Abstract: An imaging system (10) includes imaging modalities such as a PET imaging system (12) and a CT scanner (14). The CT scanner (14) is used to produce a first image (62) which is used for primary contouring. The PET system (12) is used to provide a second image (56), which provides complementary information about the same or overlapping anatomical region. After first and second images (62, 56) are registered with one another the first and second images (62, 56) are concurrently segmented to outline a keyhole (76). The keyhole portion of the second image (56) is inserted into the keyhole (76) of the first image (62). The user can observe the composite image and deform a boundary (78) of the keyhole (76) by a mouse (52) to better focus on the region of interest within previously defined keyhole.

Abstract: The invention relates to a method of segmenting a three-dimensional structure from a three-dimensional, and in particular medical, data set while making allowance for user corrections. The method is performed with the help of a deformable three-dimensional model whose surface is formed by a network of nodes and mashes that connect these nodes. Once the model has been positioned at the point in the three-dimensional data set at which the structure to be segmented is situated and positions of nodes have, if necessary, been changed by known methods of segmentation, any desired nodes can be displaced manually. The nodes of the model are re-calculated by making weighted allowance for the nodes that have been displaced manually.

Abstract: The present invention aims at improving the point-based elastic registration paradigm. According to the present invention, a force field, for example, with Gaussian-shaped forces, is applied at several points to the image to be deformed. In this case, no landmark correspondences are required and the optimal positions of the force application point are found automatically, which minimizes the difference between the source and target image. Advantageously, this may allow to control a local influence of individual control points.

Abstract: A current diagnostic image (A) and an archived diagnostic image (B) of a common region of a patient are loaded into a first memory (14) and a second memory (18). The first and second diagnostic images (A, B) are automatically aligned and registered with one another. The three 2D orthogonal views through a selected crossing point in the image (A) are concurrently displayed along with the same three orthogonal views through the corresponding crossing point in the image (B) on a display (40). A user manually corrects alignment in the first and second sets of slices that are currently displayed on the display (40) using local tools (72).

Abstract: The invention relates to a method for segmentation of a three-dimensional structure in a three-dimensional data set, especially a medical data set. The method uses a three-dimensional deformable model, wherein the surface of the model consists of a net of polygonal meshes. The meshes are split into groups, and a feature term is assigned to each group. After the model has been placed over the structure of interest, the deformable model is recalculated in consideration of the feature terms of each group.

Abstract: A reconstruction processor (34) reconstructs acquired projection data (S) into an uncorrected reconstructed image (T). A classifying algorithm (66) classifies pixels of the uncorrected reconstructed image (T) at least into metal, bone, tissue, and air pixel classes. A clustering algorithm (60) iteratively assigns pixels to best fit classes. A pixel replacement algorithm (70) replaces metal class pixels of the uncorrected reconstructed image (T) with pixel values of the bone density class to generate a metal free image. A morphological algorithm (80) applies prior knowledge of the subject's anatomy to the metal free image to correct the shapes of the class regions to generate a model tomogram image. A forward projector (88) forward projects the model tomogram image to generate model projection data (Smodel). A corrupted rays identifying algorithm (100) identifies the rays in the original projection data (S) which lie through the regions containing metal objects.

Abstract: The invention relates to a method, a system and a computer program for dynamic imaging of a moving object. First, motion between the elements of common portions of images Im(t), Im+1(t) is computed. At step 1 motion compensation the said elements is performed, using a suitable transformation. Assuming that Im+1 is the image that has to be transformed, its motion from m to m+1 is compensated applying the inverse motion estimation Formula (I) resulting in the reformatted image Formula (II) at position m. At step 2 grey value interpolation is performed, based on image Im and the transformed image I?m+1 resulting in j interpolated images Formula (III) with o<i?j. At step 3 spatial interpolation is carried out yielding a series of images for dynamic imaging of the moving object. The spatial interpolation is calculated placing the images Formula (III) at position i resulting in j images Formula (IV) with 0<i?j and the transformation's weighting factor w=i/j.

Abstract: A method and apparatus accounting for tumor motion during radiation therapy is provided. The method allows for radiation therapy treatments based on updated radiation therapy plans. For each fractionate radiation treatment that results in an updated radiation treatment, radiation treatment images are acquired, automatically segmented, and then subject to deformable registration to develop updated contours and an updated radiation therapy plan.

Abstract: The invention aims at improving the point-based elastic registration paradigm. Point-based elastic registration is typically carried out by finding corresponding point landmarks (2, 4) in both images and using the point correspondences as constraints to interpolate the global displacement field. A limitation of this approach is that it only ensures the correspondences between structures where point landmarks (2, 4) can be identified. Alternative concepts are limited by high computational costs for optimization. The concept of the invention provides a method and a system (1) wherein additional deformation field constraints are imposed by: partitioning (PART (IS, IT)) one or more restricted structures corresponding in the first (3) and the second (5) image and imposing additional constraints (fAddpart) derived from a-priori-knowledge to the one or more restricted structures.

Abstract: Ground glass opacities in the lung are non-solid nebular-like shadows in the parenchyma tissue of the lung, which may be precursors of a lung cancer. According to the present invention, ground glass opacities may automatically be determined on the basis of a texture analysis of the parenchyma. Advantageously, according to the present invention, a robust and reliable determination of ground glass opacities may be provided, even if vessels, lung walls, airspace or bronchi walls are present within the local neighborhood of the ground glass opacity.

Abstract: In a diagnostic imaging system (10), a user interface (82) facilitates viewing of 4D kinematic data sets. A set of reference points is selected in a first 3D image to designate an anatomical component. An algorithm (104) calculates a propagation of the selected reference points from the first 3D image into other 3D images. Transforms which describe the propagation of the reference points between 3D images are defined. An aligning algorithm (112) applies inverse of the transforms to the 3D images to define a series of frames for the video processor (120) to display, in which frames the designated anatomical component defined by the reference points in each of the 3D images remains fixed while the other portions of the anatomical region of interest move relative to the fixed designated anatomical component.

Abstract: An image segmentation method segments a plurality of image features in an image. The plurality of image features are segmented non-simultaneously in succession. The segmenting of each image feature includes adapting an initial mesh to boundaries of the image feature. The segmenting of each image feature further includes preventing the adapted mesh from overlapping any previously adapted mesh.

Abstract: A scanner (18) acquires images of a subject. A 3D model (52) of an organ is selected from an organ model database (50) and dropped over an image of an actual organ. A best fitting means (62) globally scales, translates and/or rotates the model (52) to best fit the actual organ represented by the image. A user uses a mouse (38) to use a set of manual tools (68) to segment and manipulate the model (52)1:o match the image data. The set of tools (68) includes: a Gaussian tool (72) for deforming a surface portion of the model along a Gaussian curve, a spherical push tool (80) for deforming the surface portion along a spherical surface segment, and a pencil tool (90) for manually drawing a line to which the surface portion is redefined.

Abstract: Ground glass opacities in the lung are non-solid nebular-like shadows in the parenchyma tissue of the lung, which may be precursors of a lung cancer. According to the present invention, ground glass opacities may automatically be determined on the basis of a texture analysis of the parenchyma. Advantageously, according to the present invention, a robust and reliable determination of ground glass opacities may be provided, even if vessels, lung walls, airspace or bronchi walls are present within the local neighborhood of the ground glass opacity.

Abstract: A method and apparatus for planning a radiation therapy are disclosed. A radiation dose distribution is adapted on the basis of shape and position variations of the organs of interest determined from a comparison of a first image and a second image which were taken at different points of time during the radiation treatment process.

Abstract: The invention relates to a method of segmenting a three-dimensional structure, contained in an object, from one or more two-dimensional images which represent a slice of the object. The method utilizes a deformable model whose surface is formed by a network of meshes which connect network points on the surface of the model to one another. First there are determined the meshes which intersect at least one image and a point on the surface of the structure to be segmented is searched along a search line which traverses the mesh and extends in the image. Subsequently, the position of the network points of the model is calculated anew. These steps are repeated a number of times and the model ultimately obtained, that is, after several deformations, is considered to be the segmentation of the three-dimensional structure from the two-dimensional images.

Abstract: The invention relates to the field of efficient segmentation of collections of anatomical structures in medical imaging. For example, in radiotherapy planning, the segmentation of a collection of several anatomical structures, which represent the target volume in risk organs is required. When using model based segmentation, organ models represented by flexible surfaces are adapted to the boundaries of the object of interest. According to an aspect of the present invention, object-specific a priori information is incorporated in the segmentation process, which allows to provide for an improved segmentation. Furthermore, the segmentation process according to the present invention, may have an improved robustness, also the time required for the segmentation maybe reduced.

Abstract: A delineation of a structure of interest can be performed by fitting 3D deformable models, for example, represented by polygonal measures, to the boundaries of the structure of interest. The deformable model fitting process is guided by minimization of the sum of an external energy, based on image feature information, which attracts the mesh to the organ boundaries and an internal energy, which pre-serves the consistent shape of the mesh. A frequent problem is that the images do not contain sufficient reliable image feature information, such as image gradients, to attract the mesh. According to the present invention, manually drawn attractors in the form of complete or partial contours corresponding to boundaries of the structure of interest are placed into the images which do not contain sufficient feature information. These attractors may easily be discriminated by a subsequent segmentation process.

Abstract: The invention relates to a method of segmenting a three-dimensional structure from a three-dimensional, and in particular medical, data set while making allowance for user corrections. The method is performed with the help of a deformable three-dimensional model whose surface is formed by a network of nodes and mashes that connect these nodes. Once the model has been positioned at the point in the three-dimensional data set at which the structure to be segmented is situated and positions of nodes have, if necessary, been changed by known methods of segmentation, any desired nodes can be displaced manually. The nodes of the model are recalculated by making weighted allowance for the nodes that have been displaced manually.

Abstract: The basic principle of deformable models consists of the adaptation of flexible surfaces, such as triangular meshes to structures in the image. The optimal adaptation of an initial mesh is solved by energy minimization, where maintaining the shape of a geometric model is traded off against detected feature points of the surface of the structure in the image. According to the present invention, a prior shape model M(t) is combined with adaptation results S(t?1) of a previous image. Advantageously, this provides for a robust segmentation of moving or deforming objects.

Abstract: A linear driving apparatus using two units of linear motors each having rotors being coupled to each other which are suitable to provide high accuracy for the positioning control and the speed control. The first and second linear motors, which, are coupled in shape by the coupling member are not controlled independently and the impellent force, to the first and second linear motors are equal. Thereby, construction of the apparatus is considerably simplified, and the positional contol and the speed control is highly accurate.