Image registration

CNRS - Institut de Mathématiques de Toulouse (Jan. 2012 - .)

University of Oxford (Jan. 2011 - Jan. 2012, Invited fellow until 2014)

Imperial College London (Jan. 2009 - Dec. 2010)

Context:

Since January 2009, I work on the development of new techniques for the registration of 3D medical images. Between January 2009 and December 2010 this work has been done in collaboration with Darryl Holm (Institute for Mathematical Sciences) and Daniel Rueckert (Biomedical Image Analysis Group) at Imperial College London, UK. Between January 2011 and January 2012, I worked at the University of Oxford in collaboration with Julia Schnabel (Institute of Biomedical Engineering). Since January 2012, I continue this work at CNRS - Institut de Mathématiques de Toulouse. This work is also done in strong collaboration with François-Xavier Vialard (Université Dauphine, Paris). Applications are possible for any kind of images, in particular cerebral images, but also images of the lungs or the heart.

Image registration consists in finding the optimal deformation to match source images onto target images with respect to spatial constrains. It has numerous applications in image analysis, from the comparison of shapes to the creation of atlases. Recent years have seen the development of diffeomorphic (smooth and invertible) registration techniques that allow large deformations. The formalism of the Large Deformation Diffeomorphic Metric Mapping (LDDMM - Beg et al., IJCV 2005) is one of the references in this context since it is designed to find geodesics between shapes, i.e., the shortest path between the shapes according to a metric. This formalism has therefore interesting statistical properties, in particular, for the creation of atlases. However, applications of the LDDMM framework on volumetric 3D medical images still remain limited for practical reasons. Interestingly, alternatives that are faster, requiring less memory or adapted to multi-modal images, have been proposed (e.g.: Avants et al., MIA 2008 / Vercauteren et al, MICCAI 2008 / ...) but none of them has been designed to explicitely estimate geodesic transformations between the registered images. In this context, I mainly work on the development of practical, but also mathematically justified, strategies for the geodesic registration of volumetric 3D cerebral images. I also work on the development of more general diffeomorphic registration strategies to estimate the motion of the lungs and the heart in CT/MR 3D images.




Illustration: (Left) Inner-surface of a baby's cortex at 36 weeks of gestational age out of a 3D MR image. The colors represent the deformations of the cortex from 36 to 43 weeks of gestational age. (Right) Slice out of a 3D image of the thoracic cage. The black structures are the lungs and the white ones are the bones (ribs and spine in particular). An extreme case of lungs motion to estimate is shown by the red isoline which represents where can be the lungs boundaries on the same subject (picture from the MICCAI Empire challenge 2010).


Software:

The source code and executables of the multi-kernel LDDMM algorithm (Risser et al. TMI 2011) and beta executables of the geodesic shooting algorithm (Vialard et al. IJCV 2011) are available on sourceforge: sourceforge.net/projects/utilzreg/. Explanations about the software are given here.

Journal papers:

Schmah T., Risser L., Vialard F.X.: Diffeomorphic image matching with left-invariant metrics. Book chapter in Fields Institute Communications 73 - Geometry, Mechanics, and Dynamics: The Legacy of Jerry Marsden (book), 2015

Papież B.W., Heinrich M.P., Fehrenbach J., Risser L., Schnabel J.A.: An implicit sliding-motion preserving regularisation via bilateral filtering for deformable image registration. Medical Image Analysis (link), 2014


Fiot J.B., Raguet H., Risser L., Cohen L.D., Fripp J., Vialard F.X., ADNI: Longitudinal deformation models, spatial regularizations and learning strategies to quantify Alzheimer's disease progression. NeuroImage: Clinical 2014 (link).


Cifor A., Risser L., Chung D., Anderson E.M., Schnabel J.A.: Hybrid Feature-based Diffeomorphic Registration for Tumour Tracking in 2-D Liver Ultrasound Images. IEEE Transactions on Medical Imaging 2013 (link).


Baluwala H.Y., Risser L., Schnabel J.A., Saddi K.A.: Towards a Physiologically Motivated Registration of Diagnostic CT and PET/CT of Lung Volumes. Medical Physics 40(02), 2013 (link).


Risser L., Vialard F.X., Baluwala H.Y., Schnabel J.A.: Piecewise-Diffeomorphic Image Registration: Application to the Motion Estimation between 3D CT Lung Images with Sliding Conditions Medical Image Analysis 2012, (link).


Bruveris M., Risser L., Vialard F.X.: Mixture of Kernels and Iterated semidirect Product of Diffeomorphisms Groups. SIAM Multiscale Modeling and Simulation 10 (4), pp: 1344-1368, 2012, (link).


Vialard F.X., Risser L., Rueckert D., Holm D.D.: Diffeomorphic Atlas Estimation using Geodesic Shooting on Volumetric Images Annals of the British Machine Vision Association, 2012, (link).


Risser L., Vialard F.X., Wolz R., Murgasova M., Holm D.D., Rueckert D., ADNI: Simultaneous Multiscale Registration using Large Deformation Diffeomorphic Metric Mapping. IEEE Transactions on Medical Imaging DOI: 10.1109/TMI.2011.2146787, 2011, (link).


Vialard F.X., Risser L., Rueckert D., Cotter C.J.: Diffeomorphic 3D Image Registration via Geodesic Shooting using an Efficient Adjoint Calculation. International Journal of Computer Vision DOI: 10.1007/s11263-011-0481-8, 2011, (link).

Conference and workshops with proceedings:

Vialard F.X., Risser L.: Spatially-varying metric learning for diffeomorphic image registration. A variational framework. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'14) - LNCS. Boston, 2014.


Risser L., Dolius L., Fonta C., Mescam M.: Diffeomorphic registration with self-adaptive spatial regularization for the segmentation of non-human primate brains. International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'14). Chicago, 2014.


Schmah T., Risser L., Vialard F.X.: Left-invariant metrics for diffeomorphic image registration with spatially-varying regularisation. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'13) - LNCS. Nagoya, 2013.


Papież B.W., Heinrich M.P., Risser L., Schnabel J.A.: Complex lung motion estimation via adaptive bilateral filtering of the deformation field. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'13) - LNCS (P.B.W. received a Young Scientist awards for this paper). Nagoya, 2013.


Cifor A., Risser L., Heinrich M.P., Chung D., Schnabel J.A.: Rigid registration of untracked freehand 2D ultrasound sweeps to 3D CT of liver tumours MICCAI Workshop on Computational and Clinical Applications in Abdominal Imaging (MICCAI-ABDI'13) - LNCS. Nagoya, 2013.


Fiot J.B., Risser L., Cohen L., Fripp J., Vialard F.X.: Local vs global descriptors of hippocampus shape evolution for Alzheimer's longitudinal population analysis. MICCAI Workshop on Spatiotemporal Image Analysis for Longitudinal and Time-Series Image Data (MICCAI-STIA'12) - LNCS. Nice, 2012.


Risser L., Heinrich M.P., Matin T., Schnabel J.A.: Piecewise-diffeomorphic registration of 3D CT/MR pulmonary images with sliding conditions. IEEE International Symposium on Biomedical Imaging (ISBI'12). Barcelona, 2012.


Cifor A., Risser L., Chung D., Anderson E.M., Schnabel J.A.: Hybrid feature-based Log-demons registration for tumour tracking in 2-D liver ultrasound images IEEE International Symposium on Biomedical Imaging (ISBI'12). Barcelona, 2012.


Bhushan M., Schnabel J.A., Heinrich M.P., Risser L., Brady M., Jenkinson M.: Motion Correction and Parameter Estimation in dceMRI sequences: Application to Colorectal Cancer. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'11) - Lecture Notes in Computer Science. Toronto, 2011.


Risser L., Baluwala H. Schnabel J.A.: Diffeomorphic registration with sliding conditions: Application to the registration of lungs CT images. International Conference on Medical Image Computing and Computer Assisted Intervention - Worshop on Pulmonary Image Analysis (MICCAI-PIA'11). Toronto, 2011.


Risser L., Heinrich M.P., Rueckert D., Schnabel J.A.: Multi-modal diffeomorphic registration using mutual information: Application to the registration of CT and MR pulmonary images. International Conference on Medical Image Computing and Computer Assisted Intervention - Worshop on Pulmonary Image Analysis (MICCAI-PIA'11). Toronto, 2011.


Risser L., Vialard F.X., Serag A., Aljabar P., Rueckert D.: Construction of Diffeomorphic Spatio-temporal Atlases using Kärcher means and LDDMM: Application to Early Cortical Development International Conference on Medical Image Computing and Computer Assisted Intervention - Worshop on Image Analysis of Human Brain Development (MICCAI-IAHBD'11). Toronto, 2011.


Vialard F.X., Risser L., Holm D.D., Rueckert D.: Diffeomorphic Atlas Estimation using Kärcher Mean and Geodesic Shooting on Volumetric Images. Medical Image Understanding and Analysis (MIUA'11). (Top ranked paper) London, 2011.


Risser L., Vialard F.X., Wolz R., Holm D., Rueckert D. Simultaneous Fine and Coarse Diffeomorphic Registration: Application to the Atrophy Measurement in Alzheimer's Disease. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'10) - Lecture Notes in Computer Science. Beijing, 2010.


Zhang D.P., Risser, L., Vialard F.X., Friman O., Neefjes L., Mollet N., Niessen W., Rueckert D. Coronary Motion Estimation Using Probability Atlas and Diffeomorphic Registration from CTA. International Workshop on Medical Imaging and Augmented Reality (MIAR'10) - Lecture Notes in Computer Science Beijing, 2010.


Risser L., Vialard F.X., Murgasova M., Holm D., Rueckert D. Large Diffeomorphic Registration using Fine and Coarse Strategies. Application to the brain growth characterization. International Workshop on Biomedical Image Registration (WBIR'10) - Lecture Notes in Computer Science 6204, pp. 186--197. Lübeck, 2010.


Zhang D.P., Risser, L., Friman O., Neefjes L., Mollet N., Niessen W., Rueckert D. Nonrigid Registration and Template Matching for Coronary Motion Modeling from 4D CTA. International Workshop on Biomedical Image Registration (WBIR'10) - Lecture Notes in Computer Science. Lübeck, 2010.


Zhang D.P., Risser L., Metz C., Mollet N.R., Niessen W., Rueckert D. Coronary artery motion modeling from 3D cardiac CT sequences. IEEE International Symposium on Biomedical Imaging (ISBI'10). Rotterdam, 2010.

Seminars and workshops without proceedings:


Risser L., Vialard F.X.: Spatially varying metrics in diffeomorphic image registration. Research Workshop on Computational Anatomy, Erwin Schrödinger International Institute for Mathematical Physics, Vienna, Austria, February 2015.

Risser L., Vialard F.X.: Learning spatially varying metrics in diffeomorphic image registration. Research Workshop on Computational Anatomy, Imperial College London, UK, June 2014.

Mescam M., Vialard F.X., Risser L.: Diffeomorphic estimation of average 3D images and their variability. Application to the anatomical analysis of the marmoset brain. CIMI workshop on Optimization and Statistics in Image Processing, Toulouse, France, June 2013.

Risser L.: A quick introduction to image registration 6th Imaging the Cell Meeting , Practical workshop in image analysis, Toulouse, France, June 2012.

Risser L.: Piecewise-diffeomorphic LDDMM registration applied to the registration of lung images. Research Workshop on Computational Anatomy, ICM Paris/ENS Cachan, France, April 2012.

Risser L.: Piecewise-diffeomorphic LogDemons applied to the registration of lung images. University of Copenhagen, Department of Computer Science (DIKU), Denmark, March 2012.

Risser L.: 3D cortical image averaging using multiscale LDDMM and Kärcher means. Neurospin - LNAO team. CEA Saclay, France, December 2011.

Risser L. and Vialard F.X.: 3D cortical image analysis using multiscale geodesic shooting and Kärcher means. Workshop NatImage'11. Institut Henri Poincaré, Paris, France, November 2011.

Risser L., Baluwala H. Schnabel J.A.: Diffeomorphic registration with sliding conditions: Application to the registration of lungs CT images. Oxford Biomedical Imaging Festival 2011. Oxford, UK, October 2011.

Risser L. Quantitative analysis of 3D cerebral images in anatomical and functionnal MRI. Groupe d'Imagerie Neurofonctionnelle, Université Bordeaux 2. Bordeaux, France, October 2011.

Risser L. Diffeomorphic image registration in medical imaging. Mini-symposium on medical registration, University of Oxford. UK, April 2011.

Risser L. LDDMM Registration of 3D cerebral images using the sum of kernels. Research Workshop on Computational Anatomy. London, UK, April 2011.

Risser L. A quick overview of diffeomorphic image registration. Medical Images and Signals module, Doctoral Training Centre, University of Oxford. UK, March 2011.

Risser L. Quantitative analysis of 3D cerebral images in anatomical and functionnal MRI. Faculté de Médecine de Rangueil. Toulouse, France, November 2010.

Risser L., Vialard F.X., Rueckert D. Multi-level kernels for LDDMM Registration of 3D medical images. Research Workshop on Computational Anatomy. London, UK, May 2010.

Risser L. Quantitative tools for the statistical analysis of shapes in medical imaging. ERIM - CHU Gabriel Montpied, Clermont-Ferrand, France, April 2010.

Risser L. Multiscale strategies for Large Deformation Diffeomorphic Metric Mapping. INRIA - ASCLEPIOS team, Sophia-Antipolis, France, February 2010.

Risser L., Darryl Holm, Daniel Rueckert. 4D segmentation of the heart from CT images. Perspectives in metamorphosis. Research Workshop on Computational Anatomy. Annapolis, MD, April 2009.

Risser L., Darryl Holm, Daniel Rueckert. The cardiomaths program: Issues in cardiac image analysis. Early Career Researcher Imaging Event. Imperial College, London, UK, March 2009.

Some results on the cortical maturation:

Registration of follow-up images acquired on pre-term babies at 33, 36 and 43 weeks of gestational age (first from 33 to 36 weeks and then from 36 to 43 weeks):
2D slices
3D view - External face of the grey matter
3D view - Internal face of the grey matter

Separation of the large and small scale contribution in the deformation estimated between 36 and 43 weeks:
Estimated deformation -> the colors represent the total amount of deformations from 36 weeks.
Estimated deformation -> the colors represent the large scale contribution in the deformations.
Estimated deformation -> the colors represent the small scale contribution in the deformations.

Other preliminary results:

Registration of 2D binary images that highlights the potential of the LDDMMs (.avi file - OK using vlc).

Registration of cardiac CT images (.avi file - OK using vlc).