Segmentation of the left ventricle in 4D-dSPECT data using free-form deformation of super quadrics

Abstract

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.

Survey of the Visual Exploration and Analysis of Perfusion Data

“…However, many aspects of the exploration are relevant for other dynamic medical volume data. As an example, the analysis of dynamic Single Photon Emission Computed Tomography (dSPECT) data is also based on the selection of regions and the investigation of curves depicting changes over time in these regions [63]. The analysis of functional MRI data also involves the analysis of time series [64].…”

Atrial and Ventricular Myocardium Extraction Using Model-based Techniques

“…When searching the literaturemanypublicationsc oncerning cardiac segmentation, especially for the left ventricularm yocardium,can be found [18,19]. Themaindifferenceb etween existing segmentation approaches andt he one presented here is that we need an accurate functionalmodel, not an anatomical one.The reasonisthatwe do not makestudieswhere anatomical structures matter(e.g.motion studies,fluid studies).…”

Automatic Segmentation of the Left Ventricle in 3D SPECT Data by Registration with a Dynamic Anatomic Model

“…The approach in [2] tries to solve this problem by using superquadrics, followed by free form deformation. These implicit dynamic 3D shape models have already been used in [3] for tracking the segmented LV in 4D-SPECT data.…”

“…These implicit dynamic 3D shape models have already been used in [3] for tracking the segmented LV in 4D-SPECT data. In [2], a very simple model is used for an initial segmentation. Subsequent ne-tuning via free-form deformation does not use model knowledge, but searches the data slicewise for points supporting the interpolation.…”