Corpus Callosum Shape Signature for Segmentation Evaluation

Author(s)

Herrera, W. G. ; Bento, M. ; Rittner, L. ; CostaFelix, R ; Machado, JC ; Alvarenga, AV

• Document type: Journal article
• Source: XXVI BRAZILIAN CONGRESS ON BIOMEDICAL ENGINEERING, CBEB 2018, VOL. 2; v. 70, n. 2, p. 5-pg., 2019-01-01.

Abstract

Corpus callosum is the greatest white matter structure in brain. It is located beneath the cortex and connects both of two hemispheres, making possible their communication. Corpus callosum shape and size are associated with some subject's characteristics such as gender, handedness and age, and alterations in its structure have correlation with some diseases and medical conditions. Diffusion MRI allows a further analysis of corpus callosum structure and functionality by accessing neuronal fibers and tissues microstructure using the water diffusion model. However, the corpus callosum segmentation (required initial step to structural analysis) in diffusion MRI is challenging, since no gold-standard is available. In this work, we propose a segmentation evaluation method that relies on the corpus callosum shape by using its shape signature. We were able to evaluate three different segmentations in diffusion MRI over a 145 subjects' dataset using manual segmentation on T-1 as reference. (AU)

• FAPESP's process: 13/07559-3 - BRAINN - The Brazilian Institute of Neuroscience and Neurotechnology
• Grantee: Fernando Cendes
• Support Opportunities: Research Grants - Research, Innovation and Dissemination Centers - RIDC