A hierarchical scheme for geodesic anatomical labeling of airway trees

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt


Aasa Feragen, Jens Petersen, Megan Owen, Pechin Chien Pau Lo, Laura Thomsen, Mathilde M. W. Wille, Asger Dirksen, Marleen de Bruijne

We present a fast and robust supervised algorithm for label-
ing anatomical airway trees, based on geodesic distances in a geometric
tree-space. Possible branch label configurations for a given unlabeled air-
way tree are evaluated based on the distances to a training set of labeled
airway trees. In tree-space, the airway tree topology and geometry change
continuously, giving a natural way to automatically handle anatomical
differences and noise. The algorithm is made efficient using a hierarchical
approach, in which labels are assigned from the top down. We only use
features of the airway centerline tree, which is relatively unaffected by

A thorough leave-one-patient-out evaluation of the algorithm is made on
40 segmented airway trees from 20 subjects labeled by 2 medical experts.
We evaluate accuracy, reproducibility and robustness in patients with
Chronic Obstructive Pulmonary Disease (COPD). Performance is statis-
tically similar to the inter- and intra-expert agreement, and we found no
significant correlation between COPD stage and labeling accuracy.
TitelMedical Image Computing and Computer-Assisted Intervention – MICCAI 2012 : 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part III
RedaktørerNicholas Ayache , Hervé Delingette , Polina Golland, Kensaku Mori
Antal sider9
ISBN (Trykt)978-3-642-33453-5
ISBN (Elektronisk)978-3-642-33454-2
StatusUdgivet - 2012
Begivenhed15th International Conference on Medical Image Computing and Computer-Assisted Intervention - Nice, Frankrig
Varighed: 1 okt. 20125 okt. 2012
Konferencens nummer: 15


Konference15th International Conference on Medical Image Computing and Computer-Assisted Intervention
NavnLecture notes in computer science

Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk

Ingen data tilgængelig

ID: 38415541