A discriminative feature selection approach for shape analysis: application to fetal brain cortical folding study

J Pontabry (1) , François Rousseau (2) , C Studholme (3) , M Koob (4, 5) , J.-L Dietemann (4, 5)

1 IES - Institute for Epigenetics and Stem cells (Helmholtz Zentrum München)
2 IMT Atlantique - ITI - Département lmage et Traitement Information
3 BICG, Dept. of Pediatrics
4 ICube - Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie
5 Service de radiologie [Strasbourg]

The development of post-processing reconstruction techniques has opened new possibilities for the study of in utero fetal brain MRI data. Recent cortical surface analysis have led to the computation of quantitative maps characterizing brain folding of the developing brain. In this paper, we describe a novel feature selection-based approach that can be used for studying the most discriminative brain folding patterns using in utero reconstructed fetal MR data. Results show that this temporal process related to brain maturation can be characterized by a small set of points, located in the main sulci.

Mots clés: Structural MRI; Fetal imaging; Feature selection; Brain development

Domaines: Traitement du signal et de l'image [eess.SP]

J Pontabry, François Rousseau, C Studholme, M Koob, J.-L Dietemann. A discriminative feature selection approach for shape analysis: application to fetal brain cortical folding study. Medical Image Analysis, 2017, 35, pp.313 - 326. ⟨10.1016/j.media.2016.07.005⟩. ⟨hal-01115169⟩