978-3-319-68127-6_2
Deep MR to CT Synthesis Using Unpaired Data
J. Wolterink (2017)
Magnetic resonance image examplebased contrast synthesis
S. Roy (2013)
10.1007/BFb0046965
A Robust Point Matching Algorithm for Autoradiograph Alignment
Anand Rangarajan (1996)
10.1007/BF00058655
Bagging predictors
L. Breiman (1996)
10.1016/S1077-3142(03)00002-X
Iconic feature based nonrigid registration: the PASHA algorithm
P. Cathier (2003)
10.1109/TMI.2013.2282126
Magnetic Resonance Image Example-Based Contrast Synthesis
Snehashis Roy (2013)
10.1016/j.neuroimage.2015.04.042
A computational atlas of the hippocampal formation using ex vivo, ultra-high resolution MRI: Application to adaptive segmentation of in vivo MRI
J. Iglesias (2015)
A probabilistic at
J. Mazziotta (2001)
Whole brain segmentation
N. Makris (2002)
10.1109/TMI.2018.2791721
Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning
Guotai Guotai Wang Wang (2018)
10.1109/TMI.2007.908121
Brain Anatomical Structure Segmentation by Hybrid Discriminative/Generative Models
Zhuowen Tu (2008)
10.1016/S1361-8415(01)80004-9
Multi-modal volume registration by maximization of mutual information
W. Wells (1996)
10.1016/j.neuroimage.2011.01.060
Smoothness-guided 3-D reconstruction of 2-D histological images
A. Cifor (2011)
10.1007/978-3-319-46726-9_8
Probabilistic Atlas of the Human Hippocampus Combining Ex Vivo MRI and Histology
D. Adler (2016)
10.1126/science.1235381
BigBrain: An Ultrahigh-Resolution 3D Human Brain Model
K. Amunts (2013)
Journal of computer assisted tomography
A. Criminisi (2011)
10.1016/j.neuroimage.2004.04.038
Fusion of autoradiographs with an MR volume using 2-D and 3-D linear transformations
G. Malandain (2004)
10.1109/ICCV.1999.791245
Fast approximate energy minimization via graph cuts
Yuri Boykov (1999)
A probabilistic atlas of the thalamic nuclei combining ex vivo MRI and histology. Organization for Human Brain Mapping
J E Iglesias (2017)
10.1002/cne.24080
Comprehensive cellular‐resolution atlas of the adult human brain
Song-Lin Ding (2016)
Smoothness-guided 3-d reconstruction
A. 3–13. Cifor (2011)
10.1145/383259.383282
Topology matching for fully automatic similarity estimation of 3D shapes
Masaki Hilaga (2001)
10.1016/j.neuroimage.2013.08.067
Histology-derived volumetric annotation of the human hippocampal subfields in postmortem MRI
D. Adler (2014)
10.1109/42.251130
Registration and three-dimensional reconstruction of autoradiographic images by the disparity analysis method
W. Zhao (1993)
10.1109/TMI.2003.815867
Mutual-information-based registration of medical images: a survey
J. Pluim (2003)
10.1145/383259.383295
Image analogies
Aaron Hertzmann (2001)
10.1137/S00361445024180
Nineteen Dubious Ways to Compute the Exponential of a Matrix, Twenty-Five Years Later
C. Moler (2003)
10.1016/j.jneumeth.2012.08.021
MRI-guided volume reconstruction of mouse brain from histological sections
Z. Yang (2012)
10.1098/RSTB.2001.0915
A probabilistic atlas and reference system for the human brain: International Consortium for Brain Mapping (ICBM).
J. Mazziotta (2001)
Image analogies. Proceedings of the 28th annual conference on Computer graphics and interactive techniques
A Hertzmann (2001)
Bagging predictors. Machine learning
N. Burgos (1996)
10.1109/42.563664
Multimodality image registration by maximization of mutual information
F. Maes (1997)
10.1109/TMI.2018.2791721
Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning
G. Wang (2018)
10.1109/42.811268
Automated model-based bias field correction of MR images of the brain
K. Leemput (1999)
10.1016/j.media.2018.02.004
A Survey of Methods for 3D Histology Reconstruction
Jonas Pichat (2018)
10.1016/j.cmpb.2009.09.002
Fast free-form deformation using graphics processing units
M. Modat (2010)
Journal of computer assisted tomography
A. Criminisi (2011)
10.1016/j.ijrobp.2014.09.015
Implementation of a novel algorithm for generating synthetic CT images from magnetic resonance imaging data sets for prostate cancer radiation therapy.
J. Kim (2015)
Bigbrain: an ultrahigh
N.J (2013)
10.1007/978-3-540-39899-8_43
The Creation of a Brain Atlas for Image Guided Neurosurgery Using Serial Histological Data
M. Chakravarty (2003)
10.5244/C.2.23
A Combined Corner and Edge Detector
C. Harris (1988)
“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告
Jun-Yan Zhu (2017)
10.1023/A:1010933404324
Random Forests
L. Breiman (2004)
10.1016/J.MEDIA.2005.03.008
Piecewise affine registration of biological images for volume reconstruction
A. Pitiot (2006)
10.1002/jemt.20829
3D reconstruction of histological sections: Application to mammary gland tissue
I. Arganda-Carreras (2010)
10.1007/978-3-642-40811-3_79
Is Synthesizing MRI Contrast Useful for Inter-modality Analysis?
J. Iglesias (2013)
10.1097/00004728-199803000-00032
Enhancement of MR images using registration for signal averaging
C. Holmes (1998)
10.1016/j.neuroimage.2017.09.056
Volumetric reconstruction from printed films: Enabling 30 year longitudinal analysis in MR neuroimaging
M. Ebner (2018)
Modelbased refinement of nonlinear registrations in 3D histology reconstruction. Medical Image Computing and Computer-Assisted Intervention–MICCAI
JE Iglesias (2018)
Three-dimensional reconstruction of stained histologi
V. Frouin (2007)
10.1002/ana.20426
Detection of entorhinal layer II using Tesla magnetic resonance imaging
Jean C. Augustinack (2005)
10.1007/11866565_113
A Log-Euclidean Framework for Statistics on Diffeomorphisms
V. Arsigny (2006)
10.1016/j.neuroimage.2008.08.04
A High-Resolution Computational Atlas of the Human Hippocampus from Postmortem Magnetic Resonance Imaging at 9.4 Tesla
P. Yushkevich (2009)
prehensive cellular - resolution atlas of the adult human brain
S. L. Ding
10.1109/TMI.2015.2461533
Estimating CT Image From MRI Data Using Structured Random Forest and Auto-Context Model
Tri Huynh (2016)
10.1007/11784012_28
3D Mouse Brain Reconstruction from Histology Using a Coarse-to-Fine Approach
P. Yushkevich (2006)
10.1016/j.neuroimage.2008.08.042
A high-resolution computational atlas of the human hippocampus from postmortem magnetic resonance imaging at 9.4 T
P. Yushkevich (2009)



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