An approach for detecting blood vessel diseases from cone-beam CT image

This paper is aimed at assisting a medical doctor to detect blood vessel diseases from the high-resolution 3D blood vessels images obtained by cone-beam CT. The important objective is to show how the representation of blood vessels morphology can lead to feature measurement and identification of an abnormal region. In the authors' approach the blood vessels structure is extracted by a graph description of blood vessels centerlines and surfaces representation using curvatures. The measurement of the anatomical information, such as the blood vessel's orientation, cross-sectional area, surface shapes, and abnormal regions volumes, are based on a structure description. In order to alert the doctor's attention to the location of a blood vessel's abnormality, the authors attempt to enhance the difference between malformed and normal shapes using the measured blood vessels characteristics. In this paper, the authors focus on the approach based on surfaces representation and they present examples on cone-beam CT images of a patient's blood vessels.