Segmentation of the cortex in fetal MRI using a topological model

Benoît Caldairou (1, 2) , Nicolas Passat (1) , Piotr Habas (3) , Colin Studholme (3) , Mériam Koob (2) , Jean-Louis Dietemann (2) , François Rousseau (1)

1 LSIIT - Laboratoire des Sciences de l'Image, de l'Informatique et de la Télédétection
2 LINC - Laboratoire d'Imagerie et de Neurosciences Cognitives
3 Biomedical Image Computing Group

The study of in utero fetal MR images is essential for the diagnosis of abnormal brain development and the study of the maturation of the brain structures. However, few automated segmentation methods have been developed so far, compare to the numerous ones existing for the adult brain anatomy, which is due to the particular properties of these images. In this paper, we propose a two-step cortex segmentation technique including anatomical priors and a topological model. Experiments performed on in utero MR data and validation by comparison to experts segmentation emphasize the relevance of the method.

Mots clés: clustering; topology; segmentation; cortex; fetal brain

Domaines: Traitement des images [eess.IV]; Imagerie médicale

Benoît Caldairou, Nicolas Passat, Piotr Habas, Colin Studholme, Mériam Koob, et al.. Segmentation of the cortex in fetal MRI using a topological model. International Symposium on Biomedical Imaging (ISBI), 2011, Chicago, United States. pp.2045-2048, ⟨10.1109/ISBI.2011.5872814⟩. ⟨hal-01695037⟩