Abstract: An image processing method, comprising acquiring an image of a 3-D tubular object of interest to segment; computing a 3-D path that corresponds to the centerline of the tubular object and defining segments on said 3-D path; creating an initial straight deformable cylindrical mesh model, of any kind of mesh, with a length defined along its longitudinal axis equal to the length of the 3-D path; dividing this initial mesh model into segments of length related to the different segments of the 3-D path; computing, for each segment of the mesh, a rigid-body transformation that transforms the initial direction of the mesh into the direction of the related segment of the 3-D path, and applying this transformation to the vertices of the mesh corresponding to that segment.

Abstract: A system for visualizing a myocardium represented by a cardiac image comprises a resampling means and a visualizing means. The resampling means resamples the intensity levels at sampling points on a plurality of curved surfaces, each curved surface enclosing at least part of a heart cavity and zero or more of the plurality of curved surfaces and being enclosed by the remaining curved surfaces of the plurality of curved surfaces, the plurality of curved surfaces together covering a hollow region in the cardiac image, the hollow region comprising the outer cavity walls of a group of at least one heart cavity. The visualizing means is arranged for visualizing at least part of at least one of the plurality of curved surfaces, using resampled intensity levels obtained from the resampling means. The group of at least one heart cavity may be the left atrium alone. It may also be the complete heart.

Abstract: An image processing system having means of automatic adaptation of 3-D surface Model to image features, for Model-based image segmentation, comprising: dynamic adaptation means for adapting the Model resolution to image features including locally setting higher resolution when reliable image features are found and setting lower resolution in the opposite case. This system comprises estimation means for estimating a feature confidence parameter for each image feature. The model resolution is locally adapted according to said parameter. The feature confidence parameter depends on the feature distance and on the estimation of quality of this feature including estimation of noise. The large distances and the noisy, although close features are penalized. The resolution of the Model is decreased in absence of confidence and is gradually increased with the rise of feature confidence.

Abstract: Method of image processing, the method comprises providing a sequence (2) of images (F) which have contrast modulation (100) along said sequence (2); providing a reference frequency (fm, 10) related to said contrast modulations (100) along said sequence (2); and filtering said sequence of images depending on said reference frequency (fm, 10). According to an embodiment, a windowed harmonic filtering is applied to the sequence of input images to extract fundamental in-phase (122) and quadrature (124) components at a heart beat frequency (fm). The resultant time-signal phase is displayed (34) as image sequence.

Abstract: A system for visualizing a myocardium represented by a cardiac image comprises a resampling means and a visualizing means. The resampling means re-samples the intensity levels at sampling points on a plurality of curved surfaces, each curved surface enclosing at least part of a heart cavity and zero or more of the plurality of curved surfaces and being enclosed by the remaining curved surfaces of the plurality of curved surfaces, the plurality of curved surfaces together covering a hollow region in the cardiac image, the hollow region comprising the outer cavity walls of a group of at least one heart cavity. The visualizing means is arranged for visualizing at least part of at least one of the plurality of curved surfaces, using resampled intensity levels obtained from the resampling means. The group of at least one heart cavity may be the left atrium alone. It may also be the complete heart.

Abstract: A method and an apparatus for segmenting contours of objects in an image is disclosed. It particularly applies to the segmentation of body organs or parts depicted in medical images. An input image containing at least one object comprises pixel data sets of at least two dimensions. An edge-detected image is obtained from the input image. Markers are selected in the edge-detected image, and assigned respective fixed electrical potential values. An electrical potential map is generated as a solution to an electrostatic problem in a resistive medium having a resistivity dependent on the edge-detected image, with the markers defining electrodes at the respective fixed potential values. Object contours are estimated, for example by thresholding, from the generated potential map.

Abstract: Image processing system for generating a multidimensional adaptive oriented filter to be applied to the point intensities of a d-dimensional image, comprising analyzing means with means (5, fi) to estimate at each image point a probability measure (Fi) of the presence of a type of feature of interest and a weighting control model (10) issuing a weighting control vector (11, VC) constructed from said probability measure, for the user to control synthesized adaptive kernels at each image point; and synthesizing means for generating the filter kernels at each image point adapted to the type of the features of interest, whose filtering strength is controlled by the weighting control vector.

Abstract: Method of image processing, the method comprises providing a sequence (2) of images (F) which have contrast modulation (100) along said sequence (2); providing a reference frequency (fm, 10) related to said contrast modulations (100) along said sequence (2); and filtering said sequence of images depending on said reference frequency (fm, 10). According to an embodiment, a windowed harmonic filtering is applied to the sequence of input images to extract fundamental in-phase (122) and quadrature (124) components at a heart beat frequency (fm). The resultant time-signal phase is displayed (34) as image sequence.

Abstract: An image processing system, for correlating shapes in multi-dimensional images including image data processor for estimating a similarity measure including estimating two image signals representing shapes defined in respective windows in two multi-dimensional images using a Hermite Transform applied to both the image signals for performing an evaluation of two first sets of scalar valued Hermite coefficients from which a combination yields a transformed set of scalar valued Hermite coefficients {KI}. The inverse Hermite Transform is applied to the transformed set of scalar valued Hermite coefficients to achieve the computation of a windowed correlation function. The maximum of the windowed correlation function is estimated as the wanted similarity measure to correlate the shapes. The correlated shapes and/or processed images are displayed.

Abstract: First and second images to be registered are filtered using a low-pass filter kernel having a sharp central peak and a slow decay away from the central peak. The apparatus determines a mapping function that transforms the filtered first image into the filtered second image.

Abstract: The invention relates to an image processing method for displaying a processed image of a three dimensional (3-D) object using a two-dimensional display means and for interacting with the surface of the displayed 3-D object comprising the construction and display of at least two coupled views of the surface of the 3-D object, including a global 3-D view and a connected local 2-D view of the surface of said object on which local interactions are made. This method further comprises interactive navigation on the object surface in one of the two views and processing data in said view with automatic updating of corresponding data in the other coupled view. Application: Medical Imaging.

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 method and an apparatus for segmenting contours of objects in an image is disclosed. It particularly applies to the segmentation of body organs or parts depicted in medical images. An input image containing at least one object comprises pixel data sets of at least two dimensions. An edge-detected image is obtained from the input image. Markers are selected in the edge-detected image, and assigned respective fixed electrical potential values. An electrical potential map is generated as a solution to an electrostatic problem in a resistive medium having a resistivity dependent on the edge-detected image, with the markers defining electrodes at the respective fixed potential values. Object contours are estimated, for example by thresholding, from the generated potential map.

Abstract: A medical viewing system having means, for analysing and visualising medical image data corresponding to folded surfaces, comprises means of segmentation of the image data to identify the object surface, means for approximating the object surface by a reference surface, and means for detecting folded portions of the object surface including means for determining points of the reference surface at which a normal to a zone forming a patch on the reference surface intersects with the object surface. If there are more than one point of intersection, then that patch corresponds to a folded portion of the object surface. Fold-portion patches are assigned a code such that, on display or printing of an image (RP) corresponding to the reference surface, the fold-portions will be flagged (for example by coloured or patterned regions (HP).

Abstract: A method for segmenting contours of objects in an image, comprising a first step of receiving an input image containing at least one object, said image comprising pixel data sets of at least two dimensions, a second step of selecting a reference point of said input image within the object, a third step of generating a coordinate map of a distance parameter between the pixels of said input image and said reference point, a fourth step of processing said input image to provide an edge-detected image from said input image, a fifth step of calculating at least one statistical moment of said distance parameter in relation to a pixel p of said input image, with weight factors depending on the edge-detected image and on a filter kernel defined on a window function centered on said pixel p, and a sixth step of analyzing said at least one statistical moment to evaluate whether said pixel p is within said object.

Abstract: Image processing system for generating a multidimensional adaptive oriented filter to be applied to the point intensities of a d-dimensional image, comprising analyzing means with means (5, fi) to estimate at each image point a probability measure (Fi) of the presence of a type of feature of interest and a weighting control model (10) issuing a weighting control vector (11, VC) constructed from said probability measure, for the user to control synthesized adaptive kernels at each image point; and synthesizing means for generating the filter kernels at each image point adapted to the type of the features of interest, whose filtering strength is controlled by the weighting control vector.

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: The invention relates to a medical image processing system comprising means for identifying a boundary of the object, and reference points of said object boundary within an observation window; and for decomposing said object boundary into boundary unit elements, centred at the reference points, means for coding each reference point including spatial information and intensity information relating to said reference point and the corresponding unit element; computing transform coefficients from said coding data. A finite number of said coefficients is used for representing said object boundary by a polynomial transform function. This system has means for comparing, matching, correlating, smoothing corresponding boundary portions of the object in different images, only by performing operations on the transform coefficients. These operations yield rotation, translation, scale change transform coefficients.

Abstract: A method for extracting geometrical data from a 2-D digital image of the spine, comprising steps for determining spine outlines, endplates and corners wherein: digitizing the spine center line and end points; constructing a 2-D image band, referred to as Rubber-Band, whose center line is a spline representing the spine center line, and unfolding said Rubber-Band for constructing a 2-D Rectangular-Band; processing the 2-D Rectangular-Band image data in order to estimate best paths going through selected points for determining the spine outlines, then the endplates based on the found outline data and the corners at the intersection of the outlines and endplates.

Abstract: An image processing method, comprising acquiring an image of a 3-D tubular object of interest to segment; computing a 3-D path that corresponds to the centerline of the tubular object and defining segments on said 3-D path; creating an initial straight deformable cylindrical mesh model, of any kind of mesh, with a length defined along its longitudinal axis equal to the length of the 3-D path; dividing this initial mesh model into segments of length related to the different segments of the 3-D path; computing, for each segment of the mesh, a rigid-body transformation that transforms the initial direction of the mesh into the direction of the related segment of the 3-D path, and applying this transformation to the vertices of the mesh corresponding to that segment.