Automated structuring of pulmonary artery segmentations using graphs.
•
Machine learning to clean graph representations.
•
Accurate semantic labeling of graphs achieved for central pulmonary arteries.
Abstract
Automated feature extraction from medical images is an important task in imaging informatics. We describe a graph-based technique for automatically identifying vascular substructures within a vascular tree segmentation. We illustrate our technique using vascular segmentations from computed tomography pulmonary angiography images. The segmentations were acquired in a semi-automated fashion using existing segmentation tools. A 3D parallel thinning algorithm was used to generate the vascular skeleton and then graph-based techniques were used to transform the skeleton to a directed graph with bifurcations and endpoints as nodes in the graph. Machine-learning classifiers were used to automatically prune false vascular structures from the directed graph. Semantic labeling of portions of the graph with pulmonary anatomy (pulmonary trunk and left and right pulmonary arteries) was achieved with high accuracy (percent correct ⩾ 0.97). Least-squares cubic splines of the centerline paths between nodes were computed and were used to extract morphological features of the vascular tree. The graphs were used to automatically obtain diameter measurements that had high correlation () with manual measurements made from the same arteries.
This work was supported in part by NIH Grants NHLBI R01 HL087119, U54HL108460, by the Department of Biomedical Informatics at the University of Pittsburgh, and by the Office of the Senior Vice President for Health Sciences at the University of Utah.