Image segmentation
View Patent ↗According to one embodiment there is provided a method of selecting a plurality of M atlases from among a larger group of N candidate atlases to form a multi-atlas data set to be used for computer automated segmentation of novel image data sets to mark objects of interest therein. A set of candidate atlases is used containing a reference image data set and segmentation data. Each of the candidate atlases is segmented against the others in a leave-one-out strategy, in which the candidate atlases are used as training data for each other. For each candidate atlas in turn, the following is carried out: registering; segmenting; computing an overlap; computing a value of the similarity measure for each of the registrations; and obtaining a set of regression parameters by performing a regression with the similarity measure being the independent variable and the overlap being the dependent variable.
1. A method of selecting a plurality of M atlases from among a larger group of N candidate atlases to form a multi-atlas data set to be used for computer automated segmentation of novel image data sets to mark objects of interest therein, the method comprising:
(a) providing a computer with a set of candidate atlases, each candidate atlas containing a reference image data set and segmentation data which marks an object of interest within the reference image data set;
(b) providing the computer with a plurality of training image data sets, each containing a training image data set and segmentation data which marks an object of interest within the training image data set;
(c) segmenting in the computer each of the training image data sets against each of the candidate atlases such that for each candidate atlas in turn the following is carried out:
(i) registering the candidate atlas with each of the training image data sets;
(ii) segmenting each of the training image data sets with the candidate atlas;
(iii) computing an overlap between each training image data set and the candidate atlas;
(iv) computing a value of the similarity measure for each of the registrations;
(v) obtaining a set of regression parameters by performing a regression with the similarity measure being the independent variable and the overlap being the dependent variable;
(d) selecting in the computer a subset of M atlases from among all the N candidate atlases to form the multi-atlas data set, the M atlases being those atlases determined to collectively provide the highest aggregate overlap over all the training data image sets.
2. The method of claim 1 followed by:
(e) outputting the multi-atlas data set to a computer program product operable to segment novel image data sets.
3. The method of claim 1 , wherein the reference image data sets and the training image data sets are one and the same image data sets, with the method being carried out using a leave-one-out strategy.
4. A computer program product stored on a non-transitory computer readable medium, bearing machine readable instructions for carrying out the method of claim 1 .
5. A computer loaded with and operable to execute machine readable instructions for carrying out the method of claim 1 .