Non-Parametric Bayesian Registration (NParBR) on CT Lungs Data - EMPIRE10 Challenge

Size: px
Start display at page:

Download "Non-Parametric Bayesian Registration (NParBR) on CT Lungs Data - EMPIRE10 Challenge"

Transcription

1 Non-Parametric Bayesian Registration (NParBR) on CT Lungs Data - EMPIRE10 Challenge David Pilutti 1, Maddalena Strumia 1, Stathis Hadjidemetriou 2 1 University Medical Center Freiburg, Freiburg, Germany 2 UMIT, Institute for Biomedical Image Analysis, Eduard-Wallnoefer-Zentrum 1, A-6060 Hall in Tirol, Austria david.pilutti@uniklinik-freiburg.de Abstract. The alignment of intra-patient lung CT data is a challenging task due to the highly deformable nature of the lungs as a result of breathing motion on their fine structure. This requires non-rigid registration techniques to obtain satisfactory alignment. We propose a novel Non-Parametric Bayesian Registration (NParBR) method to efficiently perform non-rigid registration while operating at full spatial resolution. The NParBR method assumes that the spatial misregistration causes a Gaussian smoothing on the joint intensity statistics. This is incorporated in a Bayesian formulation and the statistics are restored with a Wiener filter. The restored statistics are back-projected into spatial domain and also spatially regularized with Gaussian filtering. To evaluate the stateof-the-art non-rigid registration methods, the EMPIRE10 challenge [4] has been proposed. The NParBR method has been tested on the EM- PIRE10 datasets and resulted in good alignment in several cases. Keywords: Non-rigid registration, joint statistics restoration, lungs registration, multi-contrast registration 1 Introduction Computed Tomography (CT) images are often used in clinical procedures to highlight internal structures of the human body with high detail. The visual analysis of CT images of the lungs can be complicated by the highly deformable nature of the organs. Breathing can also affect the fine texture of the alveoli structure in the lungs with complex displacement. Therefore, non-linear registration approaches are necessary to align lung images that can be subsequently analyzed for tasks such as disease progression, pulmonary functionality analysis, and image guided treatments in case of 4D images. We propose a novel image registration method based on the assumption that the spatial misregistration smooths the joint intensity statistics. This is incorporated in a Bayesian formulation, where the joint intensity statistics are restored non-parametrically and then back-projected to the image domain to estimate the registration. Our formulation performs a dense estimation of the

2 Fig. 1: Diagram describing the registration of two images with the proposed registration method. A preliminary rigid and affine registration is performed and the result is used to initialize the iterative non-rigid registration step until the stop criterion is met. spatial transformations and spatial smoothness only once per iteration, making the time performance orders of magnitude more efficient in comparison to other state-of-the-art methods [6]. The non-parametric restoration of the joint intensity statistics removes the effect of the misregistration, and can also preserve the form of the statistics. Thus, the resulting continuous spatial registration can be approximately volume preserving [1]. This property is desirable when registering organs or lesions whose volume is not expected to be changed from motion such as breathing, heart beat, and peristalsis. The proposed method

3 produced good qualitative results on several EMPIRE10 datasets [4] with an efficient computational time. The general methodology has been also submitted for publication [5]. 2 Method A pairwise registration is between a reference image I ref and a moving image I mov. A spatial transformation T = (u x, u y, u z ) from I ref to I mov is estimated to provide a registered image as I reg = I mov (T 1 (x)) where x = (x, y, z) are the spatial coordinates. The registration can accommodate a variable contrast. The method allows the registration over a limited Region Of Interest (ROI) over the image for which the contrast is intended for and is meaningful. In this work the spatial misregistration is assumed to cause a distortion of the joint intensity statistics that is considered to be Gaussian smoothing, which is deconvolved with Wiener filtering. An analogy can be drawn between the effect of spatial misregistration and the physical phenomenon of the ferromagnetic hysteresis [2, 6, 11]. Similarly to the lack of cross distributions in ferromagnetic hysteresis or their secondary role, any cross distribution is also ignored in our method. Their magnitude is lower compared to the effect of noise, spatial resolution, and other imaging artifacts. This assumes a smoothness for anatomy in space and a larger size for anatomic structures compared to that of the extent of the misregistration. Misregistration is also assumed to be spatially smooth. As a pre-processing step, the two images I ref and I mov are normalized in terms of their dynamic range to a maximum value of 255. This preserves the form of the histogram, expedites the transformations estimation, and it is convenient for the application of the fast Fourier transform used for applying the Wiener filter to the statistics. The method then performs an additional pre-processing step concatenating a rigid and an affine registration. The result is then used to initialize the subsequent non-rigid registration. The implementation of the non-rigid registration of pairs of images involved the deconvolution of the joint intensity statistics with the Wiener filter, its backprojection to the spatial domain that gives the maximum likelihood Bayesian estimation of the spatial transformation, and the spatial regularization obtained with a Gaussian filter. The implementation interleaves between the maximum likelihood and the spatial smoothness iteratively, k = 0,..., K 1 for a total of K iterations. An overview of the registration is given with the diagram shown in fig Computation of Joint Intensity Statistics A neighborhood is defined as N (x) = x + x, where x represents all possible shifts within N. The joint intensity statistics are calculated by relating the intensities of each voxel x in I ref to each voxel in I mov at the corresponding spatial locations x + x and accumulating the occurrences of each intensity pair throughout the images. This results in a bidimensional statistics, which

4 can also differentiate between different tissue types, grouped by intensity change properties. It is assumed that two images I ref and I mov of the same anatomy under perfect alignment would give rise to the joint histogram H ideal. The joint statistics H actual of the misregistered images are considered to result from the convolution of H ideal with a 2D Gaussian filter G δ (i; 0, σ δ ): H actual = H ideal G δ (i; 0, σ δ ) + n δ, (1) where is the convolution operator, i = (i, j) is an intensity pair, σ δ standard deviation of G δ, and n δ is the noise. is the 2.2 Bayesian Restoration of Joint Intensity Statistics The total registration vector v(x) at x is assumed to consist of the underlying correct registration vector field u(x) and the misregistration vector field d(x), v(x) = u(x) + d(x). (2) Under the assumption that p(u(x)) and p(d(x)) are independent, where p denotes a probability distribution, it follows that: p(v(x)) = p(u(x)) p(d(x)), (3) where is the convolution operator. Each spatial location x in I ref is linked to a cubic spatial neighborhood N (x) in I mov. The assumption of texture uniformity within tissues leads to the probability distributions of the actual displacement v(x) and the ideal displacement u(x) as: p(v(x)) = H actual (I ref (x), I mov (x + v(x))) (4) p(u(x)) = H ideal (I ref (x), I mov (x + u(x))), (5) where H actual and H ideal are the joint histograms of two images I ref and I mov in the actual case and under assumed correct alignment, respectively. The distortion p(d(x)) assumed Gaussian can also be expressed as p(d(x)) = G(i; 0, σ δ ), (6) which is the distortion of the joint intensity statistics modeled by a Gaussian distribution. The conditional expectation of the assumed correct displacement u(x) given the initial displacement v(x) using Bayes law for p(u v) [9, 10] is: p(v u)p(u)udu E[u v] = p(u v)udu =. (7) p(v u)p(u)du It is assumed that the Fourier transform F( ) of the probability of the correct displacement F(p(u)) can be estimated from F(p(v)) by deconvolution with a Wiener filter R [10]. In the Fourier domain the Wiener filter R is defined as R = G G 2 + ɛ, (8)

5 where G is the Fourier transform of a Gaussian distribution for p(d(x)) and ɛ is the inverse of the signal to noise ratio of the statistics. That is Moreover, F(p(u)) = RF(p(v)). (9) p(v u) = p(v u) = p(d) = G(i; 0, σ δ ) (10) is the Gaussian distribution that models the distortion of the joint intensity statistics. The inverse Fourier transform of the Wiener filter R to the intensity range domain is defined as r = F 1 (R). Substituting Eq. (9) and Eq. (10) into Eq. (7) gives: p(v u)r p(v)udu G(i; 0, σδ )r p(v)udu E[u v] = = p(v u)r p(v)du G(i; 0, σδ )r p(v)du. (11) The substitution of Eq. (4) into Eq. (11) gives G(i; 0, σδ )r H actual udu E[u v] = G(i; 0, σδ )r H actual du. (12) Eq. (12) can be discretized with u x N to give: E[u v] = Σ N G(i; 0, σ δ )r H actual x Σ N G(i; 0, σ δ )r H actual. (13) 2.3 Backprojection for Spatial Misregistration The expected value E[u v] of the distortion allows the computation of the expected distortion d(x) at x as: E[d(x)] = E[d(x) v(x)] = E[v(x) u(x) v(x)] = E[v(x) v(x)] E[u(x) v(x)] = v(x) E[u(x) v(x)] = v(x) Σ N G(i; 0, σ δ )r H actual x Σ N G(i; 0, σ δ )r H actual. (14) This is an initial estimate of the misregistration calculated using the spatial neighborhood N. 2.4 Estimation of Smooth Spatial Transformation At the starting iteration k = 0 the vector v(x) is initialized to 0 everywhere. Following Eq. (13) and Eq. (14), the restored joint intensity statistics are backprojected to space to give an initial spatial transformation E[d(x)] k at iteration k > 0 to obtain T k(x) that is a rough estimate of the spatial transformation T k(x) = T k 1 (x) + E[d(x)] k, (15) where T k 1 (x) is the displacement from the previous iteration. The cumulative Bayesian estimate of the transformation T k is smoothed with a 3D Gaussian

6 filter G(x; 0, σ S ), where σ S is the standard deviation of the smoothing of the spatial transformation T k. The final estimate of the spatial transformation at iteration k is obtained with T k (x) = T k(x) G(x; 0, σ S ). (16) The value of T k (x) is calculated for all x in the ROI of I ref (x). 2.5 Implementation The method has been implemented in C ++ and operates over the 3 spatial dimensions of the data. The pairwise non-rigid registration developed is preceded by the rigid and affine registration methods provided by ITK [3] using their default settings such as for subsampling and interpolation. The Wiener filtering in Eq. (8) and Eq. (14) of the joint intensity statistics was performed in the Fourier domain using the forward and backward FFT provided by ITK [3]. The value of σ δ has been set for all datasets to 3 and is accumulated along the iterations to give the total Gaussian distortion of the joint intensity statistics. The value of ɛ of the Wiener filter has been set to 0.1 for all datasets. The spatial regularization G(x; 0, σ S ) has been performed using the efficient separable implementation of the 3D Gaussian filter from ITK [3]. The value of σ S has been set equal to the length of the side of an in-plane voxel in 3D for all datasets. A maximum number of k max = 100 iterations is enforced for the non-rigid registration. The non-rigid registration has been performed within the ROIs provided by the EMPIRE10 challenge [4] segmented using the method of van Rixoort et al. [7]. 3 Experiments and Results The NParBR method has been tested on all 30 CT image pairs of lungs provided by the EMPIRE10 challenge [4]. Each dataset consist of two images taken from the same subject, and requires intra-patient registration. The 30 datasets are subdivided into 6 different categories to cover a representative range of practical cases. Eight image pairs consist of two inspiration scans (I/I), eight image pairs consist of breathhold inspiration/expiration (I/E), four cases consist of two individual phases of a 4-D dataset (4D), four ovine datasets (Ov), two contrast/non-contrast scan pairs (Co), and finally four artificially warped scan pairs (Wa). Due to the possible large displacements of the fine structures of the lungs, which can be smaller than the displacement, the NParBR can be applied only to a subset of the provided datasets where the displacements of the fine structures are small enough. The resulting alignment for the aforementioned datasets was satisfactory after visual inspection. In Fig. 2 is an example of the application of

7 (a) Reference (b) Moving (c) Before Registration (d) After rigid/affine (e) After NParBR Fig. 2: An axial section from the volumetric registration of the dataset 05 from the EMPIRE10 challenge [4]. In (a) and (b) are the input reference and moving images, respectively. Finally in (c), (d), and (e) are the resulting overlaps before the registration, after rigid/affine registration, and after NParBR non-rigid registration, respectively. The red arrows point at structures that are better aligned after the NParBR non-rigid registration. the NParBR method over dataset number 05. The lung structures highlighted with the arrows show an improved alignment after the non-rigid registration step compared to both non registered and only rigid/affine registered images. Further validation is based on the prescribed evaluation protocol of the EMPIRE10 challenge [4] and will appear in the EMPIRE10 challenge website. 4 Summary and Discussion The registration of CT images of lungs is a challenging task mainly due to the highly deformable nature of the considered organs. Breathing can affect the fine structure of the alveoli with complex and potentially large displacement. The alignment of intra-patient lung images can be very useful for medical procedures such as the evaluation of disease progression, pulmonary functionality analysis, and image guided treatment in case of 4D images. The main contribution of this work has been to develop a novel non-rigid registration method based on a nonparametric Bayesian formulation for the estimate of the misregistration and its removal. The presented method has been developed to efficiently perform dense non-rigid registration on images representing objects with volume preserving transformations such as many of the motions of the organs in a body as well as for possible tumor lesions.

8 The proposed method can accommodate datasets of both same as well as variable image contrast and more general contrast inversion cases. The implementation is iterative and results in an effective deconvolution of the joint intensity statistics that only requires a single computation of the joint intensity statistics and spatial smoothing of the estimated registration per iteration. The method restores the joint intensity histogram non-parametrically by removing the effect of the misregistration and preserving the form of the joint intensity statistics. The restored statistics are then back-projected to the image domain. The statistical restorations together with spatial smoothness provide a spatially continuous registration that can accommodate approximate volume preservation for different anatomic regions inherently without retrospectively imposing a volume preservation constraint that can still suffer from local shearing. This approach reduces artifacts such as the shrinking and sinking effect on local regions, which can help to maximize a global measure such as MI [8], while avoiding excessive regularization such as volume preserving constraints. A misregistration particularly multicontrast can be accounted for if it gives rise to a distribution in the statistics whose size is sufficiently large compared to the value of ɛ of the Wiener filter. This made the NParBR method applicable only on a subset of the EMPIRE10 datasets. This formulation gives a performance for the NParBR method that can be orders of magnitude faster in comparison to other commonly used non-rigid registration methods while operating at full spatial resolution with comparable or better accuracy [6]. The method has been tested on the particular case of lungs registration proposed by the EMPIRE10 challenge and has shown good results in several datasets. References 1. Hadjidemetriou, E., Grossberg, M.D., Nayar, S.K.: Histogram preserving image transformations. International Journal of Computer Vision 45(1), 5 23 (2001) 2. Hill, D.L., Studholme, C., Hawkes, D.J.: Voxel similarity measures for automated image registration. In: Proc. of SPIE, vol pp International Society for Optics and Photonics (1994) 3. Ibanez, L., Schroeder, W., Ng, L., Cates, J.: The ITK Software Guide. Kitware, Inc. ISBN , second edn. (2005) 4. Murphy, K., Van Ginneken, B., Reinhardt, J.M., Kabus, S., Ding, K., Deng, X., Cao, K., Du, K., Christensen, G.E., Garcia, V., et al.: Evaluation of registration methods on thoracic CT: the EMPIRE10 challenge. IEEE Trans. on Medical Imaging 30(11), (2011) 5. Pilutti, D., Strumia, M., Büchert, M., Hadjidemetriou, S.: Non-parametric Bayesian registration (NParBR) of body tumors in DCE-MRI data. IEEE Trans. on Medical Imaging, under revision 6. Pilutti, D., Strumia, M., Hadjidemetriou, S.: Bi-modal non-rigid registration of brain MRI data with deconvolution of joint statistics. IEEE Trans. on Image Processing (2014) 7. van Rikxoort, E.M., de Hoop, B., Viergever, M.A., Prokop, M., van Ginneken, B.: Automatic lung segmentation from thoracic computed tomography scans using a hybrid approach with error detection. Medical Physics 36(7), (2009)

9 8. Rohlfing, T.: Image similarity and tissue overlaps as surrogates for image registration accuracy: widely used but unreliable. IEEE Trans. on Medical Imaging 31(2), (2012) 9. Simoncelli, E.P., Adelson, E.H.: Noise removal via Bayesian wavelet coring. In: Proc. of IEEE ICIP. vol. 1, pp (1996) 10. Sled, J.G., Zijdenbos, A.P., Evans, A.C.: A non-parametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans. on Medical Imaging 17(1), (1998) 11. Studholme, C., Hill, D.L., Hawkes, D.J.: Using voxel similarity as a measure of medical image registration. In: Proc. of BMVC. pp (1994)

Image Registration. Prof. Dr. Lucas Ferrari de Oliveira UFPR Informatics Department

Image Registration. Prof. Dr. Lucas Ferrari de Oliveira UFPR Informatics Department Image Registration Prof. Dr. Lucas Ferrari de Oliveira UFPR Informatics Department Introduction Visualize objects inside the human body Advances in CS methods to diagnosis, treatment planning and medical

More information

Variational Lung Registration With Explicit Boundary Alignment

Variational Lung Registration With Explicit Boundary Alignment Variational Lung Registration With Explicit Boundary Alignment Jan Rühaak and Stefan Heldmann Fraunhofer MEVIS, Project Group Image Registration Maria-Goeppert-Str. 1a, 23562 Luebeck, Germany {jan.ruehaak,stefan.heldmann}@mevis.fraunhofer.de

More information

Automatic Generation of Training Data for Brain Tissue Classification from MRI

Automatic Generation of Training Data for Brain Tissue Classification from MRI MICCAI-2002 1 Automatic Generation of Training Data for Brain Tissue Classification from MRI Chris A. Cocosco, Alex P. Zijdenbos, and Alan C. Evans McConnell Brain Imaging Centre, Montreal Neurological

More information

Methodological progress in image registration for ventilation estimation, segmentation propagation and multi-modal fusion

Methodological progress in image registration for ventilation estimation, segmentation propagation and multi-modal fusion Methodological progress in image registration for ventilation estimation, segmentation propagation and multi-modal fusion Mattias P. Heinrich Julia A. Schnabel, Mark Jenkinson, Sir Michael Brady 2 Clinical

More information

Nonrigid Registration using Free-Form Deformations

Nonrigid Registration using Free-Form Deformations Nonrigid Registration using Free-Form Deformations Hongchang Peng April 20th Paper Presented: Rueckert et al., TMI 1999: Nonrigid registration using freeform deformations: Application to breast MR images

More information

A Non-Linear Image Registration Scheme for Real-Time Liver Ultrasound Tracking using Normalized Gradient Fields

A Non-Linear Image Registration Scheme for Real-Time Liver Ultrasound Tracking using Normalized Gradient Fields A Non-Linear Image Registration Scheme for Real-Time Liver Ultrasound Tracking using Normalized Gradient Fields Lars König, Till Kipshagen and Jan Rühaak Fraunhofer MEVIS Project Group Image Registration,

More information

Annales UMCS Informatica AI 1 (2003) UMCS. Registration of CT and MRI brain images. Karol Kuczyński, Paweł Mikołajczak

Annales UMCS Informatica AI 1 (2003) UMCS. Registration of CT and MRI brain images. Karol Kuczyński, Paweł Mikołajczak Annales Informatica AI 1 (2003) 149-156 Registration of CT and MRI brain images Karol Kuczyński, Paweł Mikołajczak Annales Informatica Lublin-Polonia Sectio AI http://www.annales.umcs.lublin.pl/ Laboratory

More information

A Model-Independent, Multi-Image Approach to MR Inhomogeneity Correction

A Model-Independent, Multi-Image Approach to MR Inhomogeneity Correction Tina Memo No. 2007-003 Published in Proc. MIUA 2007 A Model-Independent, Multi-Image Approach to MR Inhomogeneity Correction P. A. Bromiley and N.A. Thacker Last updated 13 / 4 / 2007 Imaging Science and

More information

8/3/2017. Contour Assessment for Quality Assurance and Data Mining. Objective. Outline. Tom Purdie, PhD, MCCPM

8/3/2017. Contour Assessment for Quality Assurance and Data Mining. Objective. Outline. Tom Purdie, PhD, MCCPM Contour Assessment for Quality Assurance and Data Mining Tom Purdie, PhD, MCCPM Objective Understand the state-of-the-art in contour assessment for quality assurance including data mining-based techniques

More information

Non-Rigid Multimodal Medical Image Registration using Optical Flow and Gradient Orientation

Non-Rigid Multimodal Medical Image Registration using Optical Flow and Gradient Orientation M. HEINRICH et al.: MULTIMODAL REGISTRATION USING GRADIENT ORIENTATION 1 Non-Rigid Multimodal Medical Image Registration using Optical Flow and Gradient Orientation Mattias P. Heinrich 1 mattias.heinrich@eng.ox.ac.uk

More information

Spatio-Temporal Registration of Biomedical Images by Computational Methods

Spatio-Temporal Registration of Biomedical Images by Computational Methods Spatio-Temporal Registration of Biomedical Images by Computational Methods Francisco P. M. Oliveira, João Manuel R. S. Tavares tavares@fe.up.pt, www.fe.up.pt/~tavares Outline 1. Introduction 2. Spatial

More information

Atlas Based Segmentation of the prostate in MR images

Atlas Based Segmentation of the prostate in MR images Atlas Based Segmentation of the prostate in MR images Albert Gubern-Merida and Robert Marti Universitat de Girona, Computer Vision and Robotics Group, Girona, Spain {agubern,marly}@eia.udg.edu Abstract.

More information

MR IMAGE SEGMENTATION

MR IMAGE SEGMENTATION MR IMAGE SEGMENTATION Prepared by : Monil Shah What is Segmentation? Partitioning a region or regions of interest in images such that each region corresponds to one or more anatomic structures Classification

More information

ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N.

ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N. ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N. Dartmouth, MA USA Abstract: The significant progress in ultrasonic NDE systems has now

More information

HST.582J / 6.555J / J Biomedical Signal and Image Processing Spring 2007

HST.582J / 6.555J / J Biomedical Signal and Image Processing Spring 2007 MIT OpenCourseWare http://ocw.mit.edu HST.582J / 6.555J / 16.456J Biomedical Signal and Image Processing Spring 2007 For information about citing these materials or our Terms of Use, visit: http://ocw.mit.edu/terms.

More information

Deformable Registration Using Scale Space Keypoints

Deformable Registration Using Scale Space Keypoints Deformable Registration Using Scale Space Keypoints Mehdi Moradi a, Purang Abolmaesoumi a,b and Parvin Mousavi a a School of Computing, Queen s University, Kingston, Ontario, Canada K7L 3N6; b Department

More information

Medicale Image Analysis

Medicale Image Analysis Medicale Image Analysis Registration Validation Prof. Dr. Philippe Cattin MIAC, University of Basel Prof. Dr. Philippe Cattin: Registration Validation Contents 1 Validation 1.1 Validation of Registration

More information

Adaptive Local Multi-Atlas Segmentation: Application to Heart Segmentation in Chest CT Scans

Adaptive Local Multi-Atlas Segmentation: Application to Heart Segmentation in Chest CT Scans Adaptive Local Multi-Atlas Segmentation: Application to Heart Segmentation in Chest CT Scans Eva M. van Rikxoort, Ivana Isgum, Marius Staring, Stefan Klein and Bram van Ginneken Image Sciences Institute,

More information

Non-Rigid Image Registration III

Non-Rigid Image Registration III Non-Rigid Image Registration III CS6240 Multimedia Analysis Leow Wee Kheng Department of Computer Science School of Computing National University of Singapore Leow Wee Kheng (CS6240) Non-Rigid Image Registration

More information

1 Introduction Motivation and Aims Functional Imaging Computational Neuroanatomy... 12

1 Introduction Motivation and Aims Functional Imaging Computational Neuroanatomy... 12 Contents 1 Introduction 10 1.1 Motivation and Aims....... 10 1.1.1 Functional Imaging.... 10 1.1.2 Computational Neuroanatomy... 12 1.2 Overview of Chapters... 14 2 Rigid Body Registration 18 2.1 Introduction.....

More information

Automatic Vascular Tree Formation Using the Mahalanobis Distance

Automatic Vascular Tree Formation Using the Mahalanobis Distance Automatic Vascular Tree Formation Using the Mahalanobis Distance Julien Jomier, Vincent LeDigarcher, and Stephen R. Aylward Computer-Aided Diagnosis and Display Lab, Department of Radiology The University

More information

Non-rigid Image Registration

Non-rigid Image Registration Overview Non-rigid Image Registration Introduction to image registration - he goal of image registration - Motivation for medical image registration - Classification of image registration - Nonrigid registration

More information

RIGID IMAGE REGISTRATION

RIGID IMAGE REGISTRATION RIGID IMAGE REGISTRATION Duygu Tosun-Turgut, Ph.D. Center for Imaging of Neurodegenerative Diseases Department of Radiology and Biomedical Imaging duygu.tosun@ucsf.edu What is registration? Image registration

More information

Segmentation Using a Region Growing Thresholding

Segmentation Using a Region Growing Thresholding Segmentation Using a Region Growing Thresholding Matei MANCAS 1, Bernard GOSSELIN 1, Benoît MACQ 2 1 Faculté Polytechnique de Mons, Circuit Theory and Signal Processing Laboratory Bâtiment MULTITEL/TCTS

More information

3-D Compounding of B-Scan Ultrasound Images

3-D Compounding of B-Scan Ultrasound Images 3-D Compounding of B-Scan Ultrasound Images Jochen F. Krücker, Charles R. Meyer, Theresa A. Tuthill, Gerald L. LeCarpentier, J. Brian Fowlkes, Paul L. Carson University of Michigan, Dept. of Radiology,

More information

Intraoperative Prostate Tracking with Slice-to-Volume Registration in MR

Intraoperative Prostate Tracking with Slice-to-Volume Registration in MR Intraoperative Prostate Tracking with Slice-to-Volume Registration in MR Sean Gill a, Purang Abolmaesumi a,b, Siddharth Vikal a, Parvin Mousavi a and Gabor Fichtinger a,b,* (a) School of Computing, Queen

More information

A Duality Based Algorithm for TV-L 1 -Optical-Flow Image Registration

A Duality Based Algorithm for TV-L 1 -Optical-Flow Image Registration A Duality Based Algorithm for TV-L 1 -Optical-Flow Image Registration Thomas Pock 1, Martin Urschler 1, Christopher Zach 2, Reinhard Beichel 3, and Horst Bischof 1 1 Institute for Computer Graphics & Vision,

More information

Tomographic Reconstruction

Tomographic Reconstruction Tomographic Reconstruction 3D Image Processing Torsten Möller Reading Gonzales + Woods, Chapter 5.11 2 Overview Physics History Reconstruction basic idea Radon transform Fourier-Slice theorem (Parallel-beam)

More information

Biomedical Imaging Registration Trends and Applications. Francisco P. M. Oliveira, João Manuel R. S. Tavares

Biomedical Imaging Registration Trends and Applications. Francisco P. M. Oliveira, João Manuel R. S. Tavares Biomedical Imaging Registration Trends and Applications Francisco P. M. Oliveira, João Manuel R. S. Tavares tavares@fe.up.pt, www.fe.up.pt/~tavares Outline 1. Introduction 2. Spatial Registration of (2D

More information

Automatic Generation of Training Data for Brain Tissue Classification from MRI

Automatic Generation of Training Data for Brain Tissue Classification from MRI Automatic Generation of Training Data for Brain Tissue Classification from MRI Chris A. COCOSCO, Alex P. ZIJDENBOS, and Alan C. EVANS http://www.bic.mni.mcgill.ca/users/crisco/ McConnell Brain Imaging

More information

3/27/2012 WHY SPECT / CT? SPECT / CT Basic Principles. Advantages of SPECT. Advantages of CT. Dr John C. Dickson, Principal Physicist UCLH

3/27/2012 WHY SPECT / CT? SPECT / CT Basic Principles. Advantages of SPECT. Advantages of CT. Dr John C. Dickson, Principal Physicist UCLH 3/27/212 Advantages of SPECT SPECT / CT Basic Principles Dr John C. Dickson, Principal Physicist UCLH Institute of Nuclear Medicine, University College London Hospitals and University College London john.dickson@uclh.nhs.uk

More information

Norbert Schuff VA Medical Center and UCSF

Norbert Schuff VA Medical Center and UCSF Norbert Schuff Medical Center and UCSF Norbert.schuff@ucsf.edu Medical Imaging Informatics N.Schuff Course # 170.03 Slide 1/67 Objective Learn the principle segmentation techniques Understand the role

More information

Interactive Deformable Registration Visualization and Analysis of 4D Computed Tomography

Interactive Deformable Registration Visualization and Analysis of 4D Computed Tomography Interactive Deformable Registration Visualization and Analysis of 4D Computed Tomography Burak Erem 1, Gregory C. Sharp 2, Ziji Wu 2, and David Kaeli 1 1 Department of Electrical and Computer Engineering,

More information

Is deformable image registration a solved problem?

Is deformable image registration a solved problem? Is deformable image registration a solved problem? Marcel van Herk On behalf of the imaging group of the RT department of NKI/AVL Amsterdam, the Netherlands DIR 1 Image registration Find translation.deformation

More information

Biomedical Image Analysis based on Computational Registration Methods. João Manuel R. S. Tavares

Biomedical Image Analysis based on Computational Registration Methods. João Manuel R. S. Tavares Biomedical Image Analysis based on Computational Registration Methods João Manuel R. S. Tavares tavares@fe.up.pt, www.fe.up.pt/~tavares Outline 1. Introduction 2. Methods a) Spatial Registration of (2D

More information

Image Segmentation and Registration

Image Segmentation and Registration Image Segmentation and Registration Dr. Christine Tanner (tanner@vision.ee.ethz.ch) Computer Vision Laboratory, ETH Zürich Dr. Verena Kaynig, Machine Learning Laboratory, ETH Zürich Outline Segmentation

More information

A Study of Medical Image Analysis System

A Study of Medical Image Analysis System Indian Journal of Science and Technology, Vol 8(25), DOI: 10.17485/ijst/2015/v8i25/80492, October 2015 ISSN (Print) : 0974-6846 ISSN (Online) : 0974-5645 A Study of Medical Image Analysis System Kim Tae-Eun

More information

Optical Flow Estimation

Optical Flow Estimation Optical Flow Estimation Goal: Introduction to image motion and 2D optical flow estimation. Motivation: Motion is a rich source of information about the world: segmentation surface structure from parallax

More information

REAL-TIME ADAPTIVITY IN HEAD-AND-NECK AND LUNG CANCER RADIOTHERAPY IN A GPU ENVIRONMENT

REAL-TIME ADAPTIVITY IN HEAD-AND-NECK AND LUNG CANCER RADIOTHERAPY IN A GPU ENVIRONMENT REAL-TIME ADAPTIVITY IN HEAD-AND-NECK AND LUNG CANCER RADIOTHERAPY IN A GPU ENVIRONMENT Anand P Santhanam Assistant Professor, Department of Radiation Oncology OUTLINE Adaptive radiotherapy for head and

More information

Introduction to Image Super-resolution. Presenter: Kevin Su

Introduction to Image Super-resolution. Presenter: Kevin Su Introduction to Image Super-resolution Presenter: Kevin Su References 1. S.C. Park, M.K. Park, and M.G. KANG, Super-Resolution Image Reconstruction: A Technical Overview, IEEE Signal Processing Magazine,

More information

Lesion Segmentation and Bias Correction in Breast Ultrasound B-mode Images Including Elastography Information

Lesion Segmentation and Bias Correction in Breast Ultrasound B-mode Images Including Elastography Information Lesion Segmentation and Bias Correction in Breast Ultrasound B-mode Images Including Elastography Information Gerard Pons a, Joan Martí a, Robert Martí a, Mariano Cabezas a, Andrew di Battista b, and J.

More information

2 Michael E. Leventon and Sarah F. F. Gibson a b c d Fig. 1. (a, b) Two MR scans of a person's knee. Both images have high resolution in-plane, but ha

2 Michael E. Leventon and Sarah F. F. Gibson a b c d Fig. 1. (a, b) Two MR scans of a person's knee. Both images have high resolution in-plane, but ha Model Generation from Multiple Volumes using Constrained Elastic SurfaceNets Michael E. Leventon and Sarah F. F. Gibson 1 MIT Artificial Intelligence Laboratory, Cambridge, MA 02139, USA leventon@ai.mit.edu

More information

Non-rigid Registration using Discrete MRFs: Application to Thoracic CT Images

Non-rigid Registration using Discrete MRFs: Application to Thoracic CT Images Non-rigid Registration using Discrete MRFs: Application to Thoracic CT Images Ben Glocker 1, Nikos Komodakis 2, Nikos Paragios 3,4, and Nassir Navab 1 1 Computer Aided Medical Procedures (CAMP), TU Mï

More information

Knowledge-Based Segmentation of Brain MRI Scans Using the Insight Toolkit

Knowledge-Based Segmentation of Brain MRI Scans Using the Insight Toolkit Knowledge-Based Segmentation of Brain MRI Scans Using the Insight Toolkit John Melonakos 1, Ramsey Al-Hakim 1, James Fallon 2 and Allen Tannenbaum 1 1 Georgia Institute of Technology, Atlanta GA 30332,

More information

ECSE 626 Project Report Multimodality Image Registration by Maximization of Mutual Information

ECSE 626 Project Report Multimodality Image Registration by Maximization of Mutual Information ECSE 626 Project Report Multimodality Image Registration by Maximization of Mutual Information Emmanuel Piuze McGill University Montreal, Qc, Canada. epiuze@cim.mcgill.ca Abstract In 1997, Maes et al.

More information

Methods for data preprocessing

Methods for data preprocessing Methods for data preprocessing John Ashburner Wellcome Trust Centre for Neuroimaging, 12 Queen Square, London, UK. Overview Voxel-Based Morphometry Morphometry in general Volumetrics VBM preprocessing

More information

Preprocessing II: Between Subjects John Ashburner

Preprocessing II: Between Subjects John Ashburner Preprocessing II: Between Subjects John Ashburner Pre-processing Overview Statistics or whatever fmri time-series Anatomical MRI Template Smoothed Estimate Spatial Norm Motion Correct Smooth Coregister

More information

Hybrid Spline-based Multimodal Registration using a Local Measure for Mutual Information

Hybrid Spline-based Multimodal Registration using a Local Measure for Mutual Information Hybrid Spline-based Multimodal Registration using a Local Measure for Mutual Information Andreas Biesdorf 1, Stefan Wörz 1, Hans-Jürgen Kaiser 2, Karl Rohr 1 1 University of Heidelberg, BIOQUANT, IPMB,

More information

Automatic Lung Surface Registration Using Selective Distance Measure in Temporal CT Scans

Automatic Lung Surface Registration Using Selective Distance Measure in Temporal CT Scans Automatic Lung Surface Registration Using Selective Distance Measure in Temporal CT Scans Helen Hong 1, Jeongjin Lee 2, Kyung Won Lee 3, and Yeong Gil Shin 2 1 School of Electrical Engineering and Computer

More information

Multi-atlas labeling with population-specific template and non-local patch-based label fusion

Multi-atlas labeling with population-specific template and non-local patch-based label fusion Multi-atlas labeling with population-specific template and non-local patch-based label fusion Vladimir Fonov, Pierrick Coupé, Simon Eskildsen, Jose Manjon, Louis Collins To cite this version: Vladimir

More information

ABSTRACT 1. INTRODUCTION 2. METHODS

ABSTRACT 1. INTRODUCTION 2. METHODS Finding Seeds for Segmentation Using Statistical Fusion Fangxu Xing *a, Andrew J. Asman b, Jerry L. Prince a,c, Bennett A. Landman b,c,d a Department of Electrical and Computer Engineering, Johns Hopkins

More information

The Anatomical Equivalence Class Formulation and its Application to Shape-based Computational Neuroanatomy

The Anatomical Equivalence Class Formulation and its Application to Shape-based Computational Neuroanatomy The Anatomical Equivalence Class Formulation and its Application to Shape-based Computational Neuroanatomy Sokratis K. Makrogiannis, PhD From post-doctoral research at SBIA lab, Department of Radiology,

More information

Sampling-Based Ensemble Segmentation against Inter-operator Variability

Sampling-Based Ensemble Segmentation against Inter-operator Variability Sampling-Based Ensemble Segmentation against Inter-operator Variability Jing Huo 1, Kazunori Okada, Whitney Pope 1, Matthew Brown 1 1 Center for Computer vision and Imaging Biomarkers, Department of Radiological

More information

MEDICAL IMAGE COMPUTING (CAP 5937) LECTURE 4: Pre-Processing Medical Images (II)

MEDICAL IMAGE COMPUTING (CAP 5937) LECTURE 4: Pre-Processing Medical Images (II) SPRING 2016 1 MEDICAL IMAGE COMPUTING (CAP 5937) LECTURE 4: Pre-Processing Medical Images (II) Dr. Ulas Bagci HEC 221, Center for Research in Computer Vision (CRCV), University of Central Florida (UCF),

More information

Correspondence Detection Using Wavelet-Based Attribute Vectors

Correspondence Detection Using Wavelet-Based Attribute Vectors Correspondence Detection Using Wavelet-Based Attribute Vectors Zhong Xue, Dinggang Shen, and Christos Davatzikos Section of Biomedical Image Analysis, Department of Radiology University of Pennsylvania,

More information

Registration by continuous optimisation. Stefan Klein Erasmus MC, the Netherlands Biomedical Imaging Group Rotterdam (BIGR)

Registration by continuous optimisation. Stefan Klein Erasmus MC, the Netherlands Biomedical Imaging Group Rotterdam (BIGR) Registration by continuous optimisation Stefan Klein Erasmus MC, the Netherlands Biomedical Imaging Group Rotterdam (BIGR) Registration = optimisation C t x t y 1 Registration = optimisation C t x t y

More information

Object Identification in Ultrasound Scans

Object Identification in Ultrasound Scans Object Identification in Ultrasound Scans Wits University Dec 05, 2012 Roadmap Introduction to the problem Motivation Related Work Our approach Expected Results Introduction Nowadays, imaging devices like

More information

Coupling of surface roughness to the performance of computer-generated holograms

Coupling of surface roughness to the performance of computer-generated holograms Coupling of surface roughness to the performance of computer-generated holograms Ping Zhou* and Jim Burge College of Optical Sciences, University of Arizona, Tucson, Arizona 85721, USA *Corresponding author:

More information

Probabilistic Tracking and Model-based Segmentation of 3D Tubular Structures

Probabilistic Tracking and Model-based Segmentation of 3D Tubular Structures Probabilistic Tracking and Model-based Segmentation of 3D Tubular Structures Stefan Wörz, William J. Godinez, Karl Rohr University of Heidelberg, BIOQUANT, IPMB, and DKFZ Heidelberg, Dept. Bioinformatics

More information

Rigid and Deformable Vasculature-to-Image Registration : a Hierarchical Approach

Rigid and Deformable Vasculature-to-Image Registration : a Hierarchical Approach Rigid and Deformable Vasculature-to-Image Registration : a Hierarchical Approach Julien Jomier and Stephen R. Aylward Computer-Aided Diagnosis and Display Lab The University of North Carolina at Chapel

More information

Hierarchical Shape Statistical Model for Segmentation of Lung Fields in Chest Radiographs

Hierarchical Shape Statistical Model for Segmentation of Lung Fields in Chest Radiographs Hierarchical Shape Statistical Model for Segmentation of Lung Fields in Chest Radiographs Yonghong Shi 1 and Dinggang Shen 2,*1 1 Digital Medical Research Center, Fudan University, Shanghai, 232, China

More information

Multi-Modal Volume Registration Using Joint Intensity Distributions

Multi-Modal Volume Registration Using Joint Intensity Distributions Multi-Modal Volume Registration Using Joint Intensity Distributions Michael E. Leventon and W. Eric L. Grimson Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA leventon@ai.mit.edu

More information

2D Rigid Registration of MR Scans using the 1d Binary Projections

2D Rigid Registration of MR Scans using the 1d Binary Projections 2D Rigid Registration of MR Scans using the 1d Binary Projections Panos D. Kotsas Abstract This paper presents the application of a signal intensity independent registration criterion for 2D rigid body

More information

Registration Techniques

Registration Techniques EMBO Practical Course on Light Sheet Microscopy Junior-Prof. Dr. Olaf Ronneberger Computer Science Department and BIOSS Centre for Biological Signalling Studies University of Freiburg Germany O. Ronneberger,

More information

Image Registration + Other Stuff

Image Registration + Other Stuff Image Registration + Other Stuff John Ashburner Pre-processing Overview fmri time-series Motion Correct Anatomical MRI Coregister m11 m 21 m 31 m12 m13 m14 m 22 m 23 m 24 m 32 m 33 m 34 1 Template Estimate

More information

Respiratory Motion Compensation for C-arm CT Liver Imaging

Respiratory Motion Compensation for C-arm CT Liver Imaging Respiratory Motion Compensation for C-arm CT Liver Imaging Aline Sindel 1, Marco Bögel 1,2, Andreas Maier 1,2, Rebecca Fahrig 3, Joachim Hornegger 1,2, Arnd Dörfler 4 1 Pattern Recognition Lab, FAU Erlangen-Nürnberg

More information

A Radiometry Tolerant Method for Direct 3D/2D Registration of Computed Tomography Data to X-ray Images

A Radiometry Tolerant Method for Direct 3D/2D Registration of Computed Tomography Data to X-ray Images A Radiometry Tolerant Method for Direct 3D/2D Registration of Computed Tomography Data to X-ray Images Transfer Function Independent Registration Boris Peter Selby 1, Georgios Sakas 2, Stefan Walter 1,

More information

Translation Symmetry Detection: A Repetitive Pattern Analysis Approach

Translation Symmetry Detection: A Repetitive Pattern Analysis Approach 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops Translation Symmetry Detection: A Repetitive Pattern Analysis Approach Yunliang Cai and George Baciu GAMA Lab, Department of Computing

More information

Neuroimaging and mathematical modelling Lesson 2: Voxel Based Morphometry

Neuroimaging and mathematical modelling Lesson 2: Voxel Based Morphometry Neuroimaging and mathematical modelling Lesson 2: Voxel Based Morphometry Nivedita Agarwal, MD Nivedita.agarwal@apss.tn.it Nivedita.agarwal@unitn.it Volume and surface morphometry Brain volume White matter

More information

Elastic Registration with Partial Data

Elastic Registration with Partial Data Elastic Registration with Partial Data Senthil Periaswamy and Hany Farid Dartmouth College, Hanover, NH, 03755, USA Abstract. We have developed a general purpose registration algorithm for medical images

More information

A Registration-Based Atlas Propagation Framework for Automatic Whole Heart Segmentation

A Registration-Based Atlas Propagation Framework for Automatic Whole Heart Segmentation A Registration-Based Atlas Propagation Framework for Automatic Whole Heart Segmentation Xiahai Zhuang (PhD) Centre for Medical Image Computing University College London Fields-MITACS Conference on Mathematics

More information

Computational Neuroanatomy

Computational Neuroanatomy Computational Neuroanatomy John Ashburner john@fil.ion.ucl.ac.uk Smoothing Motion Correction Between Modality Co-registration Spatial Normalisation Segmentation Morphometry Overview fmri time-series kernel

More information

Introduction to Medical Image Processing

Introduction to Medical Image Processing Introduction to Medical Image Processing Δ Essential environments of a medical imaging system Subject Image Analysis Energy Imaging System Images Image Processing Feature Images Image processing may be

More information

Multi-modal Image Registration Using the Generalized Survival Exponential Entropy

Multi-modal Image Registration Using the Generalized Survival Exponential Entropy Multi-modal Image Registration Using the Generalized Survival Exponential Entropy Shu Liao and Albert C.S. Chung Lo Kwee-Seong Medical Image Analysis Laboratory, Department of Computer Science and Engineering,

More information

Accurate Image Registration from Local Phase Information

Accurate Image Registration from Local Phase Information Accurate Image Registration from Local Phase Information Himanshu Arora, Anoop M. Namboodiri, and C.V. Jawahar Center for Visual Information Technology, IIIT, Hyderabad, India { himanshu@research., anoop@,

More information

VALIDATION OF DIR. Raj Varadhan, PhD, DABMP Minneapolis Radiation Oncology

VALIDATION OF DIR. Raj Varadhan, PhD, DABMP Minneapolis Radiation Oncology VALIDATION OF DIR Raj Varadhan, PhD, DABMP Minneapolis Radiation Oncology Overview Basics: Registration Framework, Theory Discuss Validation techniques Using Synthetic CT data & Phantoms What metrics to

More information

Fast CT-CT Fluoroscopy Registration with Respiratory Motion Compensation for Image-Guided Lung Intervention

Fast CT-CT Fluoroscopy Registration with Respiratory Motion Compensation for Image-Guided Lung Intervention Fast CT-CT Fluoroscopy Registration with Respiratory Motion Compensation for Image-Guided Lung Intervention Po Su a,b, Zhong Xue b*, Kongkuo Lu c, Jianhua Yang a, Stephen T. Wong b a School of Automation,

More information

Registration: Rigid vs. Deformable

Registration: Rigid vs. Deformable Lecture 20 Deformable / Non-Rigid Registration ch. 11 of Insight into Images edited by Terry Yoo, et al. Spring 2017 16-725 (CMU RI) : BioE 2630 (Pitt) Dr. John Galeotti The content of these slides by

More information

An ITK Filter for Bayesian Segmentation: itkbayesianclassifierimagefilter

An ITK Filter for Bayesian Segmentation: itkbayesianclassifierimagefilter An ITK Filter for Bayesian Segmentation: itkbayesianclassifierimagefilter John Melonakos 1, Karthik Krishnan 2 and Allen Tannenbaum 1 1 Georgia Institute of Technology, Atlanta GA 30332, USA {jmelonak,

More information

EECS 556 Image Processing W 09. Interpolation. Interpolation techniques B splines

EECS 556 Image Processing W 09. Interpolation. Interpolation techniques B splines EECS 556 Image Processing W 09 Interpolation Interpolation techniques B splines What is image processing? Image processing is the application of 2D signal processing methods to images Image representation

More information

Local Image Registration: An Adaptive Filtering Framework

Local Image Registration: An Adaptive Filtering Framework Local Image Registration: An Adaptive Filtering Framework Gulcin Caner a,a.murattekalp a,b, Gaurav Sharma a and Wendi Heinzelman a a Electrical and Computer Engineering Dept.,University of Rochester, Rochester,

More information

Bayesian Spherical Wavelet Shrinkage: Applications to Shape Analysis

Bayesian Spherical Wavelet Shrinkage: Applications to Shape Analysis Bayesian Spherical Wavelet Shrinkage: Applications to Shape Analysis Xavier Le Faucheur a, Brani Vidakovic b and Allen Tannenbaum a a School of Electrical and Computer Engineering, b Department of Biomedical

More information

Introduction to fmri. Pre-processing

Introduction to fmri. Pre-processing Introduction to fmri Pre-processing Tibor Auer Department of Psychology Research Fellow in MRI Data Types Anatomical data: T 1 -weighted, 3D, 1/subject or session - (ME)MPRAGE/FLASH sequence, undistorted

More information

Department of ECE, SCSVMV University, Kanchipuram

Department of ECE, SCSVMV University, Kanchipuram Medical Image Registering: A Matlab Based Approach [1] Dr.K.Umapathy, [2] D.Vedasri, [3] H.Vaishnavi [1] Associate Professor, [2][3] UG Student, Department of ECE, SCSVMV University, Kanchipuram Abstract:-

More information

Automatic Subthalamic Nucleus Targeting for Deep Brain Stimulation. A Validation Study

Automatic Subthalamic Nucleus Targeting for Deep Brain Stimulation. A Validation Study Automatic Subthalamic Nucleus Targeting for Deep Brain Stimulation. A Validation Study F. Javier Sánchez Castro a, Claudio Pollo a,b, Jean-Guy Villemure b, Jean-Philippe Thiran a a École Polytechnique

More information

Robust Lung Ventilation Assessment

Robust Lung Ventilation Assessment Fifth International Workshop on Pulmonary Image Analysis -75- Robust Lung Ventilation Assessment Sven Kabus 1, Tobias Klinder 1, Tokihiro Yamamoto 2, Paul J. Keall 3, Billy W. Loo, Jr. 4, and Cristian

More information

MEDICAL IMAGE ANALYSIS

MEDICAL IMAGE ANALYSIS SECOND EDITION MEDICAL IMAGE ANALYSIS ATAM P. DHAWAN g, A B IEEE Engineering in Medicine and Biology Society, Sponsor IEEE Press Series in Biomedical Engineering Metin Akay, Series Editor +IEEE IEEE PRESS

More information

Broad field that includes low-level operations as well as complex high-level algorithms

Broad field that includes low-level operations as well as complex high-level algorithms Image processing About Broad field that includes low-level operations as well as complex high-level algorithms Low-level image processing Computer vision Computational photography Several procedures and

More information

Separate CT-Reconstruction for Orientation and Position Adaptive Wavelet Denoising

Separate CT-Reconstruction for Orientation and Position Adaptive Wavelet Denoising Separate CT-Reconstruction for Orientation and Position Adaptive Wavelet Denoising Anja Borsdorf 1,, Rainer Raupach, Joachim Hornegger 1 1 Chair for Pattern Recognition, Friedrich-Alexander-University

More information

Transitive and Symmetric Nonrigid Image Registration. Yi-Yu Chou

Transitive and Symmetric Nonrigid Image Registration. Yi-Yu Chou Transitive and Symmetric Nonrigid Image Registration A Thesis Presented to The Academic Faculty by Yi-Yu Chou In Partial Fulfillment of the Requirements for the Degree Master of Science School of Biomedical

More information

Application of level set based method for segmentation of blood vessels in angiography images

Application of level set based method for segmentation of blood vessels in angiography images Lodz University of Technology Faculty of Electrical, Electronic, Computer and Control Engineering Institute of Electronics PhD Thesis Application of level set based method for segmentation of blood vessels

More information

Biomedical Image Processing

Biomedical Image Processing Biomedical Image Processing Jason Thong Gabriel Grant 1 2 Motivation from the Medical Perspective MRI, CT and other biomedical imaging devices were designed to assist doctors in their diagnosis and treatment

More information

Brilliance CT Big Bore.

Brilliance CT Big Bore. 1 2 2 There are two methods of RCCT acquisition in widespread clinical use: cine axial and helical. In RCCT with cine axial acquisition, repeat CT images are taken each couch position while recording respiration.

More information

Performance Evaluation of the TINA Medical Image Segmentation Algorithm on Brainweb Simulated Images

Performance Evaluation of the TINA Medical Image Segmentation Algorithm on Brainweb Simulated Images Tina Memo No. 2008-003 Internal Memo Performance Evaluation of the TINA Medical Image Segmentation Algorithm on Brainweb Simulated Images P. A. Bromiley Last updated 20 / 12 / 2007 Imaging Science and

More information

Knowledge-Based Segmentation of Brain MRI Scans Using the Insight Toolkit

Knowledge-Based Segmentation of Brain MRI Scans Using the Insight Toolkit Knowledge-Based Segmentation of Brain MRI Scans Using the Insight Toolkit John Melonakos 1, Ramsey Al-Hakim 1, James Fallon 2 and Allen Tannenbaum 1 1 Georgia Institute of Technology, Atlanta GA 30332,

More information

3D Registration based on Normalized Mutual Information

3D Registration based on Normalized Mutual Information 3D Registration based on Normalized Mutual Information Performance of CPU vs. GPU Implementation Florian Jung, Stefan Wesarg Interactive Graphics Systems Group (GRIS), TU Darmstadt, Germany stefan.wesarg@gris.tu-darmstadt.de

More information

A Generic Framework for Non-rigid Registration Based on Non-uniform Multi-level Free-Form Deformations

A Generic Framework for Non-rigid Registration Based on Non-uniform Multi-level Free-Form Deformations A Generic Framework for Non-rigid Registration Based on Non-uniform Multi-level Free-Form Deformations Julia A. Schnabel 1, Daniel Rueckert 2, Marcel Quist 3, Jane M. Blackall 1, Andy D. Castellano-Smith

More information

Find the Correspondences

Find the Correspondences Advanced Topics in BioImage Analysis - 3. Find the Correspondences from Registration to Motion Estimation CellNetworks Math-Clinic Qi Gao 03.02.2017 Math-Clinic core facility Provide services on bioinformatics

More information

INVARIANT CORNER DETECTION USING STEERABLE FILTERS AND HARRIS ALGORITHM

INVARIANT CORNER DETECTION USING STEERABLE FILTERS AND HARRIS ALGORITHM INVARIANT CORNER DETECTION USING STEERABLE FILTERS AND HARRIS ALGORITHM ABSTRACT Mahesh 1 and Dr.M.V.Subramanyam 2 1 Research scholar, Department of ECE, MITS, Madanapalle, AP, India vka4mahesh@gmail.com

More information

A multi-atlas approach for prostate segmentation in MR images

A multi-atlas approach for prostate segmentation in MR images A multi-atlas approach for prostate segmentation in MR images Geert Litjens, Nico Karssemeijer, and Henkjan Huisman Diagnostic Image Analysis Group, Radboud University Nijmegen Medical Centre, Nijmegen,

More information