Liver Segmentation in CT Data: A Segmentation Refinement Approach

Size: px
Start display at page:

Download "Liver Segmentation in CT Data: A Segmentation Refinement Approach"

Transcription

1 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, The University of Iowa, USA, 2 Dept. of Internal Medicine, The University of Iowa, USA, reinhard-beichel@uiowa.edu, 3 Inst. for Computer Graphics and Vision, Graz University of Technology, Austria, 4 Department of Radiology, Medical University Graz. Abstract. Liver segmentation is an important prerequisite for planning of surgical interventions like liver tumor resections. For clinical applicability, the segmentation approach must be able to cope with the high variation in shape and gray-value appearance of the liver. In this paper we present a novel segmentation scheme based on a true 3D segmentation refinement concept utilizing a hybrid desktop/virtual reality user interface. The method consists of two main stages. First, an initial segmentation is generated using graph cuts. Second, an interactive segmentation refinement step allows a user to fix arbitrary segmentation errors. We demonstrate the robustness of our method on ten contrast enhanced liver CT scans. Our segmentation approach copes successfully with the high variation found in patient data sets and allows to produce segmentations in a time-efficient manner. 1 Introduction Liver cancer is one of the four most common deadly malignant neoplasms in the world, causing approximately 618,000 deaths in 2002, according to the World Health Organization 5. Tomographic imaging modalities like X-ray computed tomography (CT) play an important role in diagnosis and treatment of liver diseases like hepatocellular carcinoma (HCC). Deriving a digital geometric model of hepatic (patho)anatomy from preoperative image data facilitates treatment planning [1]. Thus, methods for liver segmentation in volume data are needed which are applicable in clinical routine. In this context, several problems have to be addressed: (a) high shape variation due to natural anatomical variation, disease (e.g., cirrhosis), or previous surgical interventions (e.g., liver segment resection), (b) inhomogeneous gray-value appearance caused by tumors or metastasis, and (c) low contrast to neighboring structures/organs like colon or Cristian Bauer was supported by the doctoral program Confluence of Vision and Graphics W T. Heimann, M. Styner, B. van Ginneken (Eds.): 3D Segmentation in The Clinic: A Grand Challenge, pp , 2007.

2 stomach. For practical application, segmentation must be capable of handling all possible cases in a time-efficient manner. Several approaches to liver segmentation have been developed so far (see [2 6] for examples). However, in summary, basic bottom-up segmentation algorithms frequently fail, especially in more complex cases like livers with large tumors. In addition, solely model-based approaches are problematic, because of the high shape variability of the liver. Very few approaches provide methods for the refinement or editing of segmentation results. In general, segmentation refinement approaches are very rare. For example, a tool is reported in [7] and [8] where Rational Gaussian (RaG) Surfaces are used to represent segmented objects. Segmentation errors can be corrected by manipulation control points using a 2D desktop setup. Another tool for data driven editing of pre-segmented images/volumes based on graph cuts or alternatively random walker algorithms was proposed in [9]. All approaches mentioned so far are based on 2D interaction and monoscopic desktop-based visualization techniques, despite the fact that 3D objects are targeted. Usually, 2D interaction methods are not sufficient for refinement of 3D models extracted from volumetric data sets, which is inherently a 3D task [10]. We propose a novel refinement approach to 3D liver segmentation. Based on an initial highly automated graph cut segmentation, refinement tools allow to manipulate the segmentation result in 3D, and thus, to correct possible errors. Segmentation refinement is facilitated by a hybrid user interface, combining a conventional desktop setup with a virtual reality (VR) system. The segmentation approach was developed for clinical application. In addition, our concept can be utilized for other segmentation tasks. 2 Methods The proposed approach to liver segmentation consists of two main stages: initial segmentation and interactive segmentation refinement. As input for the first stage, a CT volume and one or more start regions, marking liver tissue, are used. The segmentation is then generated using a graph cut approach 6. In addition, a partitioning of the segmentation and the background into volume chunks is derived from edge/surface features calculated from CT volume. These two types of output are passed on to the second stage which allows for the correction/refinement of segmentation errors remaining after the first stage. Refinement takes place in two steps. First, volume chunks can be added or removed. This step is usually very fast, and the majority of segmentation errors occurring in practice can be fixed or at least significantly reduced. Second, after conversion of the binary segmentation to a simplex mesh, arbitrary errors can be addressed by deforming the mesh using various tools. Each of the refinement steps is facilitated using interactive VR-enabled tools for true 3D segmentation inspection and refinement, allowing for stereoscopic viewing and true 3D interaction. Since 6 Note that graph cut segmentation is not used interactively, as proposed by Boykov et al. in [11], since the behavior of graph cuts is not always intuitive. 236

3 the last stage of the refinement procedure is mesh-based, a voxelization method is used to generate a labeled volume [12]. 2.1 Graph-Cut-based initial segmentation An initial segmentation is generated using a graph cut [11] approach. From image data, a graph G = (V, E) is built, where nodes are denoted by V and undirected edges by E. Nodes V of the graph are formed by data elements (voxels), and two additional terminal nodes, a source node s and sink node t. Edge weights allow to model different relations between nodes (see [11] for details). Let P denote the set of voxels from the input volume data set V to reduce computing time, only voxels with density values above 600 Hounsfield Units (HU) are considered as potentially belonging to the liver. The partition A = (A 1,..., A p,..., A P ) with A p { obj, bkg } can be used to represent the segmentation of P into object ( obj ) and background ( bkg ) voxels. Let N be the set of unordered neighboring pairs {p, q} in set P according to the used neighborhood relation. In our case, a 6-neighborhood relation is used to save memory. The cost of a given graph cut segmentation A is defined as E(A) = B(A)+λR(A) where R(A) = p P R p(a p ) takes region properties into account and B(A) = {p,q} N B p,qδ Ap A q, with δ Ap A q equaling 1 if A p A q and 0 if A p = A q, being boundary properties. The parameter λ with λ 0 allows to tradeoff the influence of both cost terms. Using the s-t cut algorithm, a partition A can be found which globally minimizes E(A). However, in practice a refinement of this segmentation result might be necessary to be useful for a given clinical application. Region term The region term R(A) specifies the costs of assigning a voxel to a label based on its gray-value similarity to object and background regions. For this purpose, user defined seed regions are utilized. Following the approach proposed in [13], region cost R p ( ) for a given voxel p is defined for labels obj and bkg as negative log-likelihoods R p ( obj ) = ln(p r(i p obj )) and R p ( bkg ) = ln(p r(i p bkg )) with P r(i p obj ) = e (Ip m obj) 2 /(2σ 2 obj ) and P r(i p bkg ) = 1 P r(i p obj ), respectively. From a object seed region placed inside the liver, the mean m obj and standard deviation σ obj are calculated. Clearly, in the above outlined approach, a simplification is made since liver gray-value appearance is usually not homogeneous. However, this simplification works quite well in practice in combination with the other processing steps. Further, the specified object seeds are incorporated as hard constraints, and the boundary of the scene is used as background seeds. Boundary term The basic idea is to utilize a surfaceness measure as boundary term which is calculated in four steps: 1. Gradient tensor calculation: First, to reduce the effect of unrelated structures on the gradient, the gray value range of the image is adapted: v low if I f < t low Ĩ f = κ(i f ) = v high if I f > t high. otherwise I f 237

4 Second, a gradient vector f = (f x, f y, f z ) T is calculated for each voxel f on the with κ gray-vale transformed data volume V by means of Gaussian derivatives with the kernel g σ = 1/(2πσ 2 ) 3 2 e x2 +y 2 +z 2 2σ 2 and standard deviation σ. The gradient tensor S = f f T is calculated for each voxel after gray-value transformation. 2. Spatial non-linear filtering: To enhance weak edges and to reduce false responses, a spatial non-linear averaging of gradient tensors is applied. The non-linear filter kernel consists of a Gaussian kernel which is modulated by the local gradient vector f. Given a vector x that points from the center of the kernel to any neighboring voxel, the weight for this voxel 1 r N is calculated as: h σ,ρ(x, f) = e 2σ 2 e tan(φ) 2 2ρ 2 if φ π 2 0 if φ = π 2 and r = 0, 1 N otherwise with r = x T x and φ = π 2 arccos( f T x/( f x )). Parameter ρ determines the strength of orientedness, and σ determines the strength of punishment depending on the distance. N is a normalization factor that makes the kernel integrate to unity. The resulting structure tensor is denoted as W. 3. Surfaceness measure calculation: Let e 1W(x), e 2W(x), e 3W(x) be the eigenvectors and λ 1W(x) λ 2W(x) λ 3W(x) the corresponding eigenvalues of W(x) at position x. If x is located on a plane-like structure, we can observe that λ 1 0, λ 2 0, and λ 3 0. Thus, we define the surfaceness measure as t(w(x)) = λ 1W(x) λ 2W(x) and the direction of the normal vector to the surface is given by e 1W(x). 4. Boundary weight calculation: In liver CT images, objects are often separated only by weak boundaries, with higher gray level gradients present in close proximity. To take these circumstances into account, we propose the following boundary cost term B p,q = min{ξ (t(w(x p ))), ξ (t(w(x q )))} c 1 if t < t 1 with the weighting function ξ(t) = c 2 if t > t 2 (t t 1 ) c2 c1 t 2 t 1 + c 1 otherwise which models a uncertainty zone between t 1 and t 2 (note: t 1 < t 2 and c 1 > c 2 ). Ideally, the graph cut segmentation should follow the ridges of the gradient magnitude. Therefore, we punish non-maximal responses in the gradient magnitude volume by adjusted the weighting function as follows: ξ non max (t) = min{ξ(t) + c nm, 1}, where c nm is a constant. 2.2 Chunk-based Segmentation Refinement After initial segmentation, objects with a similar gray-value range in close proximity can appear merged or tumors with different gray-value appearance might be missing. Therefore, a refinement may be needed in some cases. The first refinement stage is based on volume chunks, which subdivide the graph cut segmentation result (object) as well as the background into disjunct subregions. 238

5 (a) (b) (c) (d) Fig. 1. Mesh-based refinement using a sphere deformation tool. In this case the segmentation error is a leak. (a) Marking the region containing the segmentation error. (b) Refinement using the sphere tool. (c) After pushing the mesh surface back to the correct location with the sphere tool, the error is fixed. (d) The corrected region in wire frame mode highlighting the mesh contour. Fig. 2. Initial graph cut (GC) segmentation results. 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

6 Thus, the initial segmentation can be represented by chunks and it can be altered by adding or removing chunks. By thresholding t(w), a binary boundary volume (threshold t b ) representing boundary/surfaces parts is generated and merged with the boundary from the graph cut segmentation by using a logical or operation. Then the distance transformation is calculated. Inverting this distance map results in an image that can be interpreted as a height map. To avoid oversegmentation, all small local minima resulting from quantization noise in the distance map are eliminated. Applying a watershed segmentation to the distance map results in volume chunks. Since boundary voxels are not part of the chunks, they are merged with the neighboring chunks containing the most similar adjacent voxels. Since the method can handle gaps in the edge scene, the threshold t b can be set very conservatively to suppress background noise. Refinement can be done very efficiently, since the user has to select/deselect predefined chunks, which does not require a detailed border delineation. This step requires adequate tools for interactive data inspection and selection methods. For this purpose, a hybrid user interface was developed, which is described in Section Simplex-Mesh-based Refinement After the first refinement step, selected chunks are converted to a simplex mesh representation. Different tools allow then a deformation of the mesh representation. One example is shown in Fig. 1. More details regarding this mesh-based refinement step can be found in [14]. 2.4 Hybrid Desktop/Virtual Reality User Interface To facilitate segmentation refinement, a hybrid user interface consisting of a desktop part and a virtual reality (VR) part was developed (see [10] for details). It allows to solve individual refinement tasks using the best suited interaction technique, either in 2D or 3D. The VR system part provides stereoscopic visualization on a large screen projection wall, while the desktop part of the system uses a touch screen for monoscopic visualization. 3 Data and Experimental Setup For evaluation of the segmentation approach, ten liver CT data sets with undisclosed manual reference segmentation were provided by the workshop organizers. Segmentation results were sent to the organizers, which provided in return evaluation results 7. For all the experiments, the following parameters have been used: Gaussian derivative kernel: σ = 3.0; non-linear filtering: σ = 6.0, ρ = 0.4; graph cut: λ = 0.05; weighting function: t 1 = 2.0, t 2 = 10.0, c 1 = 1.0, c 2 = 0.001, c cm = 0.75; Threshold for chunk generation: t b = 10.0; gray-value transformation: t low = 50, v low = 150, t high = 200, and v high = 60. To simulate clinical 7 See for details. 240

7 work-flow, the initial seed regions were provided manually and the graph cut segmentation as well as the chunk generation was calculated automatically. Based on the initial segmentation, a medical expert was asked to perform: (a) chunkbased (CBR) and (b) mesh-based refinement (MBR). Intermediate results and task completion times were recorded. Prior to evaluation, the expert was introduced to the system by an instructor. Fig. 3. Chunk-based segmentation refinement (CBR) results. 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 Results Table 1 summarizes segmentation metrics and corresponding scores for the initial graph cut segmentation (Table 1(a)), CBR (Table 1(b)), and MBR (Table 1(c)). The averaged performance measures and scores clearly show the effectiveness 241

8 of the segmentation refinement concept: metrics and scores improve with each refinement stage. For example, after the initial graph cut segmentation, five cases have an overlap error larger than 10 %, and the over-all average is 14.3 %. Using CBR, the average overlap error was reduced to 6.5 %, and reached 5.2 % after the final MBR stage. The average time needed for seed placement is less than 30 seconds. For the CBR step 58 seconds were required on average, and the MBR step took approximately five minutes on average. Despite the low time consumption of the CBR step, it is quite effective regarding segmentation quality improvement and delivers already a good segmentation result. Computation time for the graph cut segmentation and chunk generation was approximately 30 minutes per data set, which is not critical for our application. Fig. 4. Mesh-based segmentation refinement (MBR) results. 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. In comparison, averages for the performance measures determined from an independent human segmentation of several test cases yielded: 6.4 % volumetric 242

9 overlap; 4.7 % relative absolute volume difference; 1.0 mm average symmetric absolute surface distance; 1.8 mm symmetric RMS surface distance; 19 mm maximum symmetric absolute surface distance 8. Thus, our refinement results (CBR and MBR) are within the observed variation range (see Table 1). Figs. 2, 3, and 4 depict a comparison of reference and actual segmentation for the initial graph cut, CBR, and MBR for three different data sets. Because of the formulation of the initial graph cut segmentation, larger tumors are not included in the segmentation result, as shown in the third row of Fig. 2. However, this can be easily fixed during the CBR stage (Fig. 3). Remaining errors can then be fixed in MBR stage. The examples show that the average maximum symmetric absolute surface distance of 15.7 mm on average can be explained by differences in the interpretation of the data in regions where vessels enter or leave the liver. 5 Discussion For our experiments, we have used a full-blown VR setup which is quite expensive. However, a fully functional scaled-down working setup can be built for a reasonable price, comparable to the costs of a radiological workstation. Several experiments with different physicians have shown that the system can be operated after a short learning phase (typically less that one hour), because of the intuitive 3D user interface. The proposed refinement method can also easily be integrated into clinical work-flow. The CT volume together with the manual generated start region is sent by a radiology assistant to a computing node which performs the automated segmentation steps. As soon as a result is available, a radiologist is notified that data are ready for further processing. After inspection, possible refinement, and approval of correctness, the segmentation can be used for clinical investigations or planning of treatment. A previous independently performed evaluation with twenty routinely acquired CT data sets of potential liver surgery candidates yielded a comparable segmentation error. However, more time was needed for interactive refinement. This has several reasons: lower data quality (more partial volume effect, motion blur due to cardiac motion, etc.), more severely diseased livers with larger tumors or multiple tumors, and more focus on details (e.g., consistently excluding the inferior vena cava). These observations lead to the following conclusions. First, the used imaging protocol impacts the time needed for segmentation refinement, and thus, should be optimized. Second, the developed method allows the user to adjust the level of detail according to the requirements in trade-off with interaction time. 6 Conclusion In this paper we have presented an interactive true 3D segmentation refinement concept for liver segmentation in contrast-enhanced CT data. The approach consists of two stages: initial graph cut segmentation and interactive 3D refinement. 8 The values reported were provided by the workshop organizers. 243

10 (a) Graph Cut (GC) Dataset Overlap Error Volume Diff. Avg. Dist. RMS Dist. Max. Dist. Total [%] Score [%] Score [mm] Score [mm] Score [mm] Score Score Average (b) Chunk-based Refinement (CBR) Dataset Overlap Error Volume Diff. Avg. Dist. RMS Dist. Max. Dist. Total [%] Score [%] Score [mm] Score [mm] Score [mm] Score Score Average (c) Mesh-based Refinement (MBR) Dataset Overlap Error Volume Diff. Avg. Dist. RMS Dist. Max. Dist. Total [%] Score [%] Score [mm] Score [mm] Score [mm] Score Score Average Table 1. Results of the comparison metrics and corresponding scores for all ten test cases and processing steps (see Section 4 for details). 244

11 The evaluation of our method on ten test CT data sets shows that a high segmentation quality (mean average distance of less than 1 mm) can be achieved by using this approach. In addition, the interaction time needed for refinement is quite low (approx. 6.5 minutes). Thus, the presented refinement concept is well suited for clinical application. The approach is not limited to a specific organ or modality, and therefore, it is very promising for other medical segmentation applications. References 1. Reitinger, B., Bornik, A., Beichel, R., Schmalstieg, D.: Liver surgery planning using virtual reality. IEEE Comput. Graph. Appl. 26(6) (2006) Schenk, A., Prause, G.P.M., Peitgen, H.O.: Efficient semiautomatic segmentation of 3D objects in medical images. In: Medical Image Computing and Computer- Assisted Intervention (MICCAI), Springer (2000) Pan, S., Dawant, M.: Automatic 3D segmentation of the liver from abdominal CT images: A level-set approach. In Sonka, M., Hanson, K.M., eds.: Medical Imaging: Image Processing. Volume 4322 of Proc. SPIE. (2001) Soler, L., et al.: Fully automatic anatomical, pathological, and functional segmentation from CT scans for hepatic surgery. Computer Aided Surgery 6(3) (2001) Lamecker, H., et al.: Segmentation of the liver using a 3D statistical shape model. Technical report, Konrad-Zuse-Zentrum für Informationstechnik Berlin (2004) 6. 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: Medical Image Computing and Computer-Assisted Intervention (MICCAI). Volume 4191 of Lecture Notes in Computer Science., Springer Berlin / Heidelberg (2006) Jackowski, M., Goshtasby, A.: A computer-aided design system for revision of segmentation errors. In: Proc. Medical Image Computing and Computer-Assisted Intervention (MICCAI). Volume 2. (2005) Beichel, R., et al.: Shape- and appearance-based segmentation of volumetric medical images. In: Proc. of ICIP Volume 2. (2001) Grady, L., Funka-Lea, G.: An energy minimization approach to the data driven editing of presegmented images/volumes. In: Medical Image Computing and Computer-Assisted Intervention MICCAI. Volume 4191., Springer (2006) Bornik, A., Beichel, R., Kruijff, E., Reitinger, B., Schmalstieg, D.: A hybrid user interface for manipulation of volumetric medical data. In: Proceedings of IEEE Symposium on 3D User Interfaces 2006, IEEE Computer Society (2006) Boykov, Y., Funka-Lea, G.: Graph cuts and efficient N-D image segmentation. In International Journal of Computer Vision (IJCV) 70(2) (2006) Reitinger, B., et al.: Tools for augmented reality-based liver resection planning. In Galloway, R.L., ed.: Medical Imaging 2004: Visualization, Image-Guided Procedures, and Display. Volume 5367., SPIE (2004) Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: ICCV. Volume 1. (2001) Bornik, A., Beichel, R., Schmalstieg, D.: Interactive editing of segmented volumetric datasets in a hybrid 2D/3D virtual environment. In: VRST 06: Proceedings of the ACM symposium on Virtual reality software and technology. (2006)

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

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

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

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

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

More information

HepaTux A Semiautomatic Liver Segmentation System

HepaTux A Semiautomatic Liver Segmentation System HepaTux A Semiautomatic Liver Segmentation System Andreas Beck and Volker Aurich Institut für Informatik, Heinrich-Heine-Universität Düsseldorf, D-40225 Düsseldorf becka-miccai@acs.uni-duesseldorf.de Abstract.

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

3D contour based local manual correction of tumor segmentations in CT scans

3D contour based local manual correction of tumor segmentations in CT scans 3D contour based local manual correction of tumor segmentations in CT scans Frank Heckel a, Jan Hendrik Moltz a, Lars Bornemann a, Volker Dicken a, Hans-Christian Bauknecht b,michaelfabel c, Markus Hittinger

More information

Interactive segmentation of vascular structures in CT images for liver surgery planning

Interactive segmentation of vascular structures in CT images for liver surgery planning Interactive segmentation of vascular structures in CT images for liver surgery planning L. Wang¹, C. Hansen¹, S.Zidowitz¹, H. K. Hahn¹ ¹ Fraunhofer MEVIS, Institute for Medical Image Computing, Bremen,

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

Interactive Differential Segmentation of the Prostate using Graph-Cuts with a Feature Detector-based Boundary Term

Interactive Differential Segmentation of the Prostate using Graph-Cuts with a Feature Detector-based Boundary Term MOSCHIDIS, GRAHAM: GRAPH-CUTS WITH FEATURE DETECTORS 1 Interactive Differential Segmentation of the Prostate using Graph-Cuts with a Feature Detector-based Boundary Term Emmanouil Moschidis emmanouil.moschidis@postgrad.manchester.ac.uk

More information

Automatic Lung Segmentation of Volumetric Low-Dose CT Scans Using Graph Cuts

Automatic Lung Segmentation of Volumetric Low-Dose CT Scans Using Graph Cuts Automatic Lung Segmentation of Volumetric Low-Dose CT Scans Using Graph Cuts Asem M. Ali and Aly A. Farag Computer Vision and Image Processing Laboratory (CVIP Lab) University of Louisville, Louisville,

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

Image Segmentation Using Iterated Graph Cuts BasedonMulti-scaleSmoothing

Image Segmentation Using Iterated Graph Cuts BasedonMulti-scaleSmoothing Image Segmentation Using Iterated Graph Cuts BasedonMulti-scaleSmoothing Tomoyuki Nagahashi 1, Hironobu Fujiyoshi 1, and Takeo Kanade 2 1 Dept. of Computer Science, Chubu University. Matsumoto 1200, Kasugai,

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

MEDICAL IMAGE COMPUTING (CAP 5937) LECTURE 10: Medical Image Segmentation as an Energy Minimization Problem

MEDICAL IMAGE COMPUTING (CAP 5937) LECTURE 10: Medical Image Segmentation as an Energy Minimization Problem SPRING 07 MEDICAL IMAGE COMPUTING (CAP 97) LECTURE 0: Medical Image Segmentation as an Energy Minimization Problem Dr. Ulas Bagci HEC, Center for Research in Computer Vision (CRCV), University of Central

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

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

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

Segmentation of Airways Based on Gradient Vector Flow

Segmentation of Airways Based on Gradient Vector Flow EXACT'09-191- Segmentation of Airways Based on Gradient Vector Flow Christian Bauer 1,2, Horst Bischof 1, and Reinhard Beichel 2,3,4 1 Inst. for Computer Graphics and Vision, Graz University of Technology,

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

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

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

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 COMPUTING (CAP 5937) LECTURE 9: Medical Image Segmentation (III) (Fuzzy Connected Image Segmentation)

MEDICAL IMAGE COMPUTING (CAP 5937) LECTURE 9: Medical Image Segmentation (III) (Fuzzy Connected Image Segmentation) SPRING 2017 1 MEDICAL IMAGE COMPUTING (CAP 5937) LECTURE 9: Medical Image Segmentation (III) (Fuzzy Connected Image Segmentation) Dr. Ulas Bagci HEC 221, Center for Research in Computer Vision (CRCV),

More information

Adaptive Fuzzy Connectedness-Based Medical Image Segmentation

Adaptive Fuzzy Connectedness-Based Medical Image Segmentation Adaptive Fuzzy Connectedness-Based Medical Image Segmentation Amol Pednekar Ioannis A. Kakadiaris Uday Kurkure Visual Computing Lab, Dept. of Computer Science, Univ. of Houston, Houston, TX, USA apedneka@bayou.uh.edu

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

Segmentation of Neck Lymph Nodes in CT Datasets with Stable 3D Mass-Spring Models

Segmentation of Neck Lymph Nodes in CT Datasets with Stable 3D Mass-Spring Models Segmentation of Neck Lymph Nodes in CT Datasets with Stable 3D Mass-Spring Models Jana Dornheim 1, Heiko Seim 1, Bernhard Preim 1, Ilka Hertel 2, and Gero Strauss 2 1 Otto-von-Guericke-Universität Magdeburg,

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

Nearly automatic vessels segmentation using graph-based energy minimization

Nearly automatic vessels segmentation using graph-based energy minimization Nearly automatic vessels segmentation using graph-based energy minimization Release 1.00 M. Freiman 1, J. Frank 1, L. Weizman 1 E. Nammer 2, O. Shilon 2,, L. Joskowicz 1 and J. Sosna 3 July 16, 2009 1

More information

Graph Based Image Segmentation

Graph Based Image Segmentation AUTOMATYKA 2011 Tom 15 Zeszyt 3 Anna Fabijañska* Graph Based Image Segmentation 1. Introduction Image segmentation is one of the fundamental problems in machine vision. In general it aims at extracting

More information

IMAGE SEGMENTATION IN MEDICAL IMAGING VIA GRAPH-CUTS 1

IMAGE SEGMENTATION IN MEDICAL IMAGING VIA GRAPH-CUTS 1 IMAGE SEGMENTATION IN MEDICAL IMAGING VIA GRAPH-CUTS 1 M. Jirik 2, V. Lukes 3, M. Svobodova 4, M. Zelezny 5 2 Department of Cybernetics at University of West Bohemia, mjirik@kky.zcu.cz 3 Department of

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

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

MEDICAL IMAGE COMPUTING (CAP 5937) LECTURE 10: Medical Image Segmentation as an Energy Minimization Problem

MEDICAL IMAGE COMPUTING (CAP 5937) LECTURE 10: Medical Image Segmentation as an Energy Minimization Problem SPRING 06 MEDICAL IMAGE COMPUTING (CAP 97) LECTURE 0: Medical Image Segmentation as an Energy Minimization Problem Dr. Ulas Bagci HEC, Center for Research in Computer Vision (CRCV), University of Central

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

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

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

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

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

Interactive Editing of Segmented Volumetric Datasets in a Hybrid 2D/3D Virtual Environment

Interactive Editing of Segmented Volumetric Datasets in a Hybrid 2D/3D Virtual Environment Interactive Editing of Segmented Volumetric atasets in a Hybrid 2/3 Virtual Environment Alexander Bornik bornik@icg.tu-graz.ac.at Reinhard Beichel beichel@icg.tu-graz.ac.at Institute for Computer Graphics

More information

Edge-Preserving Denoising for Segmentation in CT-Images

Edge-Preserving Denoising for Segmentation in CT-Images Edge-Preserving Denoising for Segmentation in CT-Images Eva Eibenberger, Anja Borsdorf, Andreas Wimmer, Joachim Hornegger Lehrstuhl für Mustererkennung, Friedrich-Alexander-Universität Erlangen-Nürnberg

More information

Advanced Visual Medicine: Techniques for Visual Exploration & Analysis

Advanced Visual Medicine: Techniques for Visual Exploration & Analysis Advanced Visual Medicine: Techniques for Visual Exploration & Analysis Interactive Visualization of Multimodal Volume Data for Neurosurgical Planning Felix Ritter, MeVis Research Bremen Multimodal Neurosurgical

More information

Context-sensitive Classification Forests for Segmentation of Brain Tumor Tissues

Context-sensitive Classification Forests for Segmentation of Brain Tumor Tissues Context-sensitive Classification Forests for Segmentation of Brain Tumor Tissues D. Zikic, B. Glocker, E. Konukoglu, J. Shotton, A. Criminisi, D. H. Ye, C. Demiralp 3, O. M. Thomas 4,5, T. Das 4, R. Jena

More information

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

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

More information

A Study of Medical Image Analysis System

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

More information

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

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

More information

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

Fast Correction Method for Abdominal Multi-Organ Segmentation Using 2D/3D Free Form Deformation and Posterior Shape Models

Fast Correction Method for Abdominal Multi-Organ Segmentation Using 2D/3D Free Form Deformation and Posterior Shape Models Fast Correction Method for Abdominal Multi-Organ Segmentation Using 2D/3D Free Form Deformation and Posterior Shape Models Waldo Valenzuela 1, Juan Cerrolaza 2, Ronald M. Summers 3, Marius George Linguraru

More information

Graz University of Technology. Dissertation. Virtual Liver Surgery Planning: Simulation of Resections using Virtual Reality Techniques

Graz University of Technology. Dissertation. Virtual Liver Surgery Planning: Simulation of Resections using Virtual Reality Techniques Graz University of Technology Institute for Computer Graphics and Vision Dissertation Virtual Liver Surgery Planning: Simulation of Resections using Virtual Reality Techniques Bernhard Reitinger Graz,

More information

Anatomic Hepatectomy Planning through Mobile Display Visualization and Interaction

Anatomic Hepatectomy Planning through Mobile Display Visualization and Interaction Anatomic Hepatectomy Planning through Mobile Display Visualization and Interaction Henrique Galvan DEBARBA a,1, Jerônimo GRANDI a, Anderson MACIEL a and Dinamar ZANCHET b a Instituto de Informática (INF),

More information

Automatic Vascular Tree Formation Using the Mahalanobis Distance

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

More information

Norbert Schuff VA Medical Center and UCSF

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

More information

doi: /

doi: / Yiting Xie ; Anthony P. Reeves; Single 3D cell segmentation from optical CT microscope images. Proc. SPIE 934, Medical Imaging 214: Image Processing, 9343B (March 21, 214); doi:1.1117/12.243852. (214)

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

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

Segmentation and Grouping

Segmentation and Grouping Segmentation and Grouping How and what do we see? Fundamental Problems ' Focus of attention, or grouping ' What subsets of pixels do we consider as possible objects? ' All connected subsets? ' Representation

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

Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks

Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks Du-Yih Tsai, Masaru Sekiya and Yongbum Lee Department of Radiological Technology, School of Health Sciences, Faculty of

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

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

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

MR IMAGE SEGMENTATION

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

More information

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

Image Segmentation. Shengnan Wang

Image Segmentation. Shengnan Wang Image Segmentation Shengnan Wang shengnan@cs.wisc.edu Contents I. Introduction to Segmentation II. Mean Shift Theory 1. What is Mean Shift? 2. Density Estimation Methods 3. Deriving the Mean Shift 4. Mean

More information

TUMOR DETECTION IN MRI IMAGES

TUMOR DETECTION IN MRI IMAGES TUMOR DETECTION IN MRI IMAGES Prof. Pravin P. Adivarekar, 2 Priyanka P. Khatate, 3 Punam N. Pawar Prof. Pravin P. Adivarekar, 2 Priyanka P. Khatate, 3 Punam N. Pawar Asst. Professor, 2,3 BE Student,,2,3

More information

Modern Medical Image Analysis 8DC00 Exam

Modern Medical Image Analysis 8DC00 Exam Parts of answers are inside square brackets [... ]. These parts are optional. Answers can be written in Dutch or in English, as you prefer. You can use drawings and diagrams to support your textual answers.

More information

How and what do we see? Segmentation and Grouping. Fundamental Problems. Polyhedral objects. Reducing the combinatorics of pose estimation

How and what do we see? Segmentation and Grouping. Fundamental Problems. Polyhedral objects. Reducing the combinatorics of pose estimation Segmentation and Grouping Fundamental Problems ' Focus of attention, or grouping ' What subsets of piels do we consider as possible objects? ' All connected subsets? ' Representation ' How do we model

More information

Computational Radiology Lab, Children s Hospital, Harvard Medical School, Boston, MA.

Computational Radiology Lab, Children s Hospital, Harvard Medical School, Boston, MA. Shape prior integration in discrete optimization segmentation algorithms M. Freiman Computational Radiology Lab, Children s Hospital, Harvard Medical School, Boston, MA. Email: moti.freiman@childrens.harvard.edu

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

Segmentation of Images

Segmentation of Images Segmentation of Images SEGMENTATION If an image has been preprocessed appropriately to remove noise and artifacts, segmentation is often the key step in interpreting the image. Image segmentation is a

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

Model-based segmentation and recognition from range data

Model-based segmentation and recognition from range data Model-based segmentation and recognition from range data Jan Boehm Institute for Photogrammetry Universität Stuttgart Germany Keywords: range image, segmentation, object recognition, CAD ABSTRACT This

More information

Semantic Context Forests for Learning- Based Knee Cartilage Segmentation in 3D MR Images

Semantic Context Forests for Learning- Based Knee Cartilage Segmentation in 3D MR Images Semantic Context Forests for Learning- Based Knee Cartilage Segmentation in 3D MR Images MICCAI 2013: Workshop on Medical Computer Vision Authors: Quan Wang, Dijia Wu, Le Lu, Meizhu Liu, Kim L. Boyer,

More information

Model-Based Segmentation of Pathological Lungs in Volumetric CT Data

Model-Based Segmentation of Pathological Lungs in Volumetric CT Data Third International Workshop on Pulmonary Image Analysis -31- Model-Based Segmentation of Pathological Lungs in Volumetric CT Data Shanhui Sun 1,5, Geoffrey McLennan 2,3,4,5,EricA.Hoffman 3,2,4,5,and Reinhard

More information

Lung and Lung Lobe Segmentation Methods by Fraunhofer MEVIS

Lung and Lung Lobe Segmentation Methods by Fraunhofer MEVIS Lung and Lung Lobe Segmentation Methods by Fraunhofer MEVIS Bianca Lassen, Jan-Martin Kuhnigk, Michael Schmidt, and Heinz-Otto Peitgen Fraunhofer MEVIS, Universitaetsallee 29, 28359 Bremen, Germany http://www.mevis.fraunhofer.de

More information

Rule-Based Ventral Cavity Multi-organ Automatic Segmentation in CT Scans

Rule-Based Ventral Cavity Multi-organ Automatic Segmentation in CT Scans Rule-Based Ventral Cavity Multi-organ Automatic Segmentation in CT Scans Assaf B. Spanier (B) and Leo Joskowicz The Rachel and Selim Benin School of Computer Science and Engineering, The Hebrew University

More information

Supervised Probabilistic Segmentation of Pulmonary Nodules in CT Scans

Supervised Probabilistic Segmentation of Pulmonary Nodules in CT Scans Supervised Probabilistic Segmentation of Pulmonary Nodules in CT Scans Bram van Ginneken Image Sciences Institute, University Medical Center Utrecht, the Netherlands bram@isi.uu.nl Abstract. An automatic

More information

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

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

More information

Semi-Automatic Topology Independent Contour- Based 2 ½ D Segmentation Using Live-Wire

Semi-Automatic Topology Independent Contour- Based 2 ½ D Segmentation Using Live-Wire Semi-Automatic Topology Independent Contour- Based 2 ½ D Segmentation Using Live-Wire Michael Knapp Vienna University of Technology Computer Graphics Group Favoritenstrasse 9-11/E186 1040 Wien, Austria

More information

Introduction to Medical Image Processing

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

More information

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

A Workflow Optimized Software Platform for Multimodal Neurosurgical Planning and Monitoring

A Workflow Optimized Software Platform for Multimodal Neurosurgical Planning and Monitoring A Workflow Optimized Software Platform for Multimodal Neurosurgical Planning and Monitoring Eine Workflow Optimierte Software Umgebung für Multimodale Neurochirurgische Planung und Verlaufskontrolle A

More information

Determination of a Vessel Tree Topology by Different Skeletonizing Algorithms

Determination of a Vessel Tree Topology by Different Skeletonizing Algorithms Determination of a Vessel Tree Topology by Different Skeletonizing Algorithms Andre Siegfried Prochiner 1, Heinrich Martin Overhoff 2 1 Carinthia University of Applied Sciences, Klagenfurt, Austria 2 University

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

NEW REGION GROWING ALGORITHM FOR BRAIN IMAGES SEGMENTATION

NEW REGION GROWING ALGORITHM FOR BRAIN IMAGES SEGMENTATION Volume 4, No. 5, May 203 Journal of Global Research in Computer Science RESEARCH PAPER Available Online at www.grcs.info NEW REGION GROWING ALGORITHM FOR BRAIN IMAGES SEGMENTATION Sultan Alahdali, E. A.

More information

Liver Tumor Detection using Artificial Neural Networks for Medical Images

Liver Tumor Detection using Artificial Neural Networks for Medical Images IJIRST International Journal for Innovative Research in Science & Technology Volume 2 Issue 03 August 2015 ISSN (online): 2349-6010 Liver Tumor Detection using Artificial Neural Networks for Medical Images

More information

Vertebrae Segmentation in 3D CT Images based on a Variational Framework

Vertebrae Segmentation in 3D CT Images based on a Variational Framework Vertebrae Segmentation in 3D CT Images based on a Variational Framework Kerstin Hammernik, Thomas Ebner, Darko Stern, Martin Urschler, and Thomas Pock Abstract Automatic segmentation of 3D vertebrae is

More information

Various Methods for Medical Image Segmentation

Various Methods for Medical Image Segmentation Various Methods for Medical Image Segmentation From Level Set to Convex Relaxation Doyeob Yeo and Soomin Jeon Computational Mathematics and Imaging Lab. Department of Mathematical Sciences, KAIST Hansang

More information

CT IMAGE PROCESSING IN HIP ARTHROPLASTY

CT IMAGE PROCESSING IN HIP ARTHROPLASTY U.P.B. Sci. Bull., Series C, Vol. 75, Iss. 3, 2013 ISSN 2286 3540 CT IMAGE PROCESSING IN HIP ARTHROPLASTY Anca MORAR 1, Florica MOLDOVEANU 2, Alin MOLDOVEANU 3, Victor ASAVEI 4, Alexandru EGNER 5 The use

More information

arxiv: v1 [cs.cv] 6 Jun 2017

arxiv: v1 [cs.cv] 6 Jun 2017 Volume Calculation of CT lung Lesions based on Halton Low-discrepancy Sequences Liansheng Wang a, Shusheng Li a, and Shuo Li b a Department of Computer Science, Xiamen University, Xiamen, China b Dept.

More information

EE 701 ROBOT VISION. Segmentation

EE 701 ROBOT VISION. Segmentation EE 701 ROBOT VISION Regions and Image Segmentation Histogram-based Segmentation Automatic Thresholding K-means Clustering Spatial Coherence Merging and Splitting Graph Theoretic Segmentation Region Growing

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

Topic 4 Image Segmentation

Topic 4 Image Segmentation Topic 4 Image Segmentation What is Segmentation? Why? Segmentation important contributing factor to the success of an automated image analysis process What is Image Analysis: Processing images to derive

More information

IMAGE SEGMENTATION. Václav Hlaváč

IMAGE SEGMENTATION. Václav Hlaváč IMAGE SEGMENTATION Václav Hlaváč Czech Technical University in Prague Faculty of Electrical Engineering, Department of Cybernetics Center for Machine Perception http://cmp.felk.cvut.cz/ hlavac, hlavac@fel.cvut.cz

More information

Ulrik Söderström 16 Feb Image Processing. Segmentation

Ulrik Söderström 16 Feb Image Processing. Segmentation Ulrik Söderström ulrik.soderstrom@tfe.umu.se 16 Feb 2011 Image Processing Segmentation What is Image Segmentation? To be able to extract information from an image it is common to subdivide it into background

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

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 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

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

3D Visualization of Vascular Structures

3D Visualization of Vascular Structures 3D Visualization of Vascular Structures Bernhard Preim, University of Magdeburg, Visualization Research Group Outline Methods for 3D Visualization of Vasculature Model-based Surface Visualization Explicit

More information