Interaction increases flexibility of segmentation but it leads to undesirable behavior of an algorithm if knowledge being requested is inappropriate. In region growing, this is the case for defining the homogeneity criterion, as its specification depends also on image formation properties that are not known to the user. We developed a region growing algorithm that learns its homogeneity criterion automatically from characteristics of the region to be segmented. The method is based on a model that describes homogeneity and simple shape properties of the region. Parameters of the homogeneity criterion are estimated from sample locations in the region. These locations are selected sequentially in a random walk starting at the seed point, and the homogeneity criterion is updated continuously. This approach was extended to a fully automatic and complete segmentation method by using the pixels with the smallest gradient length in the not yet segmented image region as a seed point. The methods were tested for segmentation on test images and of structures in CT and MR images. We found the methods to work reliable if the model assumption on homogeneity and region characteristics are true. Furthermore, the model is simple but robust, thus allowing for a certain degree of deviation from model constraints and still delivering the expected segmentation result.
Abstract. Interaction increases flexibility of segmentation but it leads to undesirable behaviour of an algorithm if knowledge being requested is inappropriate. In region growing, this is the case for defining the homogeneity criterion as its specification depends also on image formation properties that are not known to the user. We developed a region growing algorithm that learns its homogeneity criterion automatically from characteristics of the region to be segmented. It produces results that are only little sensitive to the seed point location and it allows a segmentation of individual structures. The method was successfully tested on artificial images and on CT images.
Segmentation is an essential step in the analysis of medical images. For segmentation of 3-D data sets in clinical practice segmentation methods are necessary which have a small user interaction time and which are highly flexible. For this purpose we propose a two-step segmentation approach. The first step results in a coarse segmentation using the Image Foresting Transformation. In the second step an active surface creates the final segmentation. Our segmentation method was tested for segmentation on real CT images. The performance was compared with the manual segmentation. We found our method to work reliable.
In dynamic SPECT (dSPECT) images, function of a particular organ may be analyzed by measuring the temporal change of the spatial distribution of a radioactive tracer. The organ-specific and location-specific time-activity curves (TAC) of the different heart regions (regions with normal blood circulation and with disturbed blood circulation) are helpful for the diagnosis of heart diseases. A problem of the derivation of the TACs is that the dSPECT images have a poor spatial and temporal resolution and the data is distorted because of noise effects, partial volume effects and scatter artifacts. Segmentation according to some homogeneity principle will deliver regions of similar functional behavior but the segmented regions do not directly point to anatomy. For our goal of anatomy-specific segmentation, information about anatomy is provided a-priori and it must be fitted to the data. For initialization the user has to place a super ellipsoid in the data set. The parameters of this super ellipsoid are obtained from the computed mean shape of six manually segmented left ventricles in test data sets. A closer fit to the high gradients of the boundaries of the heart wall is achieved using the free form deformation method. For evaluation segmentation results are compared with a manual segmentation. In all test images we could ascertain a good correspondence between the manual and automatic segmentation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.