Séminaire du 30/01/2014

jeudi 30 janvier 2014, 14h00, C218

Using brain morphology and mathematical morphology to automatically segment the newborn brain

Conférencier : Laura Gui (Université de Genève)

Résumé : The segmentation of MR images of the neonatal brain is an essential step in the study of infant brain development. State-of-the-art methods for adult brain MRI segmentation are not applicable to the neonatal brain, due to large differences in structure and tissue image intensity between newborn and adult brains. In this talk I will present a method for the segmentation of newborn brain MRI, based on the exploitation of high-level brain morphology information (regarding tissue connectivity, structure and relative location) via mathematical morphology tools. As a result, the brain is segmented both at global level (intracranial cavity, cerebellum, brainstem and the two hemispheres) and at tissue level (cortical and subcortical gray matter, myelinated and unmyelinated white matter, and cerebrospinal fluid). The proposed method does not necessitate an atlas, or manual interaction, and can be used to automatically segment newborn brains of varying anatomy (e.g. preterm- vs. term-born), allowing for group studies of brain development.