Automatic heart segmentation in CT: current and future applications

Size: px
Start display at page:

Download "Automatic heart segmentation in CT: current and future applications"

Transcription

1 Clinical applications Automatic heart segmentation in CT: current and future applications O. Ecabert J. Peters J.Weese Cristian Lorenz Jens von Berg M.J.Walker M.E. Olszewski M.Vembar Philips Research Europe, Aachen, Germany. Philips Research Europe, Hamburg, Germany. Philips Medical Systems, CT Clinical Science, Cleveland, USA. Cardiac CT is still the most challenging of all clinical applications. Robust automatic segmentation of the cardiac anatomy is a key enabler. 12 MEDICAMUNDI 50/3 2006/12 Computed Tomography (CT) is rapidly establishing itself as the non-invasive modality of choice for imaging the heart. Emerging clinical applications include CT guidance for electrophysiology procedures, planning for the correction of structural heart disease such as patent foramen ovale or septum defects, and percutaneous valve replacement. The introduction of spiral scanning in 1990 [1,2] provided high-resolution imaging within a single breath hold. The acquisition time was drastically reduced with the introduction of multislice scanners (4-channel in 1998, 16-channel in 2001, 40-channel in 2003 and 64-channel in 2004), thus paving the way for cardiac applications [3-9]. The cardiac region of interest can now be aquired in as little as six seconds. However, with the increase in the number of detector rows, the large amount of data generated poses a workflow and diagnostic challenge to the clinician, with potentially over 4000 axial images being generated for each cardiac study. In spite of the technical advances, cardiac CT is still the most challenging of all CT applications. The heart is continually moving, and the optimal cardiac phases have to be selected for reconstruction. Image characteristics are strongly influenced by inter- (and even intra-) patient variability in cardiac morphology, and individual patient s anatomy (heart rate, body mass index (BMI), shape, etc). Abnormalities, transplanted hearts, and hearts with pathology can present an unusual appearance. Acquisition protocols and reconstruction parameters have a direct repercussion on image quality. Good quality images require careful patient preparation and accurate timing of the contrast injection. Thus, there is a significant need for workflow support in routine clinical practice. Robust automatic segmentation of various structures of the cardiac anatomy is a key enabler for improving the clinical workflow. Segmentation refers to the identification of the various anatomical structures present in the image, with delineation of the boundaries or labeling of the voxels enclosed by the boundaries. Once segmentation has been performed, it is possible to extract clinical parameters such as ventricular mass, ejection fraction and wall thickness. Identification of the various cardiac structures also makes it to retrieve and display any desired view virtually instantaneously. Consequently, automatic segmentation can significantly reduce the scan-to-diagnosis time, thus helping the clinicians to reach the fundamental goal of efficient patient management. This article presents a fully automatic cardiac segmentation algorithm, and describes its use in current and emerging cardiac applications. The segmentation approach comprises two phases: a learning phase and the actual segmentation process. In the first phase, a wealth of anatomical and technical information is acquired from a representative set of data, yielding a basic cardiac model (Figure 1). During the segmentation process, the heart is first automatically detected and then the boundaries of the heart in the image are matched to the model, resulting in accurate labeling of the anatomical structures. Heart model Figure 1 shows the heart model used for segmentation. The geometry is described by a multi-compartmental mesh consisting of 15,000 triangles [10,11]. The model comprises the left and right ventricles, the left and right atria, the left-ventricular myocardium, and the trunks of the pulmonary artery and the aorta. In addition, information about important

2 1 Figure 1. Heart model used for segmentation.the model comprises seven anatomical regions (four cardiac chambers, myocardium, trunks of the pulmonary artery and of the aorta) indicated by distinct colours. Additionally, anatomical information (like landmarks) is also encoded into the model. anatomical landmarks such as the valve planes is encoded into the model. Inter-patient and inter-phase shape variability can be efficiently modeled by assigning an affine transformation to each part of the model [12]. Affine transformations cover translation, rotation, scaling along different coordinate axes and shearing. Mesh regularity is maintained by interpolation of the affine transformations at the transitions between the anatomical regions. The accuracy of this piecewise affine model was evaluated using reference meshes that were semi-automatically adapted by experts to 28 images originating from 13 patients at various cardiac phases. The piecewise affine adaptation of the model to these meshes showed that the heart anatomy of different individuals and different heart phases can be approximated with a mean residual point-to-surface error of 1.3 mm. In addition, technical information is encoded into the heart model that enables the robust matching to images. Most important is the information for detecting the proper image boundary that is associated with each triangle [13]. The starting point to generate this information is the training set of 28 heart segmentations, along with the corresponding CT images mentioned above. In addition, a huge number of more than 500 boundary detection functions have been generated that look for image gradients and check various gray value ranges. For each dataset, each triangle and each boundary detection function, we simulate the boundary detection process that occurs during adaptation. The distances between the detected boundary positions and the desired object boundary from the reference segmentations are recorded for each tested function and each triangle. Finally, each triangle is assigned the boundary detection function corresponding to the smallest average distance. Segmentation chain The automatic segmentation of the heart consists of four steps. First, the heart is detected using the generalized Hough transformation [14], which is an algorithm for detecting an object defined by a number of representative surface points in an image. A specific aspect in this step is that the surface points result from hearts of different individuals with different shapes. The algorithm is very reliable and was able to correctly detect the heart in 149 of 150 test images. The detection only failed in one patient who had a severe aortic root aneurysm. Secondly, the heart model is matched to the image, optimizing its position in space (pose) with respect to a rigid transformation (i.e. translation, rotation and isotropic scaling).thirdly, the different anatomical regions of the model are simultaneously matched to the image using the piecewise affine transformation introduced above. Finally, accurate boundary delineation is achieved using a deformable adaptation (see Intermezzo: Mesh Adaptation). The resulting segmentation can deviate from the heart model and its variability defined by the affine Automatic segmentation of the heart consists of four steps. MEDICAMUNDI 50/3 2006/12 13

3 INTERMEZZO: Mesh adaptation In model-based segmentation a triangulated mesh is deformed to the actual patient anatomy represented in the image. For the special purpose of heart segmentation, the deformable structure consists of a multi-compartmental mesh comprising 15,000 triangles. The model comprises the left and right ventricles, the left and right atria, the left-ventricular myocardium, the trunks of the pulmonary artery and the aorta. The mesh is matched to the heart by minimizing the distance between the triangles and points detected at the object boundaries (see Figure I). The matching process is performed in two steps. First, object boundaries are searched for along profiles perpendicular to the mesh triangles. Typically, the boundary detection functions attached to each triangle are evaluated at discrete positions and the position with the most promising response is selected as the edge candidate. The next step is global minimization of the sum of the squared distances between triangle centres and edge candidates. To prevent the triangles from becoming stuck at the target positions, displacements lateral to the object boundary are permitted (i.e., the triangles are free to slide along the green line in Figure I). In steps 2 and 3 of the segmentation chain (see main article, Figure 2) vertices are constrained to deform with respect to a parametric transformation. That is, the goal of the minimization of the external energy is to find the optimum parameters of a global parametric transformation. However, in step 4, the vertices are allowed to deviate from a parametric shape description. In that case, we ensure that the resulting shape remains similar to a heart by penalizing deviations from the learned shape (Figure II). This contribution is referred to as internal energy. The segmentation problem consists now of finding the optimum vertex positions which minimize the balance between image matching (external energy) and shape prior (internal energy). In Figure I the organ of interest is represented by the light blue heart and the mesh by dark blue points connected by lines. (In three dimensions, a mesh consists of points connected in triangles.) Boundary points are searched for along profiles perpendicular to each triangle. The point with the most prominent response (green point) is selected as boundary candidate. In the illustration, d is the distance between the triangle centre and the plane parallel to the object at the detected boundary (green line). The mesh is then attracted to the object by minimizing the sum of the squared distances d projected onto the boundary normal vector. The resulting effect is to move the mesh towards the object boundary while allowing cost-free lateral sliding. In deformable adaptation, the vertices are allowed to Figure I. Matching a mesh to an image. I 14 MEDICAMUNDI 50/3 2006/12

4 deform freely. However, to prevent implausible deformation, the vertex displacements can be constrained by shape priors (Figure II). Mathematically, this can be implemented by minimizing the sum of squared differences between edge vectors in the deforming mesh (red) and prior shape model (green). To remove the influence of global positioning, both the deforming mesh and the shape model are previously aligned using point-based registration represented by the transformation T [ ]. The result of the segmentation is given by the minimum of the combined energy Eext + Eint where balances the contributions II Figure II. Constraining deformation using prior shape knowledge. transformations, but the magnitude of the deviations is limited in order to preserve the basic shape. Figure 2 shows the increasing segmentation accuracy for the different steps. Typically, the time for a complete segmentation is about 25 s on an up-to-date PC. Evaluation Segmentation accuracy was measured using cross-evaluation with the 28 reference images used before. To avoid bias due to having several images from one patient, the model was trained using the images from all but one patient and the error was measured on the cyclically omitted images. To quantify the error between the adapted and reference meshes, we used the mean Euclidean distance between the triangle centers and patches of geodesic radius r = 10 mm around the corresponding triangle centers in the other mesh. This distance was also computed interchanging the reference and adapted meshes, since it is not symmetric. 2 Figure 2.Axial slice showing the segmentation state after each stage of the segmentation chain. MEDICAMUNDI 50/3 2006/12 15

5 Figure 3. Selection of cardiac data sets along with the automatic segmentation results (no user interaction).the algorithm could successfully segment these images despite noise, irregular contrast agent distribution between the chambers, variation in field-of-view and craniocaudal coverage.the segmentation was not disturbed by hearts lying partially out of the field of view. 3 These distances were averaged for the distinct structures of the heart model. Some triangles within or close to the artificial endings of the truncated vessels are poorly defined (i.e. not related to anatomical structures) and were removed during error measurement. The resulting mean segmentation error for the whole mesh was 0.82 ± 1.00 mm. The largest mean error per anatomical region was measured for the endocardium of the left ventricle (0.98 ± 1.32 mm) due to ambiguities related to the definition of the papillary muscle borders. Typical segmentation results provided by our algorithm with no user interaction are shown on Figure 3. Future applications The heart segmentation can be used in numerous different ways to support the presentation of cardiac CT images, their reconstruction, inspection, and planning of interventions. Figure 4 illustrates some examples. By converting the heart segmentation into a volume annotation, it is relatively easy to derive all kinds of measurements, such as true three-dimensional chamber volumes, end-systolic and end-diastolic phases, ejection fraction or ventricular mass. Apart from its relevance as clinical parameters, this information can be used in the imaging chain, for instance, to select the optimum cardiac phase. Furthermore, the volume annotation can be used to assign different transparencies and opacities to the parts of the heart for volume visualization. The landmarks encoded in the model can be used to establish cardiac coordinate systems and thus automatically generate standard cardiac displays such as short-axis or four-chamber views. The access to various landmarks within the cardiac anatomy opens up new applications for imaging modalities in the interventional area. This will be of an immense help to electro- Figure 4. Examples illustrating the future use of the heart model.the heart model can be converted into a volume annotation (upper left) allowing for all different kinds of volume measurements.the volume annotation can also be used within volume rendering (upper middle), where the different anatomical parts of the heart appear with a different color. Model landmarks allow automatic generation of standard cardiac displays such as four-chamber views (upper right). Further examples are the overlay of the heart model onto interventional X-ray images and the automatic generation of a rendering from the inside of the left atrium to support guidance during electrophysiological procedures MEDICAMUNDI 50/3 2006/12

6 physiologists when performing procedures such as radio-frequency (RF) ablation of the pulmonary veins. An anatomical overlay of a three-dimensional structure obtained from CT onto the fluoroscopic image would provide the clinician with additional information such as the number and the ostial location of pulmonary veins, size of the lasso catheter to be used, etc. Alternatively, an endoscopic view of the chamber (i.e. left atrium) with a fly-through capability would provide the clinician with additional three-dimensional information such as the curvature of the internal structures. Here, the heart segmentation can help to automatically find the center of the atrium and define a proper viewing direction. Outlook We have demonstrated a robust model-based cardiac segmentation algorithm that can address an important need in routine clinical practice. This is expected to be a key enabler in creating and addressing new opportunities in the entire image chain, in which the current approach to handling a large amount of data poses a significant challenge. In addition, this can also be extended to other modalities such as ultrasound and magnetic resonance imaging, and adapted to other anatomical structures, thus facilitating the use of a single robust image processing approach that can act as an enabler for new clinical applications in the future. Acknowledgement The authors would like to thank H. Schramm (Philips Research Europe Aachen, Germany) for his essential contributions to heart detection and generalized Hough transform. Further thanks go to G. Lavi and J. Lessick (Philips Medical Systems, Advanced Technology Center, Haifa, Israel) for continuous support regarding evaluation and integration A robust model-based segmentation algorithm can be an enabler for new applications. References [1] Kalender WA, Seissler W, Klotz E, Vock P. Spiral Volumetric CT with Single Breath-Hold Technique, Continuous Transport and Continuous Scanner Rotation. Radiology 1990; 176: [2] Crawford CR, King KF. Computed Tomography Scanning with Simultaneous Patient Translation. Med Phys 1990; 17: [3] Ohnesorge B, Flohr T, Becker C, Kopp AF, Schoeph UJ, Baum U et al. Cardiac Imaging by means of Electrocardiographically Gated Multi- Section Spiral CT: Initial Experience. Radiology 2001; 217: [4] Hoffmann MHK, Shi H, Manzke R, Schmid FT, De Vries L, Grass M et al. Non-Invasive Coronary Angiography with 16-Detector Row CT: Effect of Heart Rate. Radiology 2005; 234: [5] Hoffmann MHK, Shi H, Schmitz BL, Schmid FT, Lieberknecht M, Shulze R et al. Noninvasive Coronary Angiography with Multislice Computed Tomography. JAMA 2005; 293: [6] Garcia MJ, Lessick J, Hoffmann MHK, for the CATSCAN Study Investigators. Accuracy of 16-Row Multidetector Computed Tomography for the Assessment of Coronary Artery Stenosis. JAMA 2006; 296: [7] Gaspar T, Peled N. Cardiac and Vascular Imaging using 40-Slice CT: Initial Experiences. Medicamundi 2004; 48,1: [8] Watkins MW, Hesse B, Green CE, Greenberg NL, Manning M, Chaudhry E et al. Detection of Coronary Artery Stenosis using 40- Channel Computed Tomography using Multi-Segment Reconstruction. Accepted by AJC, January [9] Rubinshtein R, Gaspar T, Halon DA, Goldstein J, Peled N, Lewis BS. Prevalence and Extent of Obstructive Coronary Disease in Patients with Zero or Low Calcium Score undergoing 64-Slice Cardiac Multidetector Computed Tomography for Evaluation of a Chest Pain Syndrome. Accepted by AJC, [10] Von Berg J and Lorenz C. Multi-Surface Cardiac Modeling, Segmentation, and Tracking. Proc. Functional Imaging and Modeling of the Heart. Ser. LNCS 2005 (Frangi AF, Radeva P, Santos A, Hernandez M Eds) 3504: [11]Lorenz C, Von Berg J. A Comprehensive Shape Model of the Heart. Medical Image Analysis 2006; 10: [12] Ecabert O, Peters J, Weese J. Modeling Shape Variability for Full Heart Segmentation in Cardiac CT Images. Proceedings SPIE Medical Imaging 2006 (Reinhardt JM, Pluim JPW Eds) 6144: R R 12. [13] Peters J, Ecabert O, Weese J. Feature Optimization via Simulated Search for Model-Based Heart Segmentation. Proceedings CARS, Ser. ICS 2005 (Lemke HU, Inamura K, Doi K, Vannier MW, Farman AG Eds) 1281: [14] Ballard DH. Generalizing the Hough Transform to Detect Arbitrary Shapes. Pattern Recognition 1981; 13,2: [15] Weese J, Kaus MR, Lorenz C, Lobregt S, Truyen R, Pekar V. Shape Constrained Deformable Models for 3D Medical Image Segmentation. Image Processing in Medical Imaging (IPMI), Ser. LNCS 2001 (Insana MY, Leahy RM Eds) 2082:

Automatic Model-Based Segmentation of Medical Images

Automatic Model-Based Segmentation of Medical Images Automatic Model-Based Segmentation of Medical Images Cristian Lorenz Jochen Peters, Fabian Wenzel, Jürgen Weese May 26 th 2014 Need Medical imaging systems produce a huge amount of patient images with

More information

Simultaneous Model-based Segmentation of Multiple Objects

Simultaneous Model-based Segmentation of Multiple Objects Simultaneous Model-based Segmentation of Multiple Objects Astrid Franz 1, Robin Wolz 1, Tobias Klinder 1,2, Cristian Lorenz 1, Hans Barschdorf 1, Thomas Blaffert 1, Sebastian P. M. Dries 1, Steffen Renisch

More information

Automatic Ascending Aorta Detection in CTA Datasets

Automatic Ascending Aorta Detection in CTA Datasets Automatic Ascending Aorta Detection in CTA Datasets Stefan C. Saur 1, Caroline Kühnel 2, Tobias Boskamp 2, Gábor Székely 1, Philippe Cattin 1,3 1 Computer Vision Laboratory, ETH Zurich, 8092 Zurich, Switzerland

More information

Automated Model-Based Rib Cage Segmentation and Labeling in CT Images

Automated Model-Based Rib Cage Segmentation and Labeling in CT Images Automated Model-Based Rib Cage Segmentation and Labeling in CT Images Tobias Klinder 1,2,CristianLorenz 2,JensvonBerg 2, Sebastian P.M. Dries 2, Thomas Bülow 2,andJörn Ostermann 1 1 Institut für Informationsverarbeitung,

More information

Deformable shape models Aspects and applications in medical image analysis

Deformable shape models Aspects and applications in medical image analysis Deformable shape models Aspects and applications in medical image analysis Cristian Lorenz Tobias Klinder, Jochen Peters, Axel Saalbach Fabian Wenzel, Irina Wächter-Stehle, Jürgen Weese Philips Research

More information

4D Cardiac Reconstruction Using High Resolution CT Images

4D Cardiac Reconstruction Using High Resolution CT Images 4D Cardiac Reconstruction Using High Resolution CT Images Mingchen Gao 1, Junzhou Huang 1, Shaoting Zhang 1, Zhen Qian 2, Szilard Voros 2, Dimitris Metaxas 1, and Leon Axel 3 1 CBIM Center, Rutgers University,

More information

Ultrasound. Q-Station software. Streamlined workflow solutions. Philips Q-Station ultrasound workspace software

Ultrasound. Q-Station software. Streamlined workflow solutions. Philips Q-Station ultrasound workspace software Ultrasound Q-Station software Streamlined workflow solutions Philips Q-Station ultrasound workspace software Managing your off-cart workf low Everyone is being asked to do more with fewer resources it

More information

Whole Body MRI Intensity Standardization

Whole Body MRI Intensity Standardization Whole Body MRI Intensity Standardization Florian Jäger 1, László Nyúl 1, Bernd Frericks 2, Frank Wacker 2 and Joachim Hornegger 1 1 Institute of Pattern Recognition, University of Erlangen, {jaeger,nyul,hornegger}@informatik.uni-erlangen.de

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

A Comprehensive Method for Geometrically Correct 3-D Reconstruction of Coronary Arteries by Fusion of Intravascular Ultrasound and Biplane Angiography

A Comprehensive Method for Geometrically Correct 3-D Reconstruction of Coronary Arteries by Fusion of Intravascular Ultrasound and Biplane Angiography Computer-Aided Diagnosis in Medical Imaging, September 20-23, 1998, Chicago IL Elsevier ICS 1182 A Comprehensive Method for Geometrically Correct 3-D Reconstruction of Coronary Arteries by Fusion of Intravascular

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

FOREWORD TO THE SPECIAL ISSUE ON MOTION DETECTION AND COMPENSATION

FOREWORD TO THE SPECIAL ISSUE ON MOTION DETECTION AND COMPENSATION Philips J. Res. 51 (1998) 197-201 FOREWORD TO THE SPECIAL ISSUE ON MOTION DETECTION AND COMPENSATION This special issue of Philips Journalof Research includes a number of papers presented at a Philips

More information

Image Acquisition Systems

Image Acquisition Systems Image Acquisition Systems Goals and Terminology Conventional Radiography Axial Tomography Computer Axial Tomography (CAT) Magnetic Resonance Imaging (MRI) PET, SPECT Ultrasound Microscopy Imaging ITCS

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

Evaluation of Hessian-based filters to enhance the axis of coronary arteries in CT images

Evaluation of Hessian-based filters to enhance the axis of coronary arteries in CT images International Congress Series 1256 (2003) 1191 1196 Evaluation of Hessian-based filters to enhance the axis of coronary arteries in CT images S.D. Olabarriaga a, *, M. Breeuwer b, W.J. Niessen a a University

More information

University College London, Gower Street, London, UK, WC1E 6BT {g.gao, s.tarte, p.chinchapatnam, d.hill,

University College London, Gower Street, London, UK, WC1E 6BT {g.gao, s.tarte, p.chinchapatnam, d.hill, Validation of the use of photogrammetry to register preprocedure MR images to intra-procedure patient position for image-guided cardiac catheterization procedures Gang Gao 1, Segolene Tarte 1, Andy King

More information

Improvement of Efficiency and Flexibility in Multi-slice Helical CT

Improvement of Efficiency and Flexibility in Multi-slice Helical CT J. Shanghai Jiaotong Univ. (Sci.), 2008, 13(4): 408 412 DOI: 10.1007/s12204-008-0408-x Improvement of Efficiency and Flexibility in Multi-slice Helical CT SUN Wen-wu 1 ( ), CHEN Si-ping 2 ( ), ZHUANG Tian-ge

More information

Vessel Explorer: a tool for quantitative measurements in CT and MR angiography

Vessel Explorer: a tool for quantitative measurements in CT and MR angiography Clinical applications Vessel Explorer: a tool for quantitative measurements in CT and MR angiography J. Oliván Bescós J. Sonnemans R. Habets J. Peters H. van den Bosch T. Leiner Healthcare Informatics/Patient

More information

Volumetric Analysis of the Heart from Tagged-MRI. Introduction & Background

Volumetric Analysis of the Heart from Tagged-MRI. Introduction & Background Volumetric Analysis of the Heart from Tagged-MRI Dimitris Metaxas Center for Computational Biomedicine, Imaging and Modeling (CBIM) Rutgers University, New Brunswick, NJ Collaboration with Dr. Leon Axel,

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

3D Guide Wire Navigation from Single Plane Fluoroscopic Images in Abdominal Catheterizations

3D Guide Wire Navigation from Single Plane Fluoroscopic Images in Abdominal Catheterizations 3D Guide Wire Navigation from Single Plane Fluoroscopic Images in Abdominal Catheterizations Martin Groher 2, Frederik Bender 1, Ali Khamene 3, Wolfgang Wein 3, Tim Hauke Heibel 2, Nassir Navab 2 1 Siemens

More information

Chapter 9 Conclusions

Chapter 9 Conclusions Chapter 9 Conclusions This dissertation has described a new method for using local medial properties of shape to identify and measure anatomical structures. A bottom up approach based on image properties

More information

Gradient-Based Differential Approach for Patient Motion Compensation in 2D/3D Overlay

Gradient-Based Differential Approach for Patient Motion Compensation in 2D/3D Overlay Gradient-Based Differential Approach for Patient Motion Compensation in 2D/3D Overlay Jian Wang, Anja Borsdorf, Benno Heigl, Thomas Köhler, Joachim Hornegger Pattern Recognition Lab, Friedrich-Alexander-University

More information

GE Healthcare. Vivid 7 Dimension 08 Cardiovascular ultrasound system

GE Healthcare. Vivid 7 Dimension 08 Cardiovascular ultrasound system GE Healthcare Vivid 7 Dimension 08 Cardiovascular ultrasound system ltra Definition. Technology. Performance. Start with a system that s proven its worth in LV quantification and 4D imaging. Then add even

More information

Model Based 3D Cardiac Image Segmentation With Marginal Space Learning

Model Based 3D Cardiac Image Segmentation With Marginal Space Learning Model Based 3D Cardiac Image Segmentation With Marginal Space Learning Yefeng Zheng Imaging and Computer Vision, Siemens Corporate Technology, Princeton, NJ, USA yefeng.zheng@siemens.com Abstract Cardiovascular

More information

Generation of Triangle Meshes from Time-of-Flight Data for Surface Registration

Generation of Triangle Meshes from Time-of-Flight Data for Surface Registration Generation of Triangle Meshes from Time-of-Flight Data for Surface Registration Thomas Kilgus, Thiago R. dos Santos, Alexander Seitel, Kwong Yung, Alfred M. Franz, Anja Groch, Ivo Wolf, Hans-Peter Meinzer,

More information

Automatic Delineation of Left and Right Ventricles in Cardiac MRI Sequences Using a Joint Ventricular Model

Automatic Delineation of Left and Right Ventricles in Cardiac MRI Sequences Using a Joint Ventricular Model Automatic Delineation of Left and Right Ventricles in Cardiac MRI Sequences Using a Joint Ventricular Model Xiaoguang Lu 1,, Yang Wang 1, Bogdan Georgescu 1, Arne Littman 2, and Dorin Comaniciu 1 1 Siemens

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

Using Probability Maps for Multi organ Automatic Segmentation

Using Probability Maps for Multi organ Automatic Segmentation Using Probability Maps for Multi organ Automatic Segmentation Ranveer Joyseeree 1,2, Óscar Jiménez del Toro1, and Henning Müller 1,3 1 University of Applied Sciences Western Switzerland (HES SO), Sierre,

More information

Lecture 6: Medical imaging and image-guided interventions

Lecture 6: Medical imaging and image-guided interventions ME 328: Medical Robotics Winter 2019 Lecture 6: Medical imaging and image-guided interventions Allison Okamura Stanford University Updates Assignment 3 Due this Thursday, Jan. 31 Note that this assignment

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

Computational Medical Imaging Analysis Chapter 4: Image Visualization

Computational Medical Imaging Analysis Chapter 4: Image Visualization Computational Medical Imaging Analysis Chapter 4: Image Visualization Jun Zhang Laboratory for Computational Medical Imaging & Data Analysis Department of Computer Science University of Kentucky Lexington,

More information

4D Magnetic Resonance Analysis. MR 4D Flow. Visualization and Quantification of Aortic Blood Flow

4D Magnetic Resonance Analysis. MR 4D Flow. Visualization and Quantification of Aortic Blood Flow 4D Magnetic Resonance Analysis MR 4D Flow Visualization and Quantification of Aortic Blood Flow 4D Magnetic Resonance Analysis Complete assesment of your MR 4D Flow data Time-efficient and intuitive analysis

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

Respiratory Motion Estimation using a 3D Diaphragm Model

Respiratory Motion Estimation using a 3D Diaphragm Model Respiratory Motion Estimation using a 3D Diaphragm Model Marco Bögel 1,2, Christian Riess 1,2, Andreas Maier 1, Joachim Hornegger 1, Rebecca Fahrig 2 1 Pattern Recognition Lab, FAU Erlangen-Nürnberg 2

More information

Diagnostic quality of time-averaged ECG-gated CT data

Diagnostic quality of time-averaged ECG-gated CT data Diagnostic quality of time-averaged ECG-gated CT data Almar Klein a, Luuk J. Oostveen b, Marcel J.W. Greuter c, Yvonne Hoogeveen b, Leo J. Schultze Kool b, Cornelis H. Slump a and W. Klaas Jan Renema b

More information

Nonrigid Motion Compensation of Free Breathing Acquired Myocardial Perfusion Data

Nonrigid Motion Compensation of Free Breathing Acquired Myocardial Perfusion Data Nonrigid Motion Compensation of Free Breathing Acquired Myocardial Perfusion Data Gert Wollny 1, Peter Kellman 2, Andrés Santos 1,3, María-Jesus Ledesma 1,3 1 Biomedical Imaging Technologies, Department

More information

Tracking the Left Ventricle through Collaborative Trackers and Sparse Shape Model

Tracking the Left Ventricle through Collaborative Trackers and Sparse Shape Model Tracking the Left Ventricle through Collaborative Trackers and Sparse Shape Model Yan Zhou IMPAC Medical Systems, Elekta Inc., Maryland Heights, MO, USA Abstract. Tracking the left ventricle plays an important

More information

Scaling Calibration in the ATRACT Algorithm

Scaling Calibration in the ATRACT Algorithm Scaling Calibration in the ATRACT Algorithm Yan Xia 1, Andreas Maier 1, Frank Dennerlein 2, Hannes G. Hofmann 1, Joachim Hornegger 1,3 1 Pattern Recognition Lab (LME), Friedrich-Alexander-University Erlangen-Nuremberg,

More information

Introduction. Knowledge driven segmentation of cardiovascular images. Problem: amount of data

Introduction. Knowledge driven segmentation of cardiovascular images. Problem: amount of data Knowledge driven segmentation of cardiovascular images Introduction Boudewijn Lelieveldt, PhD Division of Image Processing, dept of Radiology, Leiden University Medical Center Introduction: why prior knowledge?

More information

US 1.

US 1. US 1 Sample image: Normal pancreas seen on sonogram. Looking up from abdomen toward the head of the patient. The liver is in front of the pancreas. A vein draining the spleen is behind the pancreas http://www.radiologyinfo.org/photocat/photos.cfm?image=abdo-us-pancr.jpg&&subcategory=abdomen&&stop=9

More information

Robust and Accurate Coronary Artery Centerline Extraction in CTA by Combining Model-Driven and Data-Driven Approaches

Robust and Accurate Coronary Artery Centerline Extraction in CTA by Combining Model-Driven and Data-Driven Approaches Robust and Accurate Coronary Artery Centerline Extraction in CTA by Combining Model-Driven and Data-Driven Approaches Yefeng Zheng, Huseyin Tek, and Gareth Funka-Lea Imaging and Computer Vision, Siemens

More information

arxiv: v2 [cs.cv] 28 Jan 2019

arxiv: v2 [cs.cv] 28 Jan 2019 Improving Myocardium Segmentation in Cardiac CT Angiography using Spectral Information Steffen Bruns a, Jelmer M. Wolterink a, Robbert W. van Hamersvelt b, Majd Zreik a, Tim Leiner b, and Ivana Išgum a

More information

Cardiac MRI visualization for ventricular tachycardia ablation

Cardiac MRI visualization for ventricular tachycardia ablation DOI 10.1007/s11548-012-0776-4 ORIGINAL ARTICLE Cardiac MRI visualization for ventricular tachycardia ablation Corine J. Godeschalk-Slagboom Rob J. van der Geest Katja Zeppenfeld Charl P. Botha Received:

More information

Extracting consistent and manifold interfaces from multi-valued volume data sets

Extracting consistent and manifold interfaces from multi-valued volume data sets Extracting consistent and manifold interfaces from multi-valued volume data sets Stephan Bischoff, Leif Kobbelt Lehrstuhl für Informatik 8, RWTH Aachen, 52056 Aachen Email: {bischoff,kobbelt}@informatik.rwth-aachen.de

More information

LOGIQ. V2 Ultrasound. Part of LOGIQ Vision Series. Imagination at work LOGIQ is a trademark of General Electric Company.

LOGIQ. V2 Ultrasound. Part of LOGIQ Vision Series. Imagination at work LOGIQ is a trademark of General Electric Company. TM LOGIQ V2 Ultrasound Part of LOGIQ Vision Series Imagination at work The brilliance of color. The simplicity of GE. Now you can add the advanced capabilities of color Doppler to patient care with the

More information

Analysis of CMR images within an integrated healthcare framework for remote monitoring

Analysis of CMR images within an integrated healthcare framework for remote monitoring Analysis of CMR images within an integrated healthcare framework for remote monitoring Abstract. We present a software for analyzing Cardiac Magnetic Resonance (CMR) images. This tool has been developed

More information

Explorative Building of 3D Vessel Tree Models 1) Technology, Inffeldgasse 16 2.OG, A-8010 Graz, Austria

Explorative Building of 3D Vessel Tree Models 1) Technology, Inffeldgasse 16 2.OG, A-8010 Graz, Austria Explorative Building of 3D Vessel Tree Models 1) Georg Langs 123, Petia Radeva 3, Francesc Carreras 4 1 Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16 2.OG,

More information

FINDING THE TRUE EDGE IN CTA

FINDING THE TRUE EDGE IN CTA FINDING THE TRUE EDGE IN CTA by: John A. Rumberger, PhD, MD, FACC Your patient has chest pain. The Cardiac CT Angiography shows plaque in the LAD. You adjust the viewing window trying to evaluate the stenosis

More information

Automatic Cerebral Aneurysm Detection in Multimodal Angiographic Images

Automatic Cerebral Aneurysm Detection in Multimodal Angiographic Images Automatic Cerebral Aneurysm Detection in Multimodal Angiographic Images Clemens M. Hentschke, Oliver Beuing, Rosa Nickl and Klaus D. Tönnies Abstract We propose a system to automatically detect cerebral

More information

Multi-part Left Atrium Modeling and Segmentation in C-Arm CT Volumes for Atrial Fibrillation Ablation

Multi-part Left Atrium Modeling and Segmentation in C-Arm CT Volumes for Atrial Fibrillation Ablation Multi-part Left Atrium Modeling and Segmentation in C-Arm CT Volumes for Atrial Fibrillation Ablation Yefeng Zheng 1, Tianzhou Wang 1, Matthias John 2, S. Kevin Zhou 1,JanBoese 2, and Dorin Comaniciu 1

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

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

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

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

ECG-Correlated Imaging of the Heart with Subsecond Multislice Spiral CT

ECG-Correlated Imaging of the Heart with Subsecond Multislice Spiral CT 888 IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 19, NO. 9, SEPTEMBER 2000 ECG-Correlated Imaging of the Heart with Subsecond Multislice Spiral CT Marc Kachelrieß*, Stefan Ulzheimer, and Willi A. Kalender

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

Left Ventricle Endocardium Segmentation for Cardiac CT Volumes Using an Optimal Smooth Surface

Left Ventricle Endocardium Segmentation for Cardiac CT Volumes Using an Optimal Smooth Surface Left Ventricle Endocardium Segmentation for Cardiac CT Volumes Using an Optimal Smooth Surface Yefeng Zheng a, Bogdan Georgescu a, Fernando Vega-Higuera b, and Dorin Comaniciu a a Integrated Data Systems

More information

Elastic registration of medical images using finite element meshes

Elastic registration of medical images using finite element meshes Elastic registration of medical images using finite element meshes Hartwig Grabowski Institute of Real-Time Computer Systems & Robotics, University of Karlsruhe, D-76128 Karlsruhe, Germany. Email: grabow@ira.uka.de

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

Medical Image Analysis

Medical Image Analysis Computer assisted Image Analysis VT04 29 april 2004 Medical Image Analysis Lecture 10 (part 1) Xavier Tizon Medical Image Processing Medical imaging modalities XRay,, CT Ultrasound MRI PET, SPECT Generic

More information

SIGMI Meeting ~Image Fusion~ Computer Graphics and Visualization Lab Image System Lab

SIGMI Meeting ~Image Fusion~ Computer Graphics and Visualization Lab Image System Lab SIGMI Meeting ~Image Fusion~ Computer Graphics and Visualization Lab Image System Lab Introduction Medical Imaging and Application CGV 3D Organ Modeling Model-based Simulation Model-based Quantification

More information

Motion artifact detection in four-dimensional computed tomography images

Motion artifact detection in four-dimensional computed tomography images Motion artifact detection in four-dimensional computed tomography images G Bouilhol 1,, M Ayadi, R Pinho, S Rit 1, and D Sarrut 1, 1 University of Lyon, CREATIS; CNRS UMR 5; Inserm U144; INSA-Lyon; University

More information

The VesselGlyph: Focus & Context Visualization in CT-Angiography

The VesselGlyph: Focus & Context Visualization in CT-Angiography The VesselGlyph: Focus & Context Visualization in CT-Angiography Matúš Straka M. Šrámek, A. La Cruz E. Gröller, D. Fleischmann Contents Motivation:» Why again a new visualization method for vessel data?

More information

Quantitative IntraVascular UltraSound (QCU)

Quantitative IntraVascular UltraSound (QCU) Quantitative IntraVascular UltraSound (QCU) Authors: Jouke Dijkstra, Ph.D. and Johan H.C. Reiber, Ph.D., Leiden University Medical Center, Dept of Radiology, Leiden, The Netherlands Introduction: For decades,

More information

Human Heart Coronary Arteries Segmentation

Human Heart Coronary Arteries Segmentation Human Heart Coronary Arteries Segmentation Qian Huang Wright State University, Computer Science Department Abstract The volume information extracted from computed tomography angiogram (CTA) datasets makes

More information

Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging

Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging 1 CS 9 Final Project Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging Feiyu Chen Department of Electrical Engineering ABSTRACT Subject motion is a significant

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

Modeling and preoperative planning for kidney surgery

Modeling and preoperative planning for kidney surgery Modeling and preoperative planning for kidney surgery Refael Vivanti Computer Aided Surgery and Medical Image Processing Lab Hebrew University of Jerusalem, Israel Advisor: Prof. Leo Joskowicz Clinical

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

Freehand 3-D Sonographic Measurement of the Superficial Femoral Artery

Freehand 3-D Sonographic Measurement of the Superficial Femoral Artery Freehand 3-D Sonographic Measurement of the Superficial Femoral Artery Dennis Sandkühler, Christian Sobotta, Matthias Samsel, Heinrich Martin Overhoff Medical Engineering Laboratory, University of Applied

More information

Basic principles of MR image analysis. Basic principles of MR image analysis. Basic principles of MR image analysis

Basic principles of MR image analysis. Basic principles of MR image analysis. Basic principles of MR image analysis Basic principles of MR image analysis Basic principles of MR image analysis Julien Milles Leiden University Medical Center Terminology of fmri Brain extraction Registration Linear registration Non-linear

More information

Computational Medical Imaging Analysis

Computational Medical Imaging Analysis Computational Medical Imaging Analysis Chapter 1: Introduction to Imaging Science Jun Zhang Laboratory for Computational Medical Imaging & Data Analysis Department of Computer Science University of Kentucky

More information

ICA vs. PCA Active Appearance Models: Application to Cardiac MR Segmentation

ICA vs. PCA Active Appearance Models: Application to Cardiac MR Segmentation ICA vs. PCA Active Appearance Models: Application to Cardiac MR Segmentation M. Üzümcü 1, A.F. Frangi 2, M. Sonka 3, J.H.C. Reiber 1, B.P.F. Lelieveldt 1 1 Div. of Image Processing, Dept. of Radiology

More information

Model-Based Respiratory Motion Compensation for Image-Guided Cardiac Interventions

Model-Based Respiratory Motion Compensation for Image-Guided Cardiac Interventions Model-Based Respiratory Motion Compensation for Image-Guided Cardiac Interventions February 8 Matthias Schneider Pattern Recognition Lab Friedrich-Alexander-University Erlangen-Nuremberg Imaging and Visualization

More information

Non-rigid 2D-3D image registration for use in Endovascular repair of Abdominal Aortic Aneurysms.

Non-rigid 2D-3D image registration for use in Endovascular repair of Abdominal Aortic Aneurysms. RAHEEM ET AL.: IMAGE REGISTRATION FOR EVAR IN AAA. 1 Non-rigid 2D-3D image registration for use in Endovascular repair of Abdominal Aortic Aneurysms. Ali Raheem 1 ali.raheem@kcl.ac.uk Tom Carrell 2 tom.carrell@gstt.nhs.uk

More information

THE DICOM 2013 INTERNATIONAL CONFERENCE & SEMINAR. DICOM Fields of Use. Klaus Neuner. Brainlab AG. Software Project Manager Feldkirchen, Germany

THE DICOM 2013 INTERNATIONAL CONFERENCE & SEMINAR. DICOM Fields of Use. Klaus Neuner. Brainlab AG. Software Project Manager Feldkirchen, Germany THE DICOM 2013 INTERNATIONAL CONFERENCE & SEMINAR March 14-16 Bangalore, India DICOM Fields of Use Klaus Neuner Brainlab AG Software Project Manager Feldkirchen, Germany Introduction This presentation

More information

Accurate Regression-based 4D Mitral Valve Segmentation from 2D MRI Slices

Accurate Regression-based 4D Mitral Valve Segmentation from 2D MRI Slices Accurate Regression-based 4D Mitral Valve Segmentation from 2D MRI Slices Dime Vitanovski 2,3, Alexey Tsymbal 2, Razvan Ioan Ionasec 1, Andreas Greiser 4, Edgar Mueller 4, Xiaoguang Lu 1, Gareth Funka-Lea

More information

Blood Particle Trajectories in Phase-Contrast-MRI as Minimal Paths Computed with Anisotropic Fast Marching

Blood Particle Trajectories in Phase-Contrast-MRI as Minimal Paths Computed with Anisotropic Fast Marching Blood Particle Trajectories in Phase-Contrast-MRI as Minimal Paths Computed with Anisotropic Fast Marching Michael Schwenke 1, Anja Hennemuth 1, Bernd Fischer 2, Ola Friman 1 1 Fraunhofer MEVIS, Institute

More information

Mitral Annulus Segmentation From 3D Ultrasound Using Graph Cuts

Mitral Annulus Segmentation From 3D Ultrasound Using Graph Cuts Mitral Annulus Segmentation From 3D Ultrasound Using Graph Cuts The MIT Faculty has made this article openly available. Please share how this access benefits you. Your story matters. Citation As Published

More information

Segmenting the Left Ventricle in 3D Using a Coupled ASM and a Learned Non-Rigid Spatial Model

Segmenting the Left Ventricle in 3D Using a Coupled ASM and a Learned Non-Rigid Spatial Model Segmenting the Left Ventricle in 3D Using a Coupled ASM and a Learned Non-Rigid Spatial Model Stephen O Brien, Ovidiu Ghita, and Paul F. Whelan Centre for Image Processing and Analysis, Dublin City University,

More information

Interactive Boundary Detection for Automatic Definition of 2D Opacity Transfer Function

Interactive Boundary Detection for Automatic Definition of 2D Opacity Transfer Function Interactive Boundary Detection for Automatic Definition of 2D Opacity Transfer Function Martin Rauberger, Heinrich Martin Overhoff Medical Engineering Laboratory, University of Applied Sciences Gelsenkirchen,

More information

Machine Learning for Medical Image Analysis. A. Criminisi

Machine Learning for Medical Image Analysis. A. Criminisi Machine Learning for Medical Image Analysis A. Criminisi Overview Introduction to machine learning Decision forests Applications in medical image analysis Anatomy localization in CT Scans Spine Detection

More information

Assessing Accuracy Factors in Deformable 2D/3D Medical Image Registration Using a Statistical Pelvis Model

Assessing Accuracy Factors in Deformable 2D/3D Medical Image Registration Using a Statistical Pelvis Model Assessing Accuracy Factors in Deformable 2D/3D Medical Image Registration Using a Statistical Pelvis Model Jianhua Yao National Institute of Health Bethesda, MD USA jyao@cc.nih.gov Russell Taylor The Johns

More information

4D Auto MVQ (Mitral Valve Quantification)

4D Auto MVQ (Mitral Valve Quantification) 4D Auto MVQ (Mitral Valve Quantification) Federico Veronesi, Glenn Reidar Lie, Stein Inge Rabben GE Healthcare Introduction As the number of mitral valve repairs is on the rise, so is the need for mitral

More information

Digital Volume Correlation for Materials Characterization

Digital Volume Correlation for Materials Characterization 19 th World Conference on Non-Destructive Testing 2016 Digital Volume Correlation for Materials Characterization Enrico QUINTANA, Phillip REU, Edward JIMENEZ, Kyle THOMPSON, Sharlotte KRAMER Sandia National

More information

A Method of Automated Landmark Generation for Automated 3D PDM Construction

A Method of Automated Landmark Generation for Automated 3D PDM Construction A Method of Automated Landmark Generation for Automated 3D PDM Construction A. D. Brett and C. J. Taylor Department of Medical Biophysics University of Manchester Manchester M13 9PT, Uk adb@sv1.smb.man.ac.uk

More information

MR Advance Techniques. Vascular Imaging. Class III

MR Advance Techniques. Vascular Imaging. Class III MR Advance Techniques Vascular Imaging Class III 1 Vascular Imaging There are several methods that can be used to evaluate the cardiovascular systems with the use of MRI. MRI will aloud to evaluate morphology

More information

Graph Cuts Based Left Atrium Segmentation Refinement and Right Middle Pulmonary Vein Extraction in C-Arm CT

Graph Cuts Based Left Atrium Segmentation Refinement and Right Middle Pulmonary Vein Extraction in C-Arm CT Graph Cuts Based Left Atrium Segmentation Refinement and Right Middle Pulmonary Vein Extraction in C-Arm CT Dong Yang a, Yefeng Zheng a and Matthias John b a Imaging and Computer Vision, Siemens Corporate

More information

Discrete Estimation of Data Completeness for 3D Scan Trajectories with Detector Offset

Discrete Estimation of Data Completeness for 3D Scan Trajectories with Detector Offset Discrete Estimation of Data Completeness for 3D Scan Trajectories with Detector Offset Andreas Maier 1, Patrick Kugler 2, Günter Lauritsch 2, Joachim Hornegger 1 1 Pattern Recognition Lab and SAOT Erlangen,

More information

Qualitative Comparison of Conventional and Oblique MRI for Detection of Herniated Spinal Discs

Qualitative Comparison of Conventional and Oblique MRI for Detection of Herniated Spinal Discs Qualitative Comparison of Conventional and Oblique MRI for Detection of Herniated Spinal Discs Doug Dean Final Project Presentation ENGN 2500: Medical Image Analysis May 16, 2011 Outline Review of the

More information

Construction of Left Ventricle 3D Shape Atlas from Cardiac MRI

Construction of Left Ventricle 3D Shape Atlas from Cardiac MRI Construction of Left Ventricle 3D Shape Atlas from Cardiac MRI Shaoting Zhang 1, Mustafa Uzunbas 1, Zhennan Yan 1, Mingchen Gao 1, Junzhou Huang 1, Dimitris N. Metaxas 1, and Leon Axel 2 1 Rutgers, the

More information

Survey of the Heart Wall Delineation Techniques

Survey of the Heart Wall Delineation Techniques Survey of the Heart Wall Delineation Techniques Anjali A. Joshi 1, Vitthal J. Gond 2 1PG Student, Department. Of Electronics and Telecommunication, Late G.N Sapkal College of Engineering, Nashik, Maharashtra,

More information

Medical Image Registration

Medical Image Registration Medical Image Registration Submitted by NAREN BALRAJ SINGH SB ID# 105299299 Introduction Medical images are increasingly being used within healthcare for diagnosis, planning treatment, guiding treatment

More information

Depth-Layer-Based Patient Motion Compensation for the Overlay of 3D Volumes onto X-Ray Sequences

Depth-Layer-Based Patient Motion Compensation for the Overlay of 3D Volumes onto X-Ray Sequences Depth-Layer-Based Patient Motion Compensation for the Overlay of 3D Volumes onto X-Ray Sequences Jian Wang 1,2, Anja Borsdorf 2, Joachim Hornegger 1,3 1 Pattern Recognition Lab, Friedrich-Alexander-Universität

More information

GE Healthcare. Vivid E9 XDclear. with

GE Healthcare. Vivid E9 XDclear. with GE Healthcare Vivid E9 XDclear with capabilities for every day Whether in TTE or TEE, capture the entire heart in a single beat. Image a valve, or the entire ventricle with excellent image quality. And

More information

Overview of Proposed TG-132 Recommendations

Overview of Proposed TG-132 Recommendations Overview of Proposed TG-132 Recommendations Kristy K Brock, Ph.D., DABR Associate Professor Department of Radiation Oncology, University of Michigan Chair, AAPM TG 132: Image Registration and Fusion Conflict

More information

Image Guidance of Intracardiac Ultrasound with Fusion of Pre-operative Images

Image Guidance of Intracardiac Ultrasound with Fusion of Pre-operative Images Image Guidance of Intracardiac Ultrasound with Fusion of Pre-operative Images Yiyong Sun 1, Samuel Kadoury 1,YongLi 1, Matthias John 2,JeffResnick 3, Gerry Plambeck 3,RuiLiao 1, Frank Sauer 1, and Chenyang

More information

Image-Based Device Tracking for the Co-registration of Angiography and Intravascular Ultrasound Images

Image-Based Device Tracking for the Co-registration of Angiography and Intravascular Ultrasound Images Image-Based Device Tracking for the Co-registration of Angiography and Intravascular Ultrasound Images Peng Wang 1, Terrence Chen 1, Olivier Ecabert 2, Simone Prummer 2, Martin Ostermeier 2, and Dorin

More information

4DM Packages. 4DM Packages & License Types. Information to help you order the appropriate licenses for your site.

4DM Packages. 4DM Packages & License Types. Information to help you order the appropriate licenses for your site. 4DM Packages 4DM Packages & License Types. Information to help you order the appropriate licenses for your site. Nuclear Cardiac Quantification, Review, and Reporting Select Your 4DM Package and corresponding

More information