Overview of the segmentation process. Top left: Eight CTA atlas scans and the corresponding manually segmented 3D surfaces. Top right: CT scan to be segmented. The atlas scans are registered and the 3D surfaces are transformed to match the subject scan. Bottom right: The 3D surfaces are combined using majority voting. Bottom left: Resulting fat voxels, obtained after thresholding and connected component analysis.
The eight pericardium atlas surfaces used for atlas-based segmentation illustrating the encountered shape and size variations in the atlas images.
(a) A random axial slice showing the result of a manually obtained whole heart segmentation (with adjusted windowing level, for better visibility). (b) Corresponding slice showing the voxels containing epicardial fat.
Random axial slice with the overlay representing the fixed mask used for the registration.
Scatter plots of automatic vs manual fat quantification methods and results from linear regression: (a) correlation between the two observers; (b) correlation between Observer 1 and the automatic method; and (c) correlation between Observer 2 and the automatic method.
Bland–Altman analysis: (a) between observers; (b) between automatic method and Observer 1; and (c) between automatic method and Observer 2.
Excluded subjects: (a) subject with lung removed and (b) segmentation leaking into the ribcage due to rare anatomical variation in heart shape.
Characteristics of the subjects (n = 98). Values are mean ± SD for continuous variables and numbers (%) for dichotomous variables.
Table representing the results of the registration strategy. Values represent mean ± SD.
Performance of the whole heart segmentation: comparing the automatic method to each of the observers and the observers to each other.
Article metrics loading...
Full text loading...