Systems and methods for automatic blood vessel extraction

A method comprising:

• receiving a three-dimensional (3D) image data set of a portion of a body;
• segmenting the 3D image data set to identify blood vessels in the 3D image data set using a neural network model;
• classifying the blood vessels using the neural network model;
• detecting starting points of the blood vessels using the neural network model;
• detecting endpoints of the blood vessels using the neural network model;
• for each endpoint:
• calculating optimal paths from possible starting points to the endpoint;
• selecting a best starting point from possible starting points;
• and
• setting a class of a path from the best starting point to the endpoint;
• and
• merging paths of the same starting point into a tree structure.

A method of generating directed graphs of blood vessels, the method comprising:

• receiving a three-dimensional (3D) image data set of a portion of a body;
• processing the 3D image data set with a neural network to generate a segmentation probability map of blood vessels in the 3D image data set;
• closing at least one hole of the blood vessel in the segmentation probability map;
• detecting starting points of the blood vessels;
• detecting endpoints of the blood vessels;
• for each endpoint:
• tracking the shortest path from the endpoint to each of the starting points, yielding probable paths;
• and
• selecting the most probable path from the probable paths;
• merging paths having a common starting point to one directed graph;
• and
• solving for at least one overlap between directed graphs.