DE102008036812A1 - Method for segmenting object from image data set, involves providing implicit form model for segmenting object from training data records - Google Patents

Abstract

The method involves providing an implicit form model for a segmenting object from training data records. The object is segmented by gradual approach of an active contour on base of the form model to the object contour in an image data set. An area of same distance is observed around the active contour superimposing the image data set for repeating the approach. Each screen dot of the image data set is assigned in the area of a signed distance value. The distance value represents a measurement for a distance of the screen dot to the active contour. An independent claim is included for a device for segmenting an object from an image data set for the execution of the method.

Description

The The present invention relates to a method and a device for segmentation of an object from an image data set in which From training data, first an implicit statistical Form model of the object is created and the segmentation of the object then by adapting an active contour to a Object contour is done in the image data set, wherein the shape model the Deformation of the active contour is limited.

in the The field of medical imaging represents the segmentation anatomical Structures such as the liver from image data sets a fundamental task. Based on the segmentation result can be the size or volume content of the object be determined. These sizes are, for example, in oncology important to monitor tumor growth and thus therapeutic success. Segmentation is also for planning an intervention very important, for example, for a planned organ transplant.

The Segmentation of complex structures, in the present patent application also referred to as objects, represents a challenging task for which numerous algorithms are known. At the Use of algorithms that rely solely on the evaluation of intensity values or derived features of the image data Difficulty with image data with low contrast or missing Edge. In addition, pathological structures and strong noise, for example due to the reduced radiation dose in computed tomography (CT), false edges and uneven Cause feature statistics and thus affect algorithms, the on edge detection or homogeneity criteria for Regions are based.

SJ Lim et al., "Segmentation of the Liver Using the Deformable Contour Method to CT Images", PCM 2005, LNCS, 3767: 570-581, 2005 , describe a 2D segmentation of the liver which first applies a combination of thresholding with morphological operations on different image resolutions. The initial contour thus obtained is then refined by searching for a smooth path in the gradient magnitudes of the image data.

Liu et al., "Liver Segmentation for CT Images Using GVF Snake," Medical Physics, 32 (12): 3699-3706, 2005 , use an active contour based on a gradient vector field (GVF) to segment the liver. A so-called Canny edge detector is used to generate an edge image which is preprocessed to eliminate erroneously excluded concave areas prior to the calculation of the gradient vector field.

Heimann et al., "Shape Constrained Automatic Segmentation of the Liver Based Heuristic Intensity Model", 3D Segmentation in the Clinic - A Grand Challenge, MICCAI 2006 Workshop, 2006 describe a 3D segmentation of the liver by fitting an Active Shape Model to the image data. This is done according to the known art of Cootes et al., "Active Shape Models - Their Training and Application", Computer Vision and Image Understanding, 61 (1): 38-59, 1995 , The explicit Active Shape Model is created using principal component analysis (PCA) of training contours consisting of sets of corresponding landmark points. New contours consistent with the shape model are then expressed by a linear combination of the mean contour and the largest eigenmodes obtained by the PCA. To adapt the shape model to the image data, intensity profiles in the direction of the surface normal of the currently active contour with different shifts are determined for each landmark. A so-called nearest neighbor classifier is then used to obtain the point along the normal that is most likely to belong to the contour of the liver. The current contour of the Active Shape Model is then deformed in the direction of the most likely object contour points, taking into account the limitations of the Active Shape Model.

Another approach to 3D liver segmentation is in Kainmüller et al., "Shape Constrained Automatic Segmentation of the Liver Based Heuristic Intensity Model", 3D Segmentation in the Clinic - A Grand Challenge, MICCAI 2006 Workshop, 2006 , described. This approach is also based on an active shape model of the liver. Instead of a nearest neighbor classifier, however, a heuristic intensity model is used here for adapting the contour to the image data.

Most 2D segmentation techniques for segmentation of the liver today are based on the so-called Active Contours Approach ("Snakes"). Here, heuristic approaches are often included to prevent the formation of impermissible contours, for example, to remove concave areas. However, this limits the applicability of these techniques. Most known 3D liver segmentation techniques today use an Active Shape Model. These are so-called explicit Active Shape Models, where the contours are represented by landmarks. Such a representation can normally only deal with a rigid topology, so that, for example, a splitting or merging of object areas is not possible. Also known free-form deformations, which are often included in the models to loosen constraints imposed by the shape models, require a special approach to avoid self-intersections. The use of explicit Active Shape Models causes problems, especially with objects, that have large curvatures. In this case, valuable image information can easily be overlooked due to the often coarse distance of the landmarks points as well as strong curvature of the contour.

The The object of the present invention is a method and a device for segmenting objects in image data sets specify a robust segmentation of objects too allow strong bends or small thickness.

The Task is with the method and the device according to the Claims 1 and 5 solved. advantageous Embodiments of the method and the device are the subject the dependent claims or can be see the description below.

at the proposed method for segmentation of an object an image dataset is not an explicit but an implicit one Active Shape Model used. The implicit Active Shape Model own statistical model of shape is first in a known manner created from training data. Subsequently, the segmentation takes place by approximation or adaptation of an active contour Base the Active Shape Model on a probable object outline in the image data set. This can be both a 2D as well to act a 3D image data set, wherein the shape model and the Active contour then respectively suitable from 2D or 3D training data to be created. The approach of the active contour takes place in the present process in several approximation steps. In this case, an area of equal distance is repeatedly superimposed on that of the image data record active contour set. This results in an outer Limitation - outside of the active contour enclosed area - and an inner boundary - within of the area enclosed by the active contour. Within the defined area of equal distance around the active contour the individual grid points of the image data set signed Distance values assigned, which is a measure of the Euclidean Display the distance between the respective grid point and the active contour. Points within the range and outside the contour get a positive distance value, points within the range and inside the contour get a negative distance value.

In this case, the individual pixels of the image data set are understood by the grid points. In addition, for each grid point in the area, a probability is determined with which the point lies on the contour of the searched object. This can be z. B. done with the above-mentioned next neighbor classifier. In this case, an intensity profile is sampled from the image data set for each raster point, the direction of the profile being given by the gradient vector of the signed distance function. Illustratively, this gradient vector corresponds to points on the contour of the Active Shape Model of the normal to the contour. Based on the intensity profile, each grid point in the area is assigned a probability. From the outer boundary of the area, the inner boundary of the area and local minima of the distance values within the area, projection beams are considered in the direction of the contour of the Active Shape Model that end up perpendicular to the active contour. Among all raster points lying on a projection beam, the raster point which belongs on this projection beam with the highest probability of limiting the object to be segmented is determined. For each pair of projection beams that end up on the same grid point of the active contour, the two grid points determined in this way are compared in their probability and the grid point with the highest probability is selected. This is done for all considered projection beams. The projection beams are chosen so that they include all halftone dots of the image data set within the same distance around the active contour. The grid points selected in this way give a probable object contour to which the contour of the Active Shape Model approximates the constraints of the underlying shape model. This procedure is repeated in each case in the next approximation step until a sufficient approximation or adaptation of the active contour to the object to be segmented is achieved, ie until the difference between the active contour and the object contour determined in the corresponding approximation step falls below a predefinable threshold value. In this case, the active contour then reflects the boundaries of the object, taking into account the Active Shape Model, so that the object is segmented. The computation of the signed distances, the probabilities and the projection paths does not have to be done in every approximation step, but only if the contour of the Active Shape Model leaves the area in which the distances etc. were calculated last time. If this is not the case, it is simply enough to see the contour of the Ac tive Shape Model to the next most certain points with the highest probability.

at the proposed method and the associated device, in which this method is implemented becomes thus an implicit Active Shape Model (implicit ASM) used, which is a robust Segmentation allows. By waiving one on landmarks based model will be those associated with such models Circumvented difficulties. However, the adaptation of an implicit ASM to the image data more complicated, since no landmark points available which are in the direction of the most likely boundary of the object can be moved. Through the proposed approach based on the range of equal distance and the one performed therein Provisions will be the approximation or adaptation, however with high reliability. The proposed Procedure mainly leads to objects with strong curvatures to better results than a landmark-based model, because no halftone dots are lost during the test. Farther can also be very thin without further action Structures or objects without the risk of self-duplication be segmented.

Preferably, in the proposed method, an implicit ASM is used, as described by Rousson et al., "Implicit Active Shape Models for 3D Segmentation in MR Imaging", MICCAI 2004, 3216: 209-216, 2004 , wherein the implicit ASM is incorporated into the so-called level set methodology.

wobei ψ – durch Mittelung aller vorzeichenbehafteten Distanzfunktionen der Trainingsdatensätze bestimmt wird und ψ_i die Eigenmoden der PCA der Trainingsdatensätze sind.To adapt such an implicit ASM, the active contour is defined as a zero level set of a level set function φ that evolves on the one hand according to the image content and on the other hand is limited in acceptable forms by another level set function ψ generated from the statistical shape model , This level set function ψ is composed of the middle level set function ψ - and a weighted sum of the N largest eigenmodes ψ _i , ie

where ψ - is determined by averaging all signed distance functions of the training data sets and ψ _{i are} the eigenmodes of the PCA of the training data sets.

A ist dabei eine affine Transformation, welche die in ψ als Nullniveaumenge eingebettete Kontur des Formmodells an die in ϕ als Nullniveaumenge eingebettete aktive Kontur, welche am Bildinhalt ausgerichtet ist, anpasst. Die Komponenten des Vektors λ sind die Gewichte der Eigenmoden. Da nur die Anpassung der beiden Konturen, d. h. der Nullniveaumengen von ϕ und ψ, interessiert, wird die Dirac'sche Deltafunktion δ in die obige Energiefunktion eingeführt. Der Integrationsraum wird als Ω ⊂ R² (bzw. Ω ⊂ R³ für den dreidimensionalen Fall) bezeichnet.The adaptation of the active contour taking into account the ASM is determined by the following energy functional indicating the quadratic difference between both level set functions:

A is an affine transformation which adapts the contour of the shape model embedded in ψ as a zero-level set to the active contour embedded in φ as the zero-level set, which is aligned on the image content. The components of the vector λ are the weights of the eigenmodes. Since only the adaptation of the two contours, ie the zero level quantities of φ and ψ, is of interest, the Dirac delta function δ is introduced into the above energy function. The integration space is referred to as Ω ⊂ R ² (or Ω ⊂ R ³ for the three-dimensional case).

This equation is iteratively minimized with respect to φ as well as A and λ. For the individual weights λ _i as well as for the components of the transformation A, which are rotation angles about the coordinate axes as well as scaling and translations, the derivative of E for the respective weight λ _i or for the respective component of A is calculated and therefore included Gradient descent performed. A rule for optimizing E with respect to φ is given according to the variational calculation from the Euler Lagrange equation to the above equation (1). The result is a restriction of the partial differential equation which controls the deformation of φ and thus the deformation of the active contour. Further details of such an approach can be found in the already mentioned publication by Rousson et al. Thus, the adaptation of the active contour, ie the level set function φ, based on both the statistical shape model and the image information. While the adaptation based on the shape model is basically known, the peculiarity of the present method lies in the proposed procedure for adaptation to the image information or image data. The determination of the halftone dots on the respective projection beams, which count with the highest probability of object limitation, can be carried out in different ways, preferably on the basis of a so-called appearance model, such as, for example, the nearest neighbor classifier.

To get the active contour to the grid points within the boundary with the highest probability In principle, the gradient of the probability map can be calculated. Since the catchment area of the gradient of a probability map is limited, an additional measure is preferably taken. This measure consists in the calculation of the gradient vector field (GVF) of the probability map. As a result, the gradient vectors, which otherwise only exist close to halftone dots with a probability greater than zero, are diffused over the entire range of equal spacing. In this way, a much larger catchment area of the gradient vectors is created to guide the active contour. The calculation of such a gradient vector field is, for example, off Xu et al., "Snakes, Shapes and Gradient Vector Flow", IEEE Transactions on Image Processing, 7 (3): 359-369, 1998 known. In this embodiment, the GVF term is introduced into the partial differential equation for deformation of the active contour and competes with the term representing the constraints based on the shape model. To describe eg. Paragios et al., Gradient Vector Flow Fast Geodesic Active Contours, International Conference on Computer Vision 2001, 67-73, 2001 , the introduction of such a GVF term in the equation for the development of the active contour.

The proposed device comprises at least one storage unit for the training data and the image data set, a computing unit to carry out the execution the process required steps, a training module for creating the statistical shape model based on the training data sets and a segmentation module that describes the process steps for customization the active contour to the object to be segmented according to the proposed method. The segmented Object can then be displayed on an image display device, which may be connected to the device.

The proposed methods and associated apparatus are especially suitable for medical image data sets Imaging, for example, for segmentation of the liver from tomographic Image data sets. Such image data sets can come from different imaging devices, for example from a computer tomograph or a magnetic resonance tomograph, however, are not limited to the latter devices.

The proposed method and the associated device be in the following with reference to an embodiment in Connection with the drawings briefly explained again. Hereby show:

1 a schematic representation of the basic procedure in the proposed method;

2 a schematic representation of the definition of the area of equal distance around the active contour;

3 a schematic representation for determining the probabilities using projection beams and

4 a schematic representation of the proposed device.

The proposed method and the associated device are explained in more detail below using the example of the segmentation of the liver from a CT image data set. 1 shows the process in a highly schematic representation. The explanations here refer to a 2D image data set, so that the active contour represents a closed line and the area of equal spacing represents a band on the central axis of which this closed line runs. However, it is obvious that the proposed method can easily be extended to three dimensions to perform segmentation in a 3D image data set.

In the proposed method several image data sets of the liver are provided by different patients, which serve as training data sets for the creation of a statistical shape model. A set of segmentation masks obtained by manual segmentation of the liver in the training data sets represents the basis of the statistical shape model. Mask points of non-zero value belong to the object, ie the liver. All other mask points with a value equal to 0 provide the background. For the analysis of possible forms of the liver, it is first necessary to eliminate variations between the individual segmentation masks caused by similarity transformations, ie, translation, rotation, and isotropic scaling. Therefore, one of the masks is first selected as the reference mask. For all other masks, appropriate transformations are then determined that maximize the degree of overlap between each pair of masks. This can be done, for example, with the technique of Tsai et al., "A Shape-Based Approach to the Segmentation of Medical Imagery Using Level Sets ", IEEE Transactions on Medical Imaging, 22 (2): 137-154, 2003. Translation, rotation and scaling are optimized for each gradient descent technique. Since the method requires a greater number of iterations and is susceptible to local minima, translation, rotation, and scaling are normalized before the gradient descent technique is used to refine the initially coarse overlay.

in the Following this mutual alignment and appropriate scaling The individual segmentation masks become the ones through these masks represented forms in an implicit representation transformed. This is done by generating a sign-afflicted Distance function for each mask, at each grid point its positive or negative Euclidean distance to the limit assigned to the illustrated form. Grid points within the Form receive a negative sign, grid points outside of the form that counts as a background, a positive one Sign.

ausgedrückt, wobei λ dem Vektor der Modengewichte λ_i der Eigenmoden, ψ – dem Mittelwert über alle Abstandsfunktionen und ψ_i den N signifikanten Eigenmoden entsprechen, die aus der PCA erhalten werden.Subsequently, a principal component analysis (PCA) is performed with the distance maps (distance map) obtained thereby to analyze the remaining variations due to different forms of the liver. New forms are implicitly called the zero level set of the level set function

where λ corresponds to the vector of the mode weights λ _{i of} the eigenmodes, ψ - the mean over all distance functions, and ψ _{i to} the N significant eigenmodes obtained from the PCA.

For the use of this image training model created from training data, a further level set function φ is introduced, which develops as an active contour according to the image content and whose development is limited by the level set function ψ of the shape model. The restriction of the adaptation of the active contour by the shape model can be described by the energy functional already explained above, which indicates the quadratic difference between the two level set functions:

This equation is minimized in an iterative manner until a static solution results, ie the values of the mode weights λ _i and the values of the transformation parameters in A (rotation angle, scaling factor, translation values) and in particular the active contour level set function φ no longer change. The active contour then corresponds to the segmented object, which, for example, can be displayed on a monitor.

The Special feature of the proposed method is the combination an implicit ASM with a special approach to the Adaptation of the active contour to the image information. This adaptation will be described in more detail below with reference to the present example explained.

at An explicit ASM is usually called Appearance Models used to the deformation or development of the active contour respectively. This includes the determination of intensity profiles at each landmark in a direction normal to the surface of the object during a training phase. Upon acceptance a normal distribution will give the Appearance Model that calculates the mean and covariance matrix of the profiles becomes. This principle was also based on random distributions extended by using both edge and non-edge Profiles determined and a neighbor neighbor classifier were used. During segmentation then becomes each landmark point in its normal direction in the direction of most likely boundary point of the object moves. Compared Using simple edge detectors is done with this known approach based on an explicit ASM a greater robustness reached the segmentation.

In contrast to this known technique, the present method and apparatus employ an implicit ASM into which an image term based on an appearance model is integrated. The procedure for adapting the active contour to the image data is described in the schematic diagrams of FIG 2 and 3 explained in more detail.

2 shows the active contour 1 , which is represented by the zero level amount of Φ. The image data itself, to which this contour is superimposed, can not be seen in this and the next figure. The active contour 1 is part of the ASM and represents in its initial form, for example, the average over the For adaptation to the image data, in the proposed method initially a narrow band of equal distance around the active contour 1 placed. The width of the tape may be, for example, 5-30 mm. This band is in the figure by the outer boundary 3 and the inner boundary 2 shown in dashed lines. The distance of the outer boundary 3 to the active contour 1 and the inner boundary 2 to the active contour 1 corresponds to the distance r, denoted by the reference numeral 4 is marked in the figure. Each halftone dot of the image data set that lies within this band becomes a positive or negative distance value, depending on the position and the distance to the active contour 1 , assigned. Thus, for example, receives point 5 a positive distance value 7 and point 6 a negative distance value 8th , The distance map obtained in this way can be created, for example, via the so-called fast marching algorithm. For all grid points within the narrow band, ie, for example, for the points 5 . 6 and 9 , intensity profiles are determined at their corresponding position within the image, whereby the intensity profiles are determined in the normal direction, which is given by ∇Φ. This normal direction is used in the 2 exemplary at the point 9 through the vector 10 indicated. A suitable appearance model calculates the probability for each grid point that it belongs to the boundary or surface of the object to be segmented. As an Appearance Model, for example, a so-called k Nearest Neighbor (k-NN) classifier can be used. Instead of a k-NN classifier, of course, other techniques, such. Mean vector & covariance matrix, which also provide a continuous probability.

Subsequently, the raster point with the highest probability on the respective projection beam is determined in each case along projection beams. The projection beams start on the edges of the narrow band (boundary lines 2 . 3 ) and at local extrema of the underlying distance map passing through the dotted line of local minima 11 in the 3 are indicated. The projection beams end vertically on the active contour 1 , For every projection beam that is inside (projection beam 12 ) or outside (projection beam 13 ) through the active contour 1 enclosed areas, a gradient slope or descent is performed on the signed set distance map representing the level set function Φ until the active contour 1 is reached. Only the halftone dot with the highest probability is determined along each projection path. This applies, for example, in the case of the projection path 12 the point 14 and at the projection path 13 the point 15 , All other grid points are no longer considered.

Finally, for all pairs of internal and external projection beams that are on the same grid point 16 on the active contour 1 only the one of the two previously determined grid points is selected, which has the higher probability of belonging to the object boundary. As a result of this algorithm, a map is obtained which contains only the highest probability halftone dots. Assuming that the Appearance Model's real boundary points have higher probabilities than non-boundary raster points, the proposed approach eliminates false boundary points. This will prevent the fitting algorithm from getting stuck in the wrong position in a local minimum.

Since the trapping range of the probability map described above is limited, the guidance of the active contour toward the edge points alone based on the gradient may not be sufficient. Therefore, in the present example, the gradient vector field (GVF) of the probability map is calculated to distribute the gradient vectors over the entire narrow band. This significantly increases the capture area. The GVF term is included in the development of the active contour, as described, for example, in the already mentioned publication by Paragios et al. is known. The GVF term competes with the limiting term previously described on the basis of the shape model derived from the above-mentioned energy functional (equation (1)). The development equation for the level set function Φ of the active contour can then be represented as follows:

Where Φ _{t represents} the time derivative of the level set function, g a stop function, "div" the divergence operator, and ν the GVF field. The first term on the right side of this equation (2), which is weighted by α, contributes to smoothing the contour taking into account the image content by means of the stop function g. The second term, weighted by β, introduces the GVF to drive the contour to the edge points. Finally, the third term, weighted by γ, represents the constraints imposed by the ASM. It yields according to the variational calculation on Φ from the Euler-Lagrange equation of the above energy function (Equation (1)). Further details of the first and second terms may be, for example, the above Publication of Paragios et al. and to the third term of the above publication by Rousson et al. be removed.

4 Finally, shows an example of the apparatus for performing the proposed method in a highly schematic representation. The device can, for example, by a computing station with a computing unit 17 and a data store 18 be formed, which receives the corresponding training records, the image data set as well as all accumulated during the implementation of the method data. A module 19 creates from the training data sets the statistical shape model based on the known process steps. A segmentation module 20 Finally, performs the special process steps of the proposed method, in particular the adaptation of the active contour to the image data, taking into account the ASM. The segmented object may eventually be attached to a monitor connected to the device 21 presented to a user. The segmentation can be done fully automatically after creation of the ASM without any user intervention.

The proposed method works compared to the algorithms, based on landmarks, especially in object areas with strong Curvature more reliable, where edge points at the known method due to the coarse distances of the Landmarks can be overlooked. By the Shifting the landmarks in normal direction can be done here in areas between the divergent shift paths, possibly important image information is not taken into account. One Another problem occurs, for example, even if a boundary point with the highest probability behind another part the surface lies.

These Problems are avoided with the present algorithm. at this algorithm will be probabilities for the entire narrow band calculated so that no single edge point is overlooked can be. However, wrong edge points must be removed to prevent the algorithm from being set in local minima. This is achieved in the proposed method in that all this particular probabilities back to the instantaneous active contour can be projected and only the point with the highest probability for each pair of projection beams for the adaptation of the active contour is taken into account.

QUOTES INCLUDE IN THE DESCRIPTION

This list The documents listed by the applicant have been automated generated and is solely for better information recorded by the reader. The list is not part of the German Patent or utility model application. The DPMA takes over no liability for any errors or omissions.

Cited non-patent literature

• SJ Lim et al., "Segmentation of the Liver Using the Deformable Contour Method to CT Images", PCM 2005, LNCS, 3767: 570-581, 2005 [0004]
• Liu et al., "Liver Segmentation for CT Images Using GVF Snake", Medical Physics, 32 (12): 3699-3706, 2005 [0005]
• - Heimann et al., "Shape Constrained Automatic Segmentation of the Liver Based Heuristic Intensity Model", 3D Segmentation in the Clinic - A Grand Challenge, MICCAI 2006 Workshop, 2006 [0006]
• Cootes et al., "Active Shape Models - Their Training and Application", Computer Vision and Image Understanding, 61 (1): 38-59, 1995 [0006]
• - Kainmüller et al., "Shape Constrained Automatic Segmentation of the Liver-based on a Heuristic Intensity Model", 3D Segmentation in the Clinic - A Grand Challenge, MICCAI 2006 Workshop, 2006 [0007]
• Rousson et al., "Implicit Active Shape Models for 3D Segmentation in MR Imaging", MICCAI 2004, 3216: 209-216, 2004 [0014]
• Xu et al., "Snakes, Shapes and Gradient Vector Flow," IEEE Transactions to Image Processing, 7 (3): 359-369, 1998. [0018]
• Paragios et al., "Gradient Vector Flow Fast Geodesic Active Contours", International Conference on Computer Vision 2001, 67-73, 2001. [0018]

Claims (5)

Method for segmenting an object from an image data set, in which - an implicit shape model for the object to be segmented is created from training data records and - the object is created by stepwise approximation of an active contour ( 1 ) is segmented on the basis of the shape model to a probable object contour in the image data record, wherein repeated areas for the approach - areas of equal distance around the active data set superimposed on the image data set ( 1 ), - each grid point ( 14 . 15 ) of the image dataset within the range is assigned a signed distance value which is a measure of a distance of the raster point ( 14 . 15 ) to the active contour ( 1 ), - projection beams ( 12 . 13 ), each of which is defined by an inner boundary ( 2 ) of the area, from an outer boundary ( 3 ) of the area as well as of local extremes ( 11 ) of the distance values between the boundaries ( 2 . 3 ) and the active contour ( 1 ) and perpendicular to the active contour ( 1 ), the projection beams ( 12 . 13 ) are chosen so that all grid points ( 14 . 15 ) within the range of the projection beams ( 12 . 13 ), - for each of the projection beams ( 12 . 13 ) each of the image data a local intensity profile at each on the projection beam ( 12 . 13 ) grid point ( 14 . 15 ) of the image data set is determined and a raster point is determined which, due to the local intensity curve, is most likely a boundary of the object, - for each pair of projection beams ( 12 . 13 ) on the same grid point ( 16 ) of the active contour ( 1 ) are compared, the previously determined halftone dots are compared with respect to their probability of representing a boundary of the object, and the halftone dot with the highest probability is selected, and - the active contour ( 1 ) is approximated to the course of the selected halftone dots, taking into account specifications of the shape model. Method according to Claim 1, in which the approximation of the active contour ( 1 ) to the course of the selected halftone dots while minimizing the equation

where φ is the active contour ( 1 ) and ψ represent permissible shapes of the shape model, λ correspond to the vector of the mode weights of the eigenvectors of the shape model and δ of the Dirac delta function, and A represents an affine transformation that adapts ψ to φ. Method according to one of Claims 1 to 2, in which the determination of the halftone dot ( 14 . 15 ) on each projection beam ( 12 . 13 ), which is most likely a boundary of the object due to the local intensity curve, based on an Appearance Model. Method according to one of Claims 1 to 3, in which, for all halftone dots ( 14 . 15 ) Within the range, on the basis of the local intensity curves determined for the halftone dots, probabilities are determined with which they represent a boundary of the object, and a gradient vector field is calculated from the probabilities and a spatial distribution of these probabilities given by the position of the halftone dots, the approximation the active contour ( 1 ) by the following development equation:

in the Φ _{t is} a time derivative of the active contour ( 1 g) is a stop function, "div" is the divergence operator, ν is the gradient vector field and α, β and γ are weighting factors. Device for carrying out the method according to one of Claims 1 to 4, which has at least one computing unit ( 17 ), a data store ( 18 ), a shape model module ( 19 ) and a segmentation module ( 20 ), wherein the mold model module ( 19 ) is adapted to enable the creation of an implicit statistical shape model of an object to be segmented from training data sets, and wherein the segmentation module ( 20 ) is designed so that it according to the method steps of the method one or more of claims 1 to 5 performs.