Global-to-Local Shape Matching for Liver Segmentation in CT Imaging

Size: px
Start display at page:

Download "Global-to-Local Shape Matching for Liver Segmentation in CT Imaging"

Transcription

1 Global-to-Local Shape Matching for Liver Segmentation in CT Imaging Kinda Anna Saddi 1,2, Mikaël Rousson 1, Christophe Chefd hotel 1, and Farida Cheriet 2 1 Department of Imaging and Visualization, Siemens Corporate Research, Princeton, NJ, USA. 2 Department of Computer Engineering, École Polytechnique of Montréal, Canada. Abstract. We propose a two-stage algorithm to segment the liver in CT images. First, we estimate the pose and global shape properties using a statistical shape model defined in the low dimensional space spanned by a training set of shapes. Then, we apply a template matching procedure to recover local deformations that were not present in the learning set. In both steps, we optimize the same image term: the likelihood of the intensity inside the region of interest and its background. The method requires a single seed point inside the liver for the initialization. We show that this global-to-local strategy is able to recover livers with peculiar shapes in arbitrary poses. 1 Introduction Medical computer-aided diagnosis based on computed tomography (CT have gained significant attention. Such a procedure typically requires the extraction of anatomical structures. In particular, current methods for liver diagnosis involve its boundary extraction. This task is quite challenging because the liver tissue and other adjacent organs are characterized by very similar densities (Hounsfield unit in CT images. Moreover, partial-volume effects make the observation of intensity discontinuities difficult (weak edges. To resolve this lack of information, shape models can be employed, but again, difficulties arise due to the large interpatient liver shape variability. While most liver segmentation tools available to clinicians still require a time-consuming human interaction, several authors have proposed to automate this process in order to make it usable in clinical applications. In [1], Soler et al. presented a cascading segmentation framework that sequentially detects different hepatic structures for surgery planning where the liver is extracted by deforming globally and locally a given template according to [2]. In [3], Park et al. used a probabilistic atlas to classify voxel intensities in abdominal CT images. More recently, a trend toward the use of 3D shape models has emerged. For example, Lamecker et al. built in [4] a statistical shape model composed of 43 segmented livers and used a modified Active Shape Model (ASM [5] for segmentation. A similar approach was considered by Heimann et al. in [6] where T. Heimann, M. Styner, B. van Ginneken (Eds.: 3D Segmentation in The Clinic: A Grand Challenge, pp , 2007.

2 a shape constrained deformable model [7] was chosen rather than the usual ASM fitting approach. This allowed them to capture shape variations that was not present in the training set. A detailed validation shows the improvement in accuracy with respect to ASM. This illustrates that relying too much on a prior shape model gives robust segmentation algorithms but generally has low accuracy. This is due to the large inter-patient shape variability of the liver which cannot be modeled from a reduced number of training samples. In practice, each liver shape has a particular geometry, only global shape characteristics remain consistent from one patient to another. Following this observation, we propose to separate the extraction of the liver in two phases: (i we estimate the pose and the global shape of the liver according to a prior shape model following [8], (ii we deform locally this initial solution using a template matching algorithm like in [9]. Both of these steps are formulated in a variational framework minimizing the same cost function on the image. In Section 2.1, we describe the region-based image term used to fit the shape model and to estimate local deformations. In Section 2.2, we present the shape model and its integration for segmentation. In Section 2.3, we detail the template matching method used to recover local deformations. Finally, in Section 3, we present several results and comparisons showing the robustness and the accuracy of our global-to-local strategy. 2 Method 2.1 Statistical Region-Based Model Let I : Ω R be the image to segment. We define p in (i and p out (i as the probability density functions of a random variable modeling intensity values i in the regions inside and outside the liver. Given this model, the optimal closed boundary Γ can be obtained using a maximum likelihood principle, minimizing the following energy as initially proposed by Zhu and Yuille in [10]: ( E data (Γ = χ(x, Γ log p in (I(x + (1 χ(x, Γ log p out (I(x dx, (1 Ω where χ(x, Γ = 1 if x is inside Γ and 0 otherwise. The intensity distributions p in (i and p out (i are estimated dynamically during the optimization process according to the intensity histograms inside each region for fixed positions of the boundary. There are different strategies to minimize this energy and obtain a region segmentation. A direct solution is to evolve a level set representation of the boundary like in [10] but, as we will see in the experiments, this has several drawbacks in our application. In this work, we propose an alternative minimization by first constraining Γ with a given shape model (Section 2.2 and then using a template registration formulation (Section 2.3 to refine locally the solution. 208

3 2.2 Shape Model In this section, we propose to constrain the boundary Γ by a shape model learned from a set of manually segmented images. Given a set of training shapes encoded by their signed distance functions {φ i } i=1..n, Tsai et al. [11] proposed to reduce the segmentation problem to a finite-dimensional optimization by constraining the problem to the subspace spanned by the training shapes. We make use of this compact representation of the embedding function. Given the distance d on the space of signed distance functions defined by: d 2 (φ 1, φ 2 = Ω (φ 1(x φ 2 (x 2 dx, we align the set of training shapes with respect to translation and rotation. Subsequently, we constrain the level set representation φ of the boundary Γ to a parametric representation of the form 3 : φα(x = φ 0 + n α i V i (x, (2 i=1 where φ 0 (x = 1 N N i=1 φ i(x represents the mean shape, {V i (x} i=1..n are the eigenmodes, and n < N is the dimension of the subspace spanned by the N training shapes. We can now represent each training shape φ i by its corresponding shape vector α i. In this notation, the goal of statistical shape learning is to infer a statistical distribution P(α from these sample shapes. Following [8], we consider a nonparametric density approximation: P(α = 1 Nσ N ( α αi K σ i=1, where K(u = 1 2π exp ( u2. (3 2 Constraining the boundary Γ to this subspace, Γ can be represented by a shape vector α, i.e. Γ is the zero crossing of the level set function φα. Introducing the parameters h R 3 and θ [0, 2π] 3 to model translation and rotation of the shape, we can express χ(θx + h, Γ as H(φα(θx + h, with H the Heaviside function. Using the short hand H φ = H(φα(θx + h, we can rewrite Eq. 1 as: ( E data (α, h, θ = H φ log p in (I(x + (1 H φ log p out (I(x dx, (4 Ω We incorporate the prior on the distribution of the shape vector α in the energy. This drives us to our final criteria: E(α, h, θ = log P(α + E data (α, h, θ (5 This energy is minimized using alternated gradient descents with respect to each unknown parameters α, h and θ. The detailed equations of these gradient descents and their implementations can be found in [8]. 3 Γ is defined as the zero crossing of the level set function φ defined in the image domain. 209

4 2.3 Template Matching To refine the segmentation, we propose a template matching algorithm that recovers local deformations of the shape obtained in the previous section. Let us consider the registration framework, we formulate the problem as finding a transformation ψ : Ω Ω that minimizes the cost functional E data (I T ψ defined in (Eq. 1, where I T (x = χ(x, Γ is the shape represented by a binary template obtained in the Section 2.2. Thus, we minimize the following energy: ( E data (I T ψ = (I T ψ log p in (I(x+(1 I T ψ log p out (I(x dx. (6 Ω In this equation, I T ψ is the warped binary template and the composition operator. Since we want to find an optimal transformation ψ, the derivation of the energy leads to the following gradient descent: E data (I T ψ ψ ( = (I T ψ log p in(i(x p out (I(x. (7 In non-rigid registration, deriving this energy according to a high-dimensional transformation results in a vector field v. To guarantee a well-posed problem, this vector field has to be regularized. For this purpose, different techniques have been proposed. The approach proposed by Christensen et al. [12] solves the registration problem using a partial differential equation and has the advantage of capturing large deformations. In this work, we use a Gaussian filtering that can be seen as a variant of the fluid-approach [12]. To find the optimal high-dimensional transformation, we build a sequence of transformations (ψ k k=0,...,+, by composition of small displacements [13], ψ k+1 = ψ k (ψ id + αv k, ψ 0 = ψ id, (8 where ψ id is the identity transformation and v k is a velocity vector field that follows the gradient of the cost functional to be minimized. Here, v k is obtained by computing the variational gradient of the cost functional given in Eq. 7. We regularize the gradient v k using a fast recursive filtering technique. This approximates a Gaussian smoothing [14] that has proven very efficient in practice. The previous iterative scheme (Eq. 8 is repeated until convergence, and can be seen as the discretization (via Taylor expansion of the transport equation in the Eulerian frame: ψ t t = Dψ t v, ψ 0 = ψ id, (9 where Dψ t stands for the Jacobian matrix of ψ t. Here, large deformations are possible because the regularization is applied to the velocity rather than the deformation (Dupuis et al. [15] detail the suitable regularity conditions on the velocity field to generate a diffeomorphism. As mentioned in Section 2.1, the region statistics are computed dynamically as the algorithm iterates. This algorithm is embedded in a coarse-to-fine strategy. 210

5 This reduces the computational cost by working with less data at lower resolutions. This also allows us to recover large displacements, and helps avoiding local minima. In this work, we used five levels of multi-resolutions. 3 Experimental Results To quantify the segmentation accuracy, we compare our results to a groundtruth. In this work, we examine 30 CT images 4 that have been manually segmented by radiological experts, working slice-by-slice in transversal view. A segmentation is defined as the entire liver tissue including all internal structures. Among these images, twenty segmentations are available for training. The other ten images are used for testing. All images are enhanced with contrast agent and most of them are pathological. In our approach, the shape model is composed of 50 segmented livers (including the 20 training images described above. The algorithm is initialized by giving one seed point inside the liver. This single point is sufficient for the initialization and does not have to be the center of mass (our algorithm has been proven robust to the initialization point. We use 30 modes of variation for the shape model. For the template matching, the regularization parameter σ is 2.0, and the number of iterations for the multi-resolution are 0, 16, 32, 48 and 16 (from high to low resolution. We compare our segmentation results to the ground-truth using five metrics: the volumetric overlap, the relative absolute volume difference, the average symmetric absolute surface distance, the symmetric RMS surface distance and the maximum symmetric absolute surface distance. These metrics are evaluated by assigning a score to each test case 5. We also compare our approach (Method A to two alternatives. The first one considers the model fitting described in Section 2.2 followed by an unconstrained level set evolution [16] (Method B. The second one uses the mean shape of the liver as initialization for the template matching described in Section 2.3 (Method C. We applied these three methods to the training images. Table 1 shows the score for every image in the training set (numbers in bold correspond to the highest score. Method A B C Table 1. Scores on the training images for the: A shape model and template matching, B shape model and level set evolution, and C mean shape and the template matching. 4 Data provided by MICCAI Workshop on 3D Segmentation in the Clinic. 5 For details see 211

6 Method Overlap Error Volume Diff. Avg. Dist RMS Dist Max. Dist. Total [%] Score [%] Score [mm] Score [mm] Score [mm] Score Score A B C Table 2. Average metrics and corresponding average scores on the 20 training cases for: A shape model and template matching, B shape model and level set evolution, and C mean shape and the template matching. Table 2 illustrates the average metrics and scores of these methods. It shows that our approach gives overall better quantitative results than the other two. Contrary to the level set approach (Method B, we apply the regularization to the deformation field. This allows us to segment irregular shapes, that would be impossible with surface evolution techniques. We decorrelate the regularization from the intrinsic geometry of the template, which allows us to recover irregular shapes while avoiding leaks. We also validate our approach on 10 test cases (not included in the shape model. Table 3 shows the metrics and the scores compared to the ground-truth. Figure 1 shows the results of three different segmentations. It includes an easy, an average and a hard case in 3 views (sagittal, coronal and transversal. We observe that our approach scores 76 points for the case 1, which means that it performed roughly as good as a human. The lowest score is 54 and corresponds to an image with a tumor (case 3 which is considered as a hard case. Since our algorithm relies on the intensity distribution inside the liver, it cannot include the whole tumor in the segmentation. Dataset Overlap Error Volume Diff. Avg. Dist RMS Dist Max. Dist. Total [%] Score [%] Score [mm] Score [mm] Score [mm] Score Score Average Table 3. Results of the comparison metrics and corresponding scores for all ten test cases. 212

7 Fig. 1. From left to right, a sagittal, coronal and transversal slice from a relatively easy case (1, top, an average case (4, middle, and a relatively difficult case (3, bottom. The outline of the reference standard segmentation is in red, the outline of the segmentation of the method described in this paper is in blue. Slices are displayed with a window of 400 and a level of 70. Approximate computation time is 324 seconds per image in average on a 2GHz dual-core Intel processor. This can be reduced (if necessary for clinical application if a lower accuracy is acceptable. 4 Conclusion We demonstrated that our global-to-local strategy succeeds generally better than two competitive approaches. The shape-based step allowed us to estimate the pose and the global shape properties of the liver with good robustness. Then, the non-rigid shape matching was able to recover local shape properties. In addition to a global regularization on the shape, our non-rigid template registration method has the advantage of preserving the topology of the liver even for large shape variations. Promising results were presented on wide range of images, some with problematic attributes like developed tumors. Further improvement are of course still possible. In particular, by considering explicitly the tumors and detecting them in parallel to the liver segmentation. 213

8 References 1. Soler, L., Delingette, H., Malandain, G., Montagnat, J., Ayache, N., Koehl, C., Dourthe, O., Malassagne, B., Smith, M., Mutter, D., Marescaux, J.: Fully automatic anatomical, pathological, and functional segmentation from CT scans for hepatic surgery. Computed Aided Surgery 6(3 ( Montagnat, J., Delingette, H.: Volumetric medical images segmentation using shape constrained deformable models. In: CVRMed. ( Park, H., Bland, P., Meyer, C.: Construction of an abdominal probabilistic atlas and its application in segmentation. IEEE Trans. on Medical Imaging 22(4 ( Lamecker, H., Lange, T., Seeba, M.: Segmentation of the liver using a 3D statistical shape model. ZIB Preprint ( Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models : their training and application. Comput. Vis. Image Underst. 61(1 ( Heimann, T., Wolf, I., Meinzer, H.P.: Active shape models for a fully automated 3d segmentation of the liver - an evaluation on clinical data. In: Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Volume 2. ( Weese, J., Kaus, M., Lorenz, C., Lobregt, S., Truyen, R., Pekar, V.: Shape constrained deformable models for 3d medical image segmentation. In: Proceedings of the Conference on Information Processing in Medical Imaging. ( Rousson, M., Cremers, D.: Efficient kernel density estimation of shape and intensity priors for level set segmentation. In: Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Volume 2. ( Saddi, K.A., Chefd hotel, C., Rousson, M., Cheriet, F.: Region-based segmentation via non-rigid template matching. In: Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA 07, Rio de Janeiro, Brazil (2007 In Press 10. Zhu, S.C., Yuille, A.L.: Region competition: Unifying snakes, region growing, and bayes/mdl for multiband image segmentation. IEEE Trans. and Pattern Analysis and Machine Intelligence 18(9 ( Tsai, A., Yezzi, A.J., Wells, W.M., Tempany, C., Tucker, D., Fan, A., Grimson, W.E.L., Willsky, A.S.: A shape-based approach to the segmentation of medical imagery using level sets. IEEE Trans. on Medical Imaging 22(2 ( Christensen, G.E., Rabbitt, R.D., Miller, M.I.: Deformable templates using large deformation kinematics. IEEE Trans. on Image Processing 5(10 ( Chefd hotel, C., Hermosillo, G., Faugeras, O.: Flows of diffeomorphisms for multimodal image registration. In: Proceedings of the IEEE International Symposium on Biomedical Imaging. ( Deriche, R.: Recursively implementing the gaussian and its derivatives. In: Proceedings of the International Conference on Image Processing, Singapore ( Dupuis, P., Grenander, U., Miller, M.: Variational problems on flows of diffeomorphisms for image matching. Quarterly of Applied Mathematics LVI(3 ( Vese, L., Chan, T.: A multiphase level set framework for image segmentation using the Mumford and Shah model. International Journal of Computer Vision 50 (

Marginal Space Learning for Efficient Detection of 2D/3D Anatomical Structures in Medical Images

Marginal Space Learning for Efficient Detection of 2D/3D Anatomical Structures in Medical Images Marginal Space Learning for Efficient Detection of 2D/3D Anatomical Structures in Medical Images Yefeng Zheng, Bogdan Georgescu, and Dorin Comaniciu Integrated Data Systems Department, Siemens Corporate

More information

Universities of Leeds, Sheffield and York

Universities of Leeds, Sheffield and York promoting access to White Rose research papers Universities of Leeds, Sheffield and York http://eprints.whiterose.ac.uk/ This is an author produced version of a paper published in Lecture Notes in Computer

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

A Generic Probabilistic Active Shape Model for Organ Segmentation

A Generic Probabilistic Active Shape Model for Organ Segmentation A Generic Probabilistic Active Shape Model for Organ Segmentation Andreas Wimmer 1,2, Grzegorz Soza 2, and Joachim Hornegger 1 1 Chair of Pattern Recognition, Department of Computer Science, Friedrich-Alexander

More information

Implicit Active Shape Models for 3D Segmentation in MR Imaging

Implicit Active Shape Models for 3D Segmentation in MR Imaging Implicit Active Shape Models for 3D Segmentation in MR Imaging Mikaël Rousson 1, Nikos Paragios 2, and Rachid Deriche 1 1 I.N.R.I.A. Sophia Antipolis, France E-mail: {Mikael.Rousson,Rachid.Deriche}@sophia.inria.fr

More information

EFFICIENT KERNEL DENSITY ESTIMATION OF SHAPE AND INTENSITY PRIORS FOR LEVEL SET SEGMENTATION

EFFICIENT KERNEL DENSITY ESTIMATION OF SHAPE AND INTENSITY PRIORS FOR LEVEL SET SEGMENTATION 13 EFFICIENT KERNEL DENSITY ESTIMATION OF SHAPE AND INTENSITY PRIORS FOR LEVEL SET SEGMENTATION Daniel Cremers Department of Computer Science, University of Bonn Bonn, Germany Mikael Rousson Department

More information

City, University of London Institutional Repository

City, University of London Institutional Repository City Research Online City, University of London Institutional Repository Citation: Doan, H., Slabaugh, G.G., Unal, G.B. & Fang, T. (2006). Semi-Automatic 3-D Segmentation of Anatomical Structures of Brain

More information

NIH Public Access Author Manuscript Proc Soc Photo Opt Instrum Eng. Author manuscript; available in PMC 2014 October 07.

NIH Public Access Author Manuscript Proc Soc Photo Opt Instrum Eng. Author manuscript; available in PMC 2014 October 07. NIH Public Access Author Manuscript Published in final edited form as: Proc Soc Photo Opt Instrum Eng. 2014 March 21; 9034: 903442. doi:10.1117/12.2042915. MRI Brain Tumor Segmentation and Necrosis Detection

More information

Fully Automatic Multi-organ Segmentation based on Multi-boost Learning and Statistical Shape Model Search

Fully Automatic Multi-organ Segmentation based on Multi-boost Learning and Statistical Shape Model Search Fully Automatic Multi-organ Segmentation based on Multi-boost Learning and Statistical Shape Model Search Baochun He, Cheng Huang, Fucang Jia Shenzhen Institutes of Advanced Technology, Chinese Academy

More information

Interactive Image Segmentation Using Level Sets and Dempster-Shafer Theory of Evidence

Interactive Image Segmentation Using Level Sets and Dempster-Shafer Theory of Evidence Interactive Image Segmentation Using Level Sets and Dempster-Shafer Theory of Evidence Björn Scheuermann and Bodo Rosenhahn Leibniz Universität Hannover, Germany {scheuermann,rosenhahn}@tnt.uni-hannover.de

More information

ADAPTIVE GRAPH CUTS WITH TISSUE PRIORS FOR BRAIN MRI SEGMENTATION

ADAPTIVE GRAPH CUTS WITH TISSUE PRIORS FOR BRAIN MRI SEGMENTATION ADAPTIVE GRAPH CUTS WITH TISSUE PRIORS FOR BRAIN MRI SEGMENTATION Abstract: MIP Project Report Spring 2013 Gaurav Mittal 201232644 This is a detailed report about the course project, which was to implement

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

Landmark-based 3D Elastic Registration of Pre- and Postoperative Liver CT Data

Landmark-based 3D Elastic Registration of Pre- and Postoperative Liver CT Data Landmark-based 3D Elastic Registration of Pre- and Postoperative Liver CT Data An Experimental Comparison Thomas Lange 1, Stefan Wörz 2, Karl Rohr 2, Peter M. Schlag 3 1 Experimental and Clinical Research

More information

College of Engineering, Trivandrum.

College of Engineering, Trivandrum. Analysis of CT Liver Images Using Level Sets with Bayesian Analysis-A Hybrid Approach Sajith A.G 1, Dr. Hariharan.S 2 1 Research Scholar, 2 Professor, Department of Electrical&Electronics Engineering College

More information

Liver Segmentation in CT Data: A Segmentation Refinement Approach

Liver Segmentation in CT Data: A Segmentation Refinement Approach Liver Segmentation in CT Data: A Segmentation Refinement Approach Reinhard Beichel 12, Christian Bauer 3, Alexander Bornik 3, Erich Sorantin 4, and Horst Bischof 3 1 Dept. of Electrical and Computer Engineering,

More information

Automatic Clinical Image Segmentation using Pathological Modelling, PCA and SVM

Automatic Clinical Image Segmentation using Pathological Modelling, PCA and SVM Automatic Clinical Image Segmentation using Pathological Modelling, PCA and SVM Shuo Li 1, Thomas Fevens 1, Adam Krzyżak 1, and Song Li 2 1 Medical Imaging Group, Department of Computer Science and Software

More information

Genetic Adaptation of Level Sets Parameters for Medical Imaging Segmentation

Genetic Adaptation of Level Sets Parameters for Medical Imaging Segmentation Genetic Adaptation of Level Sets Parameters for Medical Imaging Segmentation Dário A. B. Oliveira & Raul Q. Feitosa Catholic University of Rio de Janeiro, Brazil Mauro M. Correia Department of Surgery,

More information

Integrated Approaches to Non-Rigid Registration in Medical Images

Integrated Approaches to Non-Rigid Registration in Medical Images Work. on Appl. of Comp. Vision, pg 102-108. 1 Integrated Approaches to Non-Rigid Registration in Medical Images Yongmei Wang and Lawrence H. Staib + Departments of Electrical Engineering and Diagnostic

More information

NIH Public Access Author Manuscript Comput Med Imaging Graph. Author manuscript; available in PMC 2010 November 4.

NIH Public Access Author Manuscript Comput Med Imaging Graph. Author manuscript; available in PMC 2010 November 4. NIH Public Access Author Manuscript Published in final edited form as: Comput Med Imaging Graph. 2010 June ; 34(4): 298 307. doi:10.1016/j.compmedimag.2009.12.001. Nonparametric joint shape learning for

More information

Segmentation in Noisy Medical Images Using PCA Model Based Particle Filtering

Segmentation in Noisy Medical Images Using PCA Model Based Particle Filtering Segmentation in Noisy Medical Images Using PCA Model Based Particle Filtering Wei Qu a, Xiaolei Huang b, and Yuanyuan Jia c a Siemens Medical Solutions USA Inc., AX Division, Hoffman Estates, IL 60192;

More information

Bioimage Informatics

Bioimage Informatics Bioimage Informatics Lecture 13, Spring 2012 Bioimage Data Analysis (IV) Image Segmentation (part 2) Lecture 13 February 29, 2012 1 Outline Review: Steger s line/curve detection algorithm Intensity thresholding

More information

A Multiple-Layer Flexible Mesh Template Matching Method for Nonrigid Registration between a Pelvis Model and CT Images

A Multiple-Layer Flexible Mesh Template Matching Method for Nonrigid Registration between a Pelvis Model and CT Images A Multiple-Layer Flexible Mesh Template Matching Method for Nonrigid Registration between a Pelvis Model and CT Images Jianhua Yao 1, Russell Taylor 2 1. Diagnostic Radiology Department, Clinical Center,

More information

Kernel Density Estimation and Intrinsic Alignment for Knowledge-driven Segmentation: Teaching Level Sets to Walk

Kernel Density Estimation and Intrinsic Alignment for Knowledge-driven Segmentation: Teaching Level Sets to Walk C. Rasmussen et al. (Eds.), Pattern Recognition, Tübingen, Sept. 2004. LNCS Vol. 3175, pp. 36 44. c Springer Kernel Density Estimation and Intrinsic Alignment for Knowledge-driven Segmentation: Teaching

More information

Anatomical structures segmentation by spherical 3D ray casting and gradient domain editing

Anatomical structures segmentation by spherical 3D ray casting and gradient domain editing Anatomical structures segmentation by spherical 3D ray casting and gradient domain editing A. Kronman 1, L. Joskowicz 1, and J. Sosna 2 1 School of Eng. and Computer Science, The Hebrew Univ. of Jerusalem,

More information

3D Statistical Shape Model Building using Consistent Parameterization

3D Statistical Shape Model Building using Consistent Parameterization 3D Statistical Shape Model Building using Consistent Parameterization Matthias Kirschner, Stefan Wesarg Graphisch Interaktive Systeme, TU Darmstadt matthias.kirschner@gris.tu-darmstadt.de Abstract. We

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

Level-set MCMC Curve Sampling and Geometric Conditional Simulation

Level-set MCMC Curve Sampling and Geometric Conditional Simulation Level-set MCMC Curve Sampling and Geometric Conditional Simulation Ayres Fan John W. Fisher III Alan S. Willsky February 16, 2007 Outline 1. Overview 2. Curve evolution 3. Markov chain Monte Carlo 4. Curve

More information

Level Set Evolution with Region Competition: Automatic 3-D Segmentation of Brain Tumors

Level Set Evolution with Region Competition: Automatic 3-D Segmentation of Brain Tumors 1 Level Set Evolution with Region Competition: Automatic 3-D Segmentation of Brain Tumors 1 Sean Ho, 2 Elizabeth Bullitt, and 1,3 Guido Gerig 1 Department of Computer Science, 2 Department of Surgery,

More information

Comparison of Vessel Segmentations using STAPLE

Comparison of Vessel Segmentations using STAPLE Comparison of Vessel Segmentations using STAPLE Julien Jomier, Vincent LeDigarcher, and Stephen R. Aylward Computer-Aided Diagnosis and Display Lab The University of North Carolina at Chapel Hill, Department

More information

Comparison of Vessel Segmentations Using STAPLE

Comparison of Vessel Segmentations Using STAPLE Comparison of Vessel Segmentations Using STAPLE Julien Jomier, Vincent LeDigarcher, and Stephen R. Aylward Computer-Aided Diagnosis and Display Lab, The University of North Carolina at Chapel Hill, Department

More information

Automated segmentation methods for liver analysis in oncology applications

Automated segmentation methods for liver analysis in oncology applications University of Szeged Department of Image Processing and Computer Graphics Automated segmentation methods for liver analysis in oncology applications Ph. D. Thesis László Ruskó Thesis Advisor Dr. Antal

More information

An Automated Image-based Method for Multi-Leaf Collimator Positioning Verification in Intensity Modulated Radiation Therapy

An Automated Image-based Method for Multi-Leaf Collimator Positioning Verification in Intensity Modulated Radiation Therapy An Automated Image-based Method for Multi-Leaf Collimator Positioning Verification in Intensity Modulated Radiation Therapy Chenyang Xu 1, Siemens Corporate Research, Inc., Princeton, NJ, USA Xiaolei Huang,

More information

Pathology Hinting as the Combination of Automatic Segmentation with a Statistical Shape Model

Pathology Hinting as the Combination of Automatic Segmentation with a Statistical Shape Model Pathology Hinting as the Combination of Automatic Segmentation with a Statistical Shape Model Pascal A. Dufour 1,2, Hannan Abdillahi 3, Lala Ceklic 3, Ute Wolf-Schnurrbusch 2,3, and Jens Kowal 1,2 1 ARTORG

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

Fully Automatic Model Creation for Object Localization utilizing the Generalized Hough Transform

Fully Automatic Model Creation for Object Localization utilizing the Generalized Hough Transform Fully Automatic Model Creation for Object Localization utilizing the Generalized Hough Transform Heike Ruppertshofen 1,2,3, Cristian Lorenz 2, Peter Beyerlein 4, Zein Salah 3, Georg Rose 3, Hauke Schramm

More information

Occluded Facial Expression Tracking

Occluded Facial Expression Tracking Occluded Facial Expression Tracking Hugo Mercier 1, Julien Peyras 2, and Patrice Dalle 1 1 Institut de Recherche en Informatique de Toulouse 118, route de Narbonne, F-31062 Toulouse Cedex 9 2 Dipartimento

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

LIVER cancer has been among the 6 most common. Automatic Liver Segmentation based on Shape Constraints and Deformable Graph Cut in CT Images

LIVER cancer has been among the 6 most common. Automatic Liver Segmentation based on Shape Constraints and Deformable Graph Cut in CT Images IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Automatic Liver Segmentation based on Shape Constraints and Deformable Graph Cut in CT Images Guodong Li #, Xinjian Chen #, Fei Shi, Weifang Zhu, Jie Tian*, Fellow,

More information

Pathology Hinting as the Combination of Automatic Segmentation with a Statistical Shape Model

Pathology Hinting as the Combination of Automatic Segmentation with a Statistical Shape Model Pathology Hinting as the Combination of Automatic Segmentation with a Statistical Shape Model Pascal A. Dufour 12,HannanAbdillahi 3, Lala Ceklic 3,Ute Wolf-Schnurrbusch 23,JensKowal 12 1 ARTORG Center

More information

Hierarchical, Learning-based Automatic Liver Segmentation

Hierarchical, Learning-based Automatic Liver Segmentation Hierarchical, Learning-based Automatic Liver Segmentation Haibin Ling 1, S. Kevin Zhou 1, Yefeng Zheng 1, Bogdan Georgescu 1 Michael Suehling 2, and Dorin Comaniciu 1 1 Integrated Data Systems Department

More information

Efficient Liver Segmentation exploiting Level-Set Speed Images with 2.5D Shape Propagation

Efficient Liver Segmentation exploiting Level-Set Speed Images with 2.5D Shape Propagation Efficient Liver Segmentation exploiting Level-Set Speed Images with 2.5D Shape Propagation Jeongjin Lee 1, Namkug Kim 2, Ho Lee 1, Joon Beom Seo 2, Hyung Jin Won 2, Yong Moon Shin 2, and Yeong Gil Shin

More information

Prostate Detection Using Principal Component Analysis

Prostate Detection Using Principal Component Analysis Prostate Detection Using Principal Component Analysis Aamir Virani (avirani@stanford.edu) CS 229 Machine Learning Stanford University 16 December 2005 Introduction During the past two decades, computed

More information

Probabilistic Registration of 3-D Medical Images

Probabilistic Registration of 3-D Medical Images Probabilistic Registration of 3-D Medical Images Mei Chen, Takeo Kanade, Dean Pomerleau, Jeff Schneider CMU-RI-TR-99-16 The Robotics Institute Carnegie Mellon University Pittsburgh, Pennsylvania 1513 July,

More information

AN essential part of any computer-aided surgery is planning

AN essential part of any computer-aided surgery is planning 1 A Model Based Validation Scheme for Organ Segmentation in CT Scan Volumes Hossein Badakhshannoory, Student Member, IEEE, and Parvaneh Saeedi, Member, IEEE Abstract In this work, we propose a novel approach

More information

Segmentation of Bony Structures with Ligament Attachment Sites

Segmentation of Bony Structures with Ligament Attachment Sites Segmentation of Bony Structures with Ligament Attachment Sites Heiko Seim 1, Hans Lamecker 1, Markus Heller 2, Stefan Zachow 1 1 Visualisierung und Datenanalyse, Zuse-Institut Berlin (ZIB), 14195 Berlin

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

Subcortical Structure Segmentation using Probabilistic Atlas Priors

Subcortical Structure Segmentation using Probabilistic Atlas Priors Subcortical Structure Segmentation using Probabilistic Atlas Priors Sylvain Gouttard 1, Martin Styner 1,2, Sarang Joshi 3, Brad Davis 2, Rachel G. Smith 1, Heather Cody Hazlett 1, Guido Gerig 1,2 1 Department

More information

A Systematic Analysis System for CT Liver Image Classification and Image Segmentation by Local Entropy Method

A Systematic Analysis System for CT Liver Image Classification and Image Segmentation by Local Entropy Method A Systematic Analysis System for CT Liver Image Classification and Image Segmentation by Local Entropy Method A.Anuja Merlyn 1, A.Anuba Merlyn 2 1 PG Scholar, Department of Computer Science and Engineering,

More information

Multiple Motion and Occlusion Segmentation with a Multiphase Level Set Method

Multiple Motion and Occlusion Segmentation with a Multiphase Level Set Method Multiple Motion and Occlusion Segmentation with a Multiphase Level Set Method Yonggang Shi, Janusz Konrad, W. Clem Karl Department of Electrical and Computer Engineering Boston University, Boston, MA 02215

More information

Local or Global Minima: Flexible Dual-Front Active Contours

Local or Global Minima: Flexible Dual-Front Active Contours Local or Global Minima: Flexible Dual-Front Active Contours Hua Li 1,2 and Anthony Yezzi 1 1 School of ECE, Georgia Institute of Technology, Atlanta, GA, USA 2 Dept. of Elect. & Info. Eng., Huazhong Univ.

More information

A Level Set Based Predictor-Corrector Algorithm for Vessel Segmentation

A Level Set Based Predictor-Corrector Algorithm for Vessel Segmentation A Level Set Based Predictor-Corrector Algorithm for Vessel Segmentation Weixian Yan, Tanchao Zhu, Yongming Xie, Wai-Man Pang, Jing Qin, Pheng-Ann Heng Shenzhen Institute of Advanced Integration Technology,

More information

Automated Segmentation Using a Fast Implementation of the Chan-Vese Models

Automated Segmentation Using a Fast Implementation of the Chan-Vese Models Automated Segmentation Using a Fast Implementation of the Chan-Vese Models Huan Xu, and Xiao-Feng Wang,,3 Intelligent Computation Lab, Hefei Institute of Intelligent Machines, Chinese Academy of Science,

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

Medical Image Analysis Active Shape Models

Medical Image Analysis Active Shape Models Medical Image Analysis Active Shape Models Mauricio Reyes, Ph.D. mauricio.reyes@istb.unibe.ch ISTB - Institute for Surgical Technology and Biomechanics University of Bern Lecture Overview! Statistical

More information

Learning-based Neuroimage Registration

Learning-based Neuroimage Registration Learning-based Neuroimage Registration Leonid Teverovskiy and Yanxi Liu 1 October 2004 CMU-CALD-04-108, CMU-RI-TR-04-59 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Abstract

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

SCIENCE & TECHNOLOGY

SCIENCE & TECHNOLOGY Pertanika J. Sci. & Technol. 26 (1): 309-316 (2018) SCIENCE & TECHNOLOGY Journal homepage: http://www.pertanika.upm.edu.my/ Application of Active Contours Driven by Local Gaussian Distribution Fitting

More information

MEDICAL IMAGE NOISE REDUCTION AND REGION CONTRAST ENHANCEMENT USING PARTIAL DIFFERENTIAL EQUATIONS

MEDICAL IMAGE NOISE REDUCTION AND REGION CONTRAST ENHANCEMENT USING PARTIAL DIFFERENTIAL EQUATIONS MEDICAL IMAGE NOISE REDUCTION AND REGION CONTRAST ENHANCEMENT USING PARTIAL DIFFERENTIAL EQUATIONS Miguel Alemán-Flores, Luis Álvarez-León Departamento de Informática y Sistemas, Universidad de Las Palmas

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

Segmentation of 3-D medical image data sets with a combination of region based initial segmentation and active surfaces

Segmentation of 3-D medical image data sets with a combination of region based initial segmentation and active surfaces Header for SPIE use Segmentation of 3-D medical image data sets with a combination of region based initial segmentation and active surfaces Regina Pohle, Thomas Behlau, Klaus D. Toennies Otto-von-Guericke

More information

Biomedical Image Processing for Human Elbow

Biomedical Image Processing for Human Elbow Biomedical Image Processing for Human Elbow Akshay Vishnoi, Sharad Mehta, Arpan Gupta Department of Mechanical Engineering Graphic Era University Dehradun, India akshaygeu001@gmail.com, sharadm158@gmail.com

More information

Cognition Network Technology for a Fully Automated 3D Segmentation of Liver

Cognition Network Technology for a Fully Automated 3D Segmentation of Liver Cognition Network Technology for a Fully Automated 3D Segmentation of Liver Günter Schmidt, Maria Athelogou, Ralf Schönmeyer, Rene Korn, and Gerd Binnig Definiens AG, Research, Trappentreustr. 1, 80339

More information

Semi-automatic Segmentation of Vertebral Bodies in Volumetric MR Images Using a Statistical Shape+Pose Model

Semi-automatic Segmentation of Vertebral Bodies in Volumetric MR Images Using a Statistical Shape+Pose Model Semi-automatic Segmentation of Vertebral Bodies in Volumetric MR Images Using a Statistical Shape+Pose Model A. Suzani, A. Rasoulian S. Fels, R. N. Rohling P. Abolmaesumi Robotics and Control Laboratory,

More information

Efficient population registration of 3D data

Efficient population registration of 3D data Efficient population registration of 3D data Lilla Zöllei 1, Erik Learned-Miller 2, Eric Grimson 1, William Wells 1,3 1 Computer Science and Artificial Intelligence Lab, MIT; 2 Dept. of Computer Science,

More information

Extract Object Boundaries in Noisy Images using Level Set. Literature Survey

Extract Object Boundaries in Noisy Images using Level Set. Literature Survey Extract Object Boundaries in Noisy Images using Level Set by: Quming Zhou Literature Survey Submitted to Professor Brian Evans EE381K Multidimensional Digital Signal Processing March 15, 003 Abstract Finding

More information

Deformable Segmentation using Sparse Shape Representation. Shaoting Zhang

Deformable Segmentation using Sparse Shape Representation. Shaoting Zhang Deformable Segmentation using Sparse Shape Representation Shaoting Zhang Introduction Outline Our methods Segmentation framework Sparse shape representation Applications 2D lung localization in X-ray 3D

More information

Deep Learning Shape Priors for Object Segmentation

Deep Learning Shape Priors for Object Segmentation 2013 IEEE Conference on Computer Vision and Pattern Recognition Deep Learning Shape Priors for Object Segmentation Fei Chen a,c Huimin Yu a,b Roland Hu a Xunxun Zeng d a Department of Information Science

More information

Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information

Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information Mustafa Berkay Yilmaz, Hakan Erdogan, Mustafa Unel Sabanci University, Faculty of Engineering and Natural

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

Method of Background Subtraction for Medical Image Segmentation

Method of Background Subtraction for Medical Image Segmentation Method of Background Subtraction for Medical Image Segmentation Seongjai Kim Department of Mathematics and Statistics, Mississippi State University Mississippi State, MS 39762, USA and Hyeona Lim Department

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

Registration-Based Segmentation of Medical Images

Registration-Based Segmentation of Medical Images School of Computing National University of Singapore Graduate Research Paper Registration-Based Segmentation of Medical Images by Li Hao under guidance of A/Prof. Leow Wee Kheng July, 2006 Abstract Medical

More information

3D Surface Reconstruction of the Brain based on Level Set Method

3D Surface Reconstruction of the Brain based on Level Set Method 3D Surface Reconstruction of the Brain based on Level Set Method Shijun Tang, Bill P. Buckles, and Kamesh Namuduri Department of Computer Science & Engineering Department of Electrical Engineering University

More information

Collaborative Multi Organ Segmentation by Integrating Deformable and Graphical Models

Collaborative Multi Organ Segmentation by Integrating Deformable and Graphical Models Collaborative Multi Organ Segmentation by Integrating Deformable and Graphical Models Mustafa Gökhan Uzunbaş 1, Chao Chen 1, Shaoting Zhang 1, Kilian M. Pohl 2, Kang Li 3, and Dimitris Metaxas 1 1 CBIM,

More information

Ischemic Stroke Lesion Segmentation Proceedings 5th October 2015 Munich, Germany

Ischemic Stroke Lesion Segmentation   Proceedings 5th October 2015 Munich, Germany 0111010001110001101000100101010111100111011100100011011101110101101012 Ischemic Stroke Lesion Segmentation www.isles-challenge.org Proceedings 5th October 2015 Munich, Germany Preface Stroke is the second

More information

Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing

Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing Tomoyuki Nagahashi 1, Hironobu Fujiyoshi 1, and Takeo Kanade 2 1 Dept. of Computer Science, Chubu University. Matsumoto 1200,

More information

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter

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

Region Based Image Segmentation using a Modified Mumford-Shah Algorithm

Region Based Image Segmentation using a Modified Mumford-Shah Algorithm Region Based Image Segmentation using a Modified Mumford-Shah Algorithm Jung-ha An and Yunmei Chen 2 Institute for Mathematics and its Applications (IMA), University of Minnesota, USA, 2 Department of

More information

Automatic Logo Detection and Removal

Automatic Logo Detection and Removal Automatic Logo Detection and Removal Miriam Cha, Pooya Khorrami and Matthew Wagner Electrical and Computer Engineering Carnegie Mellon University Pittsburgh, PA 15213 {mcha,pkhorrami,mwagner}@ece.cmu.edu

More information

Sparse Shape Registration for Occluded Facial Feature Localization

Sparse Shape Registration for Occluded Facial Feature Localization Shape Registration for Occluded Facial Feature Localization Fei Yang, Junzhou Huang and Dimitris Metaxas Abstract This paper proposes a sparsity driven shape registration method for occluded facial feature

More information

Deformable Contour Method: A Constrained Optimization Approach

Deformable Contour Method: A Constrained Optimization Approach Deformable Contour Method: A Constrained Optimization Approach Xun Wang, Lei He, Chia Y. Han, William G. Wee Electrical & Computer Engineering and Computer Science Department University of Cincinnati,

More information

Hierarchical Multi structure Segmentation Guided by Anatomical Correlations

Hierarchical Multi structure Segmentation Guided by Anatomical Correlations Hierarchical Multi structure Segmentation Guided by Anatomical Correlations Oscar Alfonso Jiménez del Toro oscar.jimenez@hevs.ch Henning Müller henningmueller@hevs.ch University of Applied Sciences Western

More information

Kidney Segmentation in Ultrasound Images Using Curvelet Transform and Shape Prior

Kidney Segmentation in Ultrasound Images Using Curvelet Transform and Shape Prior 013 International Conference on Communication Systems and Network Technologies Kidney Segmentation in Ultrasound Images Using Curvelet Transform and Shape Prior Ehsan Jokar 1, Hossein Pourghassem Department

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

Geometrical Modeling of the Heart

Geometrical Modeling of the Heart Geometrical Modeling of the Heart Olivier Rousseau University of Ottawa The Project Goal: Creation of a precise geometrical model of the heart Applications: Numerical calculations Dynamic of the blood

More information

Multiphase Dynamic Labeling for Variational Recognition-Driven Image Segmentation

Multiphase Dynamic Labeling for Variational Recognition-Driven Image Segmentation Multiphase Dynamic Labeling for Variational Recognition-Driven Image Segmentation Daniel Cremers 1, Nir Sochen 2, and Christoph Schnörr 3 1 Department of Computer Science University of California, Los

More information

Implicit Active Contours Driven by Local Binary Fitting Energy

Implicit Active Contours Driven by Local Binary Fitting Energy Implicit Active Contours Driven by Local Binary Fitting Energy Chunming Li 1, Chiu-Yen Kao 2, John C. Gore 1, and Zhaohua Ding 1 1 Institute of Imaging Science 2 Department of Mathematics Vanderbilt University

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

Applying Catastrophe Theory to Image Segmentation

Applying Catastrophe Theory to Image Segmentation Applying Catastrophe Theory to Image Segmentation Mohamad Raad, Majd Ghareeb, Ali Bazzi Department of computer and communications engineering Lebanese International University Beirut, Lebanon Abstract

More information

A novel automatically initialized level set approach based on region correlation for lumbar vertebrae CT image segmentation

A novel automatically initialized level set approach based on region correlation for lumbar vertebrae CT image segmentation This full text paper was peer-reviewed at the direction of IEEE Instrumentation and Measurement Society prior to the acceptance and publication. A novel automatically initialized level set approach based

More information

Semi-Automatic Detection of Cervical Vertebrae in X-ray Images Using Generalized Hough Transform

Semi-Automatic Detection of Cervical Vertebrae in X-ray Images Using Generalized Hough Transform Semi-Automatic Detection of Cervical Vertebrae in X-ray Images Using Generalized Hough Transform Mohamed Amine LARHMAM, Saïd MAHMOUDI and Mohammed BENJELLOUN Faculty of Engineering, University of Mons,

More information

Shape-based Diffeomorphic Registration on Hippocampal Surfaces Using Beltrami Holomorphic Flow

Shape-based Diffeomorphic Registration on Hippocampal Surfaces Using Beltrami Holomorphic Flow Shape-based Diffeomorphic Registration on Hippocampal Surfaces Using Beltrami Holomorphic Flow Abstract. Finding meaningful 1-1 correspondences between hippocampal (HP) surfaces is an important but difficult

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

STATISTICS AND ANALYSIS OF SHAPE

STATISTICS AND ANALYSIS OF SHAPE Control and Cybernetics vol. 36 (2007) No. 2 Book review: STATISTICS AND ANALYSIS OF SHAPE by H. Krim, A. Yezzi, Jr., eds. There are numerous definitions of a notion of shape of an object. These definitions

More information

LOCAL-GLOBAL OPTICAL FLOW FOR IMAGE REGISTRATION

LOCAL-GLOBAL OPTICAL FLOW FOR IMAGE REGISTRATION LOCAL-GLOBAL OPTICAL FLOW FOR IMAGE REGISTRATION Ammar Zayouna Richard Comley Daming Shi Middlesex University School of Engineering and Information Sciences Middlesex University, London NW4 4BT, UK A.Zayouna@mdx.ac.uk

More information

STIC AmSud Project. Graph cut based segmentation of cardiac ventricles in MRI: a shape-prior based approach

STIC AmSud Project. Graph cut based segmentation of cardiac ventricles in MRI: a shape-prior based approach STIC AmSud Project Graph cut based segmentation of cardiac ventricles in MRI: a shape-prior based approach Caroline Petitjean A joint work with Damien Grosgeorge, Pr Su Ruan, Pr JN Dacher, MD October 22,

More information

Knowledge-Based Deformable Matching for Pathology Detection

Knowledge-Based Deformable Matching for Pathology Detection Knowledge-Based Deformable Matching for Pathology Detection Thesis Proposal Mei Chen CMU-RI-TR-97-20 The Robotics Institute Carnegie Mellon University Pittsburgh, Pennsylvania 15213 May 1997 c 1997 Carnegie

More information

Fast 3D Mean Shift Filter for CT Images

Fast 3D Mean Shift Filter for CT Images Fast 3D Mean Shift Filter for CT Images Gustavo Fernández Domínguez, Horst Bischof, and Reinhard Beichel Institute for Computer Graphics and Vision, Graz University of Technology Inffeldgasse 16/2, A-8010,

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