Details

Autor(en) / Beteiligte

• Payer, Christian
• Pienn, Michael
• Bálint, Zoltán
• Shekhovtsov, Alexander
• Talakic, Emina
• Nagy, Eszter
• Olschewski, Andrea
• Olschewski, Horst
• Urschler, Martin

Titel

Automated integer programming based separation of arteries and veins from thoracic CT images

Ist Teil von

• Medical image analysis, 2016-12, Vol.34, p.109-122

Ort / Verlag

Netherlands: Elsevier B.V

Erscheinungsjahr

2016

Link zum Volltext

Quelle

Elsevier ScienceDirect Journals Complete

Beschreibungen/Notizen

• •A fully automatic artery-vein separation algorithm for thoracic CT image data is shown.•Artery-vein separation is based on two integer programs incorporating local and global anatomical and geometric properties of vessels.•The costly subtree extraction integer program is solved by a very efficient MRF solver.•Quantitative evaluation on 25 datasets indicate very good overlap with manual reference segmentations, outperforming a related method. Automated computer-aided analysis of lung vessels has shown to yield promising results for non-invasive diagnosis of lung diseases. To detect vascular changes which affect pulmonary arteries and veins differently, both compartments need to be identified. We present a novel, fully automatic method that separates arteries and veins in thoracic computed tomography images, by combining local as well as global properties of pulmonary vessels. We split the problem into two parts: the extraction of multiple distinct vessel subtrees, and their subsequent labeling into arteries and veins. Subtree extraction is performed with an integer program (IP), based on local vessel geometry. As naively solving this IP is time-consuming, we show how to drastically reduce computational effort by reformulating it as a Markov Random Field. Afterwards, each subtree is labeled as either arterial or venous by a second IP, using two anatomical properties of pulmonary vessels: the uniform distribution of arteries and veins, and the parallel configuration and close proximity of arteries and bronchi. We evaluate algorithm performance by comparing the results with 25 voxel-based manual reference segmentations. On this dataset, we show good performance of the subtree extraction, consisting of very few non-vascular structures (median value: 0.9%) and merged subtrees (median value: 0.6%). The resulting separation of arteries and veins achieves a median voxel-based overlap of 96.3% with the manual reference segmentations, outperforming a state-of-the-art interactive method. In conclusion, our novel approach provides an opportunity to become an integral part of computer aided pulmonary diagnosis, where artery/vein separation is important. [Display omitted]