Method and system for machine learning based classification of vascular branches

Abstract

A method and apparatus for learning based classification of vascular branches to distinguish falsely detected branches from true branches is disclosed. A plurality of overlapping fixed size branch segments are sampled from branches of a detected centerline tree of a target vessel extracted from a medical image of a patient. A plurality of 1D profiles are extracted along each of the overlapping fixed size branch segments. A probability score for each of the overlapping fixed size branch segments is calculated based on the plurality of 1D profiles extracted for each branch segment using a trained deep neural network classifier. The trained deep neural network classifier may be a convolutional neural network (CNN) trained to predict a probability of a branch segment being fully part of a target vessel based on multi-channel 1D input. A final probability score is assigned to each centerline point in the branches of the detected centerline tree based on the probability scores of the overlapping branch segments containing that centerline point. The branches of the detected centerline tree of the target vessel are pruned based on the final probability scores of the centerline points.