Abstract
Quantitative volumes from brain magnetic resonance imaging (MRI) acquired across the life course may be useful for investigating long term effects of risk and resilience factors for brain development and healthy aging, and for understanding early life determinants of adult brain structure. Therefore, there is an increasing need for automated segmentation tools that can be applied to images acquired at different life stages. We developed an automatic segmentation method for human brain MRI, where a sliding window approach and a multi-class random forest classifier were applied to high-dimensional feature vectors for accurate segmentation. The method performed well on brain MRI data acquired from 179 individuals, analyzed in three age groups: newborns (38–42 weeks gestational age), children and adolescents (4–17 years) and adults (35–71 years). As the method can learn from partially labeled datasets, it can be used to segment large-scale datasets efficiently. It could also be applied to different populations and imaging modalities across the life course.
Highlights
During early life, the brain undergoes significant morphological and functional changes, the integrity of which determines long-term neurological, cognitive and psychiatric functions (Tamnes et al, 2013)
The infant brain presents challenges to automated segmentation algorithms developed for adult brain due to: wide variations in head size and shape in early life, rapid changes in tissue contrast associated with myelination, decreases in brain water, changes in tissue density, and relatively low contrast to noise ratio between gray matter (GM) and white matter (WM)
The highest accuracies obtained for brainstem, cerebellum, deep GM, and WM with mean Dice coefficient of 90–94%, while cortex and cerebrospinal fluid (CSF) had average Dice coefficients of 89 and 85%, respectively
Summary
The brain undergoes significant morphological and functional changes, the integrity of which determines long-term neurological, cognitive and psychiatric functions (Tamnes et al, 2013). Improved understanding of cerebral structural changes across the life course may be useful for studying early life determinants and atypical trajectories that underlie these common problems. Quantitative volumes from brain structural magnetic resonance imaging (MRI) acquired at different stages of life offer the possibility of new insight into cerebral phenotypes of disease, biomarkers for evaluating treatment protocols, and improved clinical decision-making and diagnosis. The literature presents a clear distinction between methods developed for different ages partly because the computational task is determined by properties of the acquired data and these. The infant brain presents challenges to automated segmentation algorithms developed for adult brain due to: wide variations in head size and shape in early life, rapid changes in tissue contrast associated with myelination, decreases in brain water, changes in tissue density, and relatively low contrast to noise ratio between gray matter (GM) and white matter (WM). Automated segmentation tools for modeling structure over years are limited, and this hampers research that would benefit from robust assessment of the newborn to the adult trajectory
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
