Deep Learning for Regularization Prediction in Diffeomorphic Image Registration

This paper presents a predictive model for estimating regularization parameters of diffeomorphic image registration. We introduce a novel framework that automatically determines the parameters controlling the smoothness of diffeomorphic transformations. Our method significantly reduces the effort of parameter tuning, which is time and labor-consuming. To achieve the goal, we develop a predictive model based on deep convolutional neural networks (CNN) that learns the mapping between pairwise images and the regularization parameter of image registration. In contrast to previous methods that estimate such parameters in a high-dimensional image space, our model is built in an efficient bandlimited space with much lower dimensions. We demonstrate the effectiveness of our model on both 2D synthetic data and 3D real brain images. Experimental results show that our model not only predicts appropriate regularization parameters for image registration, but also improving the network training in terms of time and memory efficiency.

[1]  Karl J. Friston,et al.  Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation , 2011, NeuroImage.

[2]  P. Ellen Grant,et al.  Frequency Diffeomorphisms for Efficient Image Registration , 2017, IPMI.

[3]  William M. Wells,et al.  Bayesian Registration via Local Image Regions: Information, Selection and Marginalization , 2009, IPMI.

[4]  S. Allassonnière,et al.  Stochastic Algorithm For Parameter Estimation For Dense Deformable Template Mixture Model , 2008, 0802.1521.

[5]  Nicholas Ayache,et al.  A Log-Euclidean Framework for Statistics on Diffeomorphisms , 2006, MICCAI.

[6]  R. Buckner,et al.  Normative estimates of cross-sectional and longitudinal brain volume decline in aging and AD , 2005, Neurology.

[7]  Jian Wang,et al.  Efficient Laplace Approximation for Bayesian Registration Uncertainty Quantification , 2018, MICCAI.

[8]  Paul A. Viola,et al.  Multi-modal volume registration by maximization of mutual information , 1996, Medical Image Anal..

[9]  William M. Wells,et al.  A Marginalized MAP Approach and EM Optimization for Pair-Wise Registration , 2007, IPMI.

[10]  P. Thomas Fletcher,et al.  Finite-Dimensional Lie Algebras for Fast Diffeomorphic Image Registration , 2015, IPMI.

[11]  L. Younes,et al.  Statistics on diffeomorphisms via tangent space representations , 2004, NeuroImage.

[12]  P. Ellen Grant,et al.  Temporal Registration in In-Utero Volumetric MRI Time Series , 2016, MICCAI.

[13]  Michael I. Jordan,et al.  An Introduction to Variational Methods for Graphical Models , 1999, Machine Learning.

[14]  Alain Trouvé,et al.  Computing Large Deformation Metric Mappings via Geodesic Flows of Diffeomorphisms , 2005, International Journal of Computer Vision.

[15]  Daniel Rueckert,et al.  Diffeomorphic 3D Image Registration via Geodesic Shooting Using an Efficient Adjoint Calculation , 2011, International Journal of Computer Vision.

[16]  Polina Golland,et al.  Registration Uncertainty Quantification Via Low-dimensional Characterization of Geometric Deformations. , 2019, Magnetic resonance imaging.

[17]  P. Thomas Fletcher,et al.  Fast Diffeomorphic Image Registration via Fourier-Approximated Lie Algebras , 2018, International Journal of Computer Vision.

[18]  Mark W. Woolrich,et al.  Probabilistic inference of regularisation in non-rigid registration , 2012, NeuroImage.

[19]  Thierry Siméon,et al.  Adaptive tuning of the sampling domain for dynamic-domain RRTs , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[20]  Arthur W. Toga,et al.  Construction of a 3D probabilistic atlas of human cortical structures , 2008, NeuroImage.

[21]  Polina Golland,et al.  Fast Geodesic Regression for Population-Based Image Analysis , 2017, MICCAI.

[22]  Nick C Fox,et al.  The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods , 2008, Journal of magnetic resonance imaging : JMRI.

[23]  Frank Preiswerk,et al.  A Feature-Driven Active Framework for Ultrasound-Based Brain Shift Compensation , 2018, MICCAI.

[24]  L. R. Dice Measures of the Amount of Ecologic Association Between Species , 1945 .

[25]  Michael I. Miller,et al.  Evolutions equations in computational anatomy , 2009, NeuroImage.

[26]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[27]  Marc Niethammer,et al.  Memory Efficient LDDMM for Lung CT , 2016, MICCAI.

[28]  Thomas Stützle,et al.  Evolutionary medical image registration using automatic parameter tuning , 2013, 2013 IEEE Congress on Evolutionary Computation.

[29]  Y. Amit,et al.  Towards a coherent statistical framework for dense deformable template estimation , 2007 .

[30]  Alejandro F. Frangi,et al.  Temporal diffeomorphic free-form deformation: Application to motion and strain estimation from 3D echocardiography , 2012, Medical Image Anal..

[31]  P. Thomas Fletcher,et al.  Bayesian Estimation of Regularization and Atlas Building in Diffeomorphic Image Registration , 2013, IPMI.

[32]  Daniel Rueckert,et al.  Diffeomorphic Registration Using B-Splines , 2006, MICCAI.

[33]  Yong Wang,et al.  Plug-and-Play Priors for Reconstruction-Based Placental Image Registration , 2019, SUSI/PIPPI@MICCAI.

[34]  Brian B. Avants,et al.  Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain , 2008, Medical Image Anal..

[35]  Guido Gerig,et al.  Image registration and segmentation in longitudinal MRI using temporal appearance modeling , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[36]  Anderson Rocha,et al.  Medical image registration based on watershed transform from greyscale marker and multi-scale parameter search , 2017, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[37]  Yutaka Satoh,et al.  Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[38]  Karl J. Friston,et al.  Unified segmentation , 2005, NeuroImage.

[39]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[40]  Polina Golland,et al.  Low-Dimensional Statistics of Anatomical Variability via Compact Representation of Image Deformations , 2016, MICCAI.

[41]  Sanjay Ranka,et al.  Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer's Disease Classification , 2018, AMIA.