Method and system for extracting centerline representation of vascular structures in medical images via optimal paths in computational flow fields

An apparatus for extracting a centerline of a target vessel in a medical image of a patient, comprising:

• means for estimating a vessel orientation tensor for each of a plurality of voxels associated with the target vessel in the medical image using a trained vessel orientation tensor classifier;
• means for estimating a flow field for the plurality of voxels associated with the target vessel in the medical image based on the vessel orientation tensor estimated for each of the plurality of voxels;
• and
• means for extracting a centerline of the target vessel based on the estimated flow field for the plurality of voxels associated with the target vessel in the medical image by detecting a path that carries maximum flow.

A non-transitory computer readable medium storing computer program instructions for extracting a centerline of a target vessel in a medical image of a patient, the computer program instructions when executed by a processor cause the processor to perform operations comprising:

• estimating a vessel orientation tensor for each of a plurality of voxels associated with the target vessel in the medical image using a trained vessel orientation tensor classifier;
• estimating a flow field for the plurality of voxels associated with the target vessel in the medical image based on the vessel orientation tensor estimated for each of the plurality of voxels;
• and
• extracting a centerline of the target vessel based on the estimated flow field for the plurality of voxels associated with the target vessel in the medical image by detecting a path that carries maximum flow.