| 摘要 |
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. The segmentation of the sought surface is performed at step 16, whereby the discarded features are not taken into account for evaluating the quality of fit of a candidate deformation of the. The resulting surface is being displayed on a suitable display means at step 18, whereby it is preferably overlaid on original, notably diagnostic data for user's analysis. In case when the user is satisfied with the result of the segmentation, the segmented surface is stored at step 18. Otherwise, the process is returned to step 14, where a further selectivity factor is accessed. It is possible that the further selectivity factor is altered at step 11 by a user's input, or, alternatively it may be provided by a certain alteration algorithm 13. The invention further relates to a system, a computer program, a workstation, a viewing station, a computer program and a user interface.
|
