Automated extraction and labelling of the arterial tree from whole-body MRA data

• Published in: Medical image analysis Vol. 24; no. 1; pp. 28 - 40
• Main Authors: Shahzad, Rahil, Dzyubachyk, Oleh, Staring, Marius, Kullberg, Joel, Johansson, Lars, Ahlström, Håkan, Lelieveldt, Boudewijn P.F., van der Geest, Rob J.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.08.2015
• Subjects: Aged; Algorithms; Arteries - anatomy & histology; Atlas-based image registration; Female; Graph matching; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Imaging, Three-Dimensional - methods; Intensity inhomogeneity correction; Machine Learning; Magnetic Resonance Angiography - methods; Male; Pattern Recognition, Automated - methods; Reproducibility of Results; Sensitivity and Specificity; Vessel tree extraction; Whole Body Imaging - methods; Whole-body MRA; Intensity inhomogeneity correction; Atlas-based image registration; Whole-body MRA; Vessel tree extraction; Graph matching
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2015.05.008

•A fully automated method for extraction and labelling of the arterial tree from 3D whole-body MRA data is presented.•A novel approach for intensity inhomogeneity correction for whole-body MRA data has been developed.•Centerline extraction was performed using the vessel-enhanced probability map of the estimated contrast class.•Optimal strategy for inter-subject registration of the centerlines of the vascular tree has been identified.•A combination of atlas-based and graph-based approaches were used to accurately label the arterial tree segments. [Display omitted] In this work, we present a fully automated algorithm for extraction of the 3D arterial tree and labelling the tree segments from whole-body magnetic resonance angiography (WB-MRA) sequences. The algorithm developed consists of two core parts (i) 3D volume reconstruction from different stations with simultaneous correction of different types of intensity inhomogeneity, and (ii) Extraction of the arterial tree and subsequent labelling of the pruned extracted tree. Extraction of the arterial tree is performed using the probability map of the “contrast” class, which is obtained as one of the results of the inhomogeneity correction scheme. We demonstrate that such approach is more robust than using the difference between the pre- and post-contrast channels traditionally used for this purpose. Labelling the extracted tree is performed by using a combination of graph-based and atlas-based approaches. Validation of our method with respect to the extracted tree was performed on the arterial tree subdivided into 32 segments, 82.4% of which were completely detected, 11.7% partially detected, and 5.9% were missed on a cohort of 35 subjects. With respect to automated labelling accuracy of the 32 segments, various registration strategies were investigated on a training set consisting of 10 scans. Further analysis on the test set consisting of 25 data sets indicates that 69% of the vessel centerline tree in the head and neck region, 80% in the thorax and abdomen region, and 84% in the legs was accurately labelled to the correct vessel segment. These results indicate clinical potential of our approach in enabling fully automated and accurate analysis of the entire arterial tree. This is the first study that not only automatically extracts the WB-MRA arterial tree, but also labels the vessel tree segments.