3D segmentation of abdominal aorta from CT-scan and MR images

Anthony A. Duquette (1) , Pierre-Marc Jodoin (1) , Olivier Bouchot (2) , Alain Lalande (2)

1 MOIVRE Centre
2 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]

We designed a generic method for segmenting the aneurismal sac of an abdominal aortic aneurysm (AAA) both from multi-slice MR and CT-scan examinations. It is a semi-automatic method requiring little human intervention and based on graph cut theory to segment the lumen interface and the aortic wall of AAAs. Our segmentation method works independently on MRI and CT-scan volumes and has been tested on a 44 patient dataset and 10 synthetic images. Segmentation and maximum diameter estimation were compared to manual tracing from 4 experts. An inter-observer study was performed in order to measure the variability range of a human observer. Based on three metrics (the maximum aortic diameter, the volume overlap and the Hausdorff distance) the variability of the results obtained by our method is shown to be similar to that of a human operator, both for the lumen interface and the aortic wall. As will be shown, the average distance obtained with our method is less than one standard deviation away from each expert, both for healthy subjects and for patients with AAA. Our semi-automatic method provides reliable contours of the abdominal aorta from CT-scan or MRI, allowing rapid and reproducible evaluations of AAA.

Mots clés: AAA segmentation; MRI; CT scan; Graph cut; Volume segmentation

Domaines: Imagerie médicale

Anthony A. Duquette, Pierre-Marc Jodoin, Olivier Bouchot, Alain Lalande. 3D segmentation of abdominal aorta from CT-scan and MR images. Computerized Medical Imaging and Graphics, 2012, 36, pp.294-303. ⟨hal-00726535⟩