Automatic myocardium segmentation in late-enhancement MRI

Cybèle Ciofolo (1) , Maxim Fradkin (1) , Benoît Mory (1) , Gilion Hautvast (2) , Marcel Breeuwer (2)

1 Medisys - MedisysResearch Lab
2 HI - CS&AD - Healthcare Informatics - Clinical Science & Advanced Development - Philips Medical Systems Nederlands B.V.

We propose a novel automatic method to segment the myocardium on late-enhancement cardiac MR (LE CMR) images with a multi-step approach. First, in each slice of the LE CMR volume, a geometrical template is deformed so that its borders fit the myocardial contours. The second step consists in introducing a shape prior of the left ventricle. To do so, we use the cine MR sequence that is acquired along with the LE CMR volume. As the myocardial contours can be more easily automatically obtained on this data, they are used to build a 3D mesh representing the left ventricle geometry and the underlying myocardium thickness. This mesh is registered towards the contours obtained with the geometrical template, then locally adjusted to guarantee that scars are included inside the final segmentation. The quantitative evaluation on 27 volumes (272 slices) shows robust and accurate results.

Mots clés: Image Segmentation; Late-Enhancement; Magnetic Resonance Imaging; Cardiovascular System; Automation.; Automation

Domaines: Imagerie médicale

Cybèle Ciofolo, Maxim Fradkin, Benoît Mory, Gilion Hautvast, Marcel Breeuwer. Automatic myocardium segmentation in late-enhancement MRI. 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2008. ISBI 2008., May 2008, Paris, France. pp. 225-228, ⟨10.1109/ISBI.2008.4540973⟩. ⟨hal-00350565⟩