Abstract: For each of a number of landmarks in an image an initial position of the landmark is defined. Next a neighborhood around the initial position, comprising a number of candidate locations of the landmark is sampled and a cost is associated with each of the candidate locations. A cost function expressing a weighted sum of overall gray level cost and overall shape cost for all candidate locations is optimized. A segmented anatomic entity is defined as a path through a selected combination of candidate locations for which combination the cost function is optimized.

Abstract: For each of a number of landmarks in an image an initial position of the landmark is defined. Next a neighborhood around the initial position, comprising a number of candidate locations of the landmark is sampled and a cost is associated with each of the candidate locations. A cost function expressing a weighted sum of overall gray level cost and overall shape cost for all candidate locations is optimized. A segmented anatomic entity is defined as a path through a selected combination of candidate locations for which combination the cost function is optimized.

Abstract: A basic component of Computer-Aided Detection systems for digital mammography comprises generating candidate mass locations suitable for further analysis. A component is described that relies on filtering either the background image or the complementary foreground mammographic detail by a purely signal processing method on the one hand or a processing method based on a physical model on the other hand. The different steps of the signal processing approach consist of band-pass filtering the image by one or more band pass filters, multidimensional clustering, iso-contouring of the distance to centroid of the one or more filtered values, and finally candidate generation and segmentation by contour processing. The physics-based approach also filters the image to retrieve a fat-corrected image to model the background of the breast, and the resulting image is subjected to a blob detection filter to model the intensity bumps on the foreground component of the breast that are associated with mass candidates.

Abstract: The orientation of an image such as a radiographic image is deduced from the digital representation of the image. In one embodiment the curvature is calculated and a decision on the orientation of the image is obtained on the basis of the value of the calculated curvature.

Abstract: The present invention relates to a method for processing and presenting at least a first image (102) and a second image (103), these images being digital medical images. A first step in the method is performing image registration between the first image (102) and the second image (103) to generate a pixel-level mapping between both images. The registration takes into account a region-level correspondence between the first image (102) and the second image (103) A second step is presenting the first image (102) and the second image (103) simultaneously on a display (103). A third step is presenting a first magnification (104) of a region of interest (106) in the first image (102) and a second magnification (105) of a corresponding region (108) in the second image (103). The corresponding region (108) in the second image (103) being determined based on the pixel-level mapping.

Abstract: Method to bring out a temporal difference between corresponding structures in a reference image R and a floating image F by convolving the reference image R and the floating image F with a window function Hw to generate Rw and Fw, applying a non-rigid transformation resulting in a transformation field g(rR) mapping every location rR to a corresponding location rF in the floating image F and generating a subtraction image by performing subtraction Rw(r)?Fw(g(r)) wherein r represents a voxel (x, y, z) in reference image R.

Abstract: A workflow method for temporal nodule review by registering a reference image R with a floating image F, convolving the reference image R and the floating image with the same window function Hw to generate Rw and Fw, generating a subtraction image by performing subtraction Rw?Fw (g(r)) wherein r represents a voxel (x, y, z) in reference image R, applying a pattern detector to said subtraction image to detect corresponding nodules in reference image R and floating image F and displaying corresponding nodules.

Abstract: An image point in a displayed reference image R is selected and a non-rigid transformation resulting in a transformation field g(rR) mapping every location rR to a corresponding location rF in a floating image F is applied, next a rigid body transformation is applied to floating image F such that rF coincides with the selected image point and the transformed floating image is displayed.

Abstract: A method of mapping geometrical objects to a digital image. At least one anchor point in a model is selected and mapped to the digital image. A geometric transformation is computed on the basis of at least one correspondence between an anchor object and a corresponding mapped object, and the calculated geometric transformation is applied to at least one geometric object thereby mapping it from the model image to a corresponding mapped position in the digital image.

Abstract: Several methods for retrospective correction of intensity inhomogeneities in digital diagnostic radiation images are presented. The methods are based on the correction of a digital image representation by means of a bias field. The bias field is deduced from the digital image representation of the diagnostic radiation image.

Abstract: A Markov Random Field (MRF)-based technique is described for performing clustering of images characterized by poor or limited data. The proposed method is a statistical classification model that labels the image pixels based on the description of their statistical and contextual information. Apart from evaluating the pixel statistics that originate from the definition of the K-means clustering scheme, the model expands the analysis by the description of the spatial dependence between pixels and their labels (context), hence leading to the reduction of the inhomogeneity of the segmentation output with respect to the result of pure K-means clustering.

Abstract: A method for point-of-interest attraction towards an object pixel in a digital image by first performing object segmentation resulting in a contour-based or a region-based representation of object pixels and background pixels of the image. Secondly a vector distance transform image is computed comprising a vector displacement of each background pixel towards the nearest of said object pixels and the nearest object pixel for a given background pixel is determined by adding the vector displacement to said background pixel. Finally the point-of-interest is attracted towards the determined nearest object pixel.

Abstract: For each of a number of landmarks in an image an initial position of the landmark is defined. Next a neighborhood around the initial position, comprising a number of candidate locations of the landmark is sampled and a cost is associated with each of the candidate locations. A cost function expressing a weighted sum of overall gray level cost and overall shape cost for all candidate locations is optimized. A segmented anatomic entity is defined as a path through a selected combination of candidate locations for which combination the cost function is optimized.

Abstract: A gray value model is generated encoding photometric knowledge at landmark positions. This step exploits intensity correlation in neighborhoods sampled around landmark positions. A geometric model is generated encoding geometric knowledge between landmarks. This step exploits spatial correlation between landmarks of segmented anatomic entities.

Abstract: Several methods for retrospective correction of intensity inhomogeneities in digital diagnostic radiation images are presented. The methods are based on the correction of a digital image representation by means of a bias field. The bias field is deduced from the digital image representation of the diagnostic radiation image.

Abstract: Several methods for retrospective correction of intensity inhomogeneites in digital diagnostic radiation images are presented. The methods are based on the correction of a digital image representation by means of a bias field. The bias field is deduced from the digital image representation of the diagnostic radiation image.

Abstract: A display device has means for controlling display of a blended image obtained by mapping a structure in a first image onto its corresponding structure in a second image by applying a geometric transformation to the first image so that the transformed first image and the second image are expressed in a common coordinate system. Starting from initial values the parameters of the geometric transformation are updated taking into account the result of an evaluation of a cost function. The superimposed images are blended.

Abstract: In a method for radiographic scoring of a radiographic image at least one region of interest is determined. Each of the determined regions of interest is displayed in close proximity to a number of reference stages each having an associated score. For each region of interest a reference stage image best matching the displayed region of interest is selected and the score number associated with the selected reference stage image is associated with the region of interest. Score numbers retained for each of the regions of interest are combined to form the score number of the radiographic image.

Abstract: A first and a second image are expressed in a common coordinate system by applying a geometric transformation to the second image so as to map a structure in the second image onto a corresponding structure in the first image in a common coordinate system. Starting from initial values, the parameters of the geometric transformation are updated taking into account the result of an evaluation of a cost function. Measurements are performed in the common coordinate system.

Abstract: A structure in a first image is mapped onto its corresponding structure in a second image by applying a geometric transformation to the first image so that both images are expressed in a common coordinate system. Starting from initial values the parameters of the geometric transformation are updated taking into account the result of an evaluation of a cost function. Finally the superimposed images may be blended.