Extraction of objects from CT images by sequential segmentation and carving

摘要

Extracting objects from a computed tomography (CT) image, including: sequentially applying segmentation and carving on volumetric data of the objects in the CT image; and splitting and merging the segmented objects based on homogeneity of the objects in the CT image.

主权项

1. A non-transitory computer readable medium containing instructions that when executed by a processor perform a method of extracting objects from a computed tomography (CT) image, the method comprising:
applying bilateral filtering to a volumetric data of the objects in the CT image; sequentially segmenting and carving the objects from the volumetric data of the objects in the CT image, wherein the objects are segmented and carved in the order of:
(1) homogeneous bulk objects, (2) homogeneous medium thickness objects, (3) homogeneous sheet objects, (4) homogeneous metallic objects, and (5) heterogeneous objects; adjusting object boundaries of the objects by level set-based active contours which include finding a contour represented by a level set function having an internal term related to contour smoothness and an external term related to image information; and splitting and merging the segmented objects based on homogeneity of the objects in the CT image.