Diffusion Tensor Registration Using Probability Kernels and Discrete Optimization

نویسندگان

  • Aristeidis Sotiras
  • Nikos Paragios
  • Jean-François Deux
  • Mezri Maatouk
  • Alain Rahmouni
  • Guillaume Bassez
چکیده

In this report, we propose a novel diffusion tensor registration algorithm based on a discrete optimization approach in a Reproducing Kernel Hilbert Space (RKHS) setting. Our approach encodes both the diffusion information and the spatial localization of tensors in a probabilistic framework. The diffusion probabilities are mapped to a RKHS, where we define a registration energy that accounts both for target matching and deformation regularity in both translation and rotation spaces. The six-dimensional deformation space is quantized and discrete energy minimization is performed using efficient linear programming. We show that the algorithm allows for tensor reorientation directly in the optimization framework. Experimental results on a manually annotated dataset of diffusion tensor images of the calf muscle demonstrate the potential of the proposed approach. Key-words: Registration, DTI, Diffusion tensor, Kernels, Markov Random Fields ∗ Aristeidis Sotiras, Radhouène Neji and Nikos Paragios are affiliated to Laboratoire MAS, Ecole Centrale Paris, Châtenay-Malabry, France and to Equipe GALEN, INRIA Saclay Île-de-France, Orsay, France † Jean-François Deux, Mezri Maatouk, Alain Rahmouni et Guillaume Bassez are affiliated to Centre Hospitalier Universitaire Henri Mondor, Créteil, France ‡ Nikos Komodakis is affiliated to Department of Computer Science, University of Crete, Greece § Gilles Fleury is affiliated to Département SSE, Ecole Supérieure d’Electricité, Gif-sur-Yvette, France in ria -0 03 88 48 6, v er si on 1 26 M ay 2 00 9 Recalage d’images IRM de tenseurs de diffusion en utilisant des noyaux de probabilits et un schma d’optimisation discrte Résumé : Dans ce rapport, nous proposons une nouvelle approche pour le recalage d’images IRM de tenseurs diffusion qui se base sur un schma d’optimisation discrte dans espace de Hilbert. Notre mthode traite aussi bien l’information de diffusion que l’information de localisation spatiale dans un contexte probabiliste. Les probabilits gaussiennes de diffusions sont immerges dans un espace de Hilbert, o nous dfinissons une nergie de recalage qui tient compte la fois de la similarit entre tenseurs et de la rgularit de la dformation dans l’espace des translations et des rotations. L’espace de dformation (six-dimensionnel) est discrtis, ce qui permet d’utiliser une approche efficace de programmation linaire pour optimiser l’nergie dfinie. Nous montrons que l’algorithme permet d’inclure directement la rorientation des tenseurs dans l’tape d’optimisation. Les rsultats exprimentaux sur des images IRM de tenseurs de diffusion du mollet qui ont t pralablement segmentes d’une faon manuelle montrent le potentiel de notre approche. Mots-clés : Recalage, IRM de diffusion, Tenseur de diffusion, Noyaux, Champs Markoviens Aleatoires in ria -0 03 88 48 6, v er si on 1 26 M ay 2 00 9 Diffusion Tensor Registration Using Probability Kernels and Discrete Optimization 3

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Multimodality and Nonrigid Image Registration with Application to Diffusion Tensor Imaging

Multimodality and Nonrigid Image Registration with Application to Diffusion Tensor Imaging Mohammed Khader The great challenge in image registration is to devise computationally efficient algorithms for aligning images so that their details overlap accurately. The first problem addressed in this thesis is multimodality medical image registration, which we formulate as an optimization problem in...

متن کامل

Review of Techniques for Registration of Diffusion Tensor Imaging

Image registration is a common image processing task, and therefore, many algorithms have been proposed and described to carry it out for different image modalities. However, the application of these algorithms to diffusion tensor imaging is not straightforward due to the special features of this kind of data, where a tensor is defined at each voxel. The information provided by the diffusion te...

متن کامل

Deformable Registration of Diffusion Tensor MR Images with Explicit Orientation Optimization

In this paper, we present a novel deformable registration algorithm for diffusion tensor MR images that enables explicit optimization of tensor reorientation. The optimization seeks a piecewise affine transformation that divides the image domain into uniform regions and transform each region affinely. The objective function captures both the image similarity and the smoothness of the transforma...

متن کامل

Nonlinear Registration of Diffusion Tensor Images Using Directional Information

G. K. Rohde1,2, S. Pajevic3, C. Pierpaoli1 STBB/LIMB/NICHD, National Institutes of Health, Bethesda, Maryland, United States, Dept. of Mathematics, University of Maryland, College Park, Maryland, United States, MSCL/CIT, National Institutes of Health, Bethesda, Maryland, United States Introduction In Diffusion Tensor (DT) MRI [1], local diffusion properties are described via a 3x3 symmetric dif...

متن کامل

Multi-channel Diffusion Tensor Image Registration via adaptive chaotic PSO

Registration or spatial normalization of diffusion tensor images plays an important role in many areas of human brain white matter research, such as analysis of Fraction Anisotropy (FA) or whiter matter tracts. More difficult than registration of scalar images, spatial normalization of tensor images requires two important parts: one is tensor interpolation, and the other is tensor reorientation...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2009