Abstract: A suitable database, including a temporal series of images is acquired (3) and subjected to a suitable binary segmentation (4) to create temporally sequenced binary coded images large portions corresponding to blood are labeled as unity, the rest is set to zero. A preceding binary coded image (8a) corresponding to a phase (t) from the temporal sequence is subtracted from a subsequent binary coded image (8b) corresponding to a phase (t+1) yielding a multi-dimensional temporal feature map (8c). A pre-defined deformable shape model is deformed (14) to fit the temporal feature map. The segmentation results are displayed (18) using suitable display (47). The segmented surface is overlaid on the original data using a two-, three- or four-dimensional visualization technique and can be presented as a color-code in a suitable transparency mode.

Abstract: A method is arranged to segment a surface in a multi-dimensional dataset comprising a plurality of images. Data processing and data acquisition steps can be temporally or geographically distanced, so that the results of a suitable data segmentation are accessed. Next, suitable plurality of image features resembling possible spatial positions of the surface conceived to be segmented are selected and accessed. The features are subsequently matched for all image portions, whereby for each feature a matching error is assigned. A pre-defined selectivity factor is accessed defining a maximum allowable variable fraction of the features having largest matching errors which can be discarded. The segmentation of the sought surface is performed, whereby the discarded features are not taken into account for evaluating the quality of fit of a candidate deformation. The resulting surface is displayed on a suitable display means.

Abstract: The invention relates to a data processing apparatus and a method for providing visualisation parameters controlling the display of a medical image (12). The data processing apparatus comprises a mapping component (16). The mapping component (16) is arranged to receive a current dataset (15) corresponding to the medical image and comprising a content description thereof, to compare the content description of the current dataset (15) with a content description of a plurality of stored datasets, to select at least one further dataset out of the plurality of stored datasets, to retrieve stored visualisation parameters corresponding to the at least one further dataset, and to prepare the retrieved visualisation parameters as the visualisation parameters controlling the display of the medical image (12).

Abstract: The method according to the invention is arranged to segment a surface in a multi-dimensional dataset comprising a plurality of images, which may be acquired using a suitable data-acquisition unit at a preparatory step 2. It is possible that data processing and data acquisition steps are temporally or geographically distanced, so that at step 4 the results of a suitable data segmentation step 6 are accessed, whereby said results comprise portions of the image which are subsequently used to segment the surface using the method of the invention. Next, at step 8 a suitable plurality of image features resembling possible spatial positions of the surface conceived to be segmented are selected and accessed. The features are subsequently matched for all image portions at step 10, whereby for each feature a matching error is assigned. At step 14 a pre-defined selectivity factor is accessed defining a maximum allowable variable fraction of the features having largest matching errors which can be discarded.

Abstract: The method (1) according to the invention may be schematically divided into three major phases. Phase (2) comprises step (3) of acquiring a suitable dataset, which is then subjected to a suitable binary segmentation at step (4) results of which are being accessed at step (5). The results comprise temporally sequenced binary coded images, whereby image portions corresponding to blood are labeled as unity, the rest is set to zero. The subsequent phase (12) of the method according to the invention is directed to performing the image processing for segmenting a structure. At step (8) a computation is performed whereby a preceding binary coded image (8a) corresponding to a phase from the temporal sequence is subtracted from a subsequent binary coded image 8b corresponding to a phase yielding a multi-dimensional temporal feature map (8c). At step (9) spatial positions corresponding to a certain voxel value are derived and are used to segment the structure.

Abstract: The invention relates to a method of image segmentation for delineating a structure associated with a reference structure in an image. For this purpose a segmentation of the reference structure is accessed. The appearance of different tissue types is learned using the model by non parametric robust estimation that employs a fuzzy kNN classifier in two stages (outlier reduction and final estimation). The model is used to provide seed points for the segmentation. The graph cut method is adapted to perform segmentation of the sought structure. The invention further relates to a system and a computer program for image segmentation.

Abstract: The invention relates to a method 1 of image segmentation where in step 2 a prior model representative of a structure conceived to be segmented in an image is accessed. Preferably, the image comprises a medical diagnostic image. Still preferably, the medical diagnostic image is prepared in a DICOM format, whereby supplementary information is stored besides diagnostic data. In these cases the method 1 according to the invention advantageously proceeds to step 3, where the supplementary information is extracted from electronic file 5, comprising for example suitable patient-related information 5a and/or suitable structure-related information 5b. Examples of the patient-related information comprise a patient's age, sex, group, etc., whereas examples of the structure-related information may comprise an anatomic location of the structure, such as rectum, bladder, lung etc, or the suspected/diagnosed pathology of the patient.

Abstract: The method 1 according to the invention is preferably practiced in real time and directly after a suitable acquisition 3 of the multi-dimensional dataset, which is accessed at step 5 and the images constituting the multi-dimensional dataset are classified at step 8. Preferably, for reducing an amount of data to be processed at step 6 the image data is subjected to a restrictive region of interest determination. At step 9 the classified cardiac images are subjected to a an image thinning operator so that the resulting images comprise a plurality of connected image components which are further analyzed at step 14. After the thinning step 9 a labeling step 11 is performed, where different connected components in the multi-dimensional dataset are accordingly labeled. This step is preferably followed by a region growing step 13, which is constrained by binary threshold used at step 8b. For each connected image component a factor F is computed at step 14.