A method, a system and a computer program for segmenting a structure in a dataset

Abstract

The method 1 according to the invention may be schematically divided into three major phases. Phase 2 comprises preparatory steps, namely the 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. A pre-defined deformable shape model is accessed at step 11, which is then deformed at step 14 in accordance with spatial coordinates, derived at step 9. Preferably, the segmentation result is stored at step 16. Finally, during a further phase 22 of the method according to the invention, the segmentation results are displayed at step 18 using suitable display means. Preferably, the segmented surface is overlaid on the original data using a two- , three- or four-dimensional visualization technique. Still preferable, to ease comprehension of the result, the segmented surface is presented as a color-code in a suitable transparency mode. The invention further relates to an apparatus and a computer program for segmenting a structure in a dataset.

Description

technical field [0001] The present invention relates to a method for segmenting structures in a data set comprising a plurality of multidimensional images acquired for various time phases in a time series, each multidimensional image comprising information about a target tissue and about another tissue data. [0002] The present invention also relates to a system for segmenting structures in a data set comprising a plurality of multidimensional images acquired for respective temporal phases in a time series, each multidimensional image comprising data on target tissue and on additional tissue. [0003] The invention furthermore relates to a computer program for segmenting structures in a data set comprising a plurality of multidimensional images acquired for individual time phases in a time series, each multidimensional image comprising data about a target tissue and about additional tissue . Background technique [0004] An example of the method explained in the opening p...

AI Technical Summary

Problems solved by technology

[0005] The disadvantage of the known method is that it provides an inherently low-level pixel-based segmentation technique whose quality depends heavily on the original image quality

Moreover, the threshold in the known method needs to be adjusted according to the image contrast

Images