Magnetic resonance imaging of the newborn brain: automatic segmentation of brain images into 50 anatomical regions

• Published in: PloS one Vol. 8; no. 4; p. e59990
• Main Authors: Gousias, Ioannis S, Hammers, Alexander, Counsell, Serena J, Srinivasan, Latha, Rutherford, Mary A, Heckemann, Rolf A, Hajnal, Jo V, Rueckert, Daniel, Edwards, A David
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 02-04-2013; Public Library of Science (PLoS)
• Subjects: Age; Algorithms; Brain; Brain - anatomy & histology; Brain - physiology; Brain research; Care and treatment; Comparative analysis; Computer Science; Councils; Female; Health aspects; Humans; Image processing; Image segmentation; Infant; Infant, Newborn; Infants; Magnetic resonance; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Medical research; Medicine; Neonates; Neuroimaging; Newborn babies; NMR; Nuclear magnetic resonance; Pediatrics; Premature infants; Propagation; Registration; Reproducibility of Results; Resonance; Segmentation; Target recognition; United Kingdom > UK
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0059990

We studied methods for the automatic segmentation of neonatal and developing brain images into 50 anatomical regions, utilizing a new set of manually segmented magnetic resonance (MR) images from 5 term-born and 15 preterm infants imaged at term corrected age called ALBERTs. Two methods were compared: individual registrations with label propagation and fusion; and template based registration with propagation of a maximum probability neonatal ALBERT (MPNA). In both cases we evaluated the performance of different neonatal atlases and MPNA, and the approaches were compared with the manual segmentations by means of the Dice overlap coefficient. Dice values, averaged across regions, were 0.81±0.02 using label propagation and fusion for the preterm population, and 0.81±0.02 using the single registration of a MPNA for the term population. Segmentations of 36 further unsegmented target images of developing brains yielded visibly high-quality results. This registration approach allows the rapid construction of automatically labeled age-specific brain atlases for neonates and the developing brain.