The ability to study changes in brain morphometry in longitudinal studies majorly depends on the accuracy and reproducibility of the brain tissue quantification. We evaluate the accuracy and reproducibility of four previously proposed automatic brain tissue segmentation methods: FAST, SPM5, an automatically trained k-nearest neighbor (kNN) classifier, and a conventional kNN classifier based on a prior training set. The intensity nonuniformity correction and skull-stripping mask were the same for all methods. Evaluations were performed on MRI scans of elderly subjects derived from the general population. Accuracy was evaluated by comparison to two manual segmentations of MRI scans of six subjects (mean age 65.9 ± 4.4. years). Reproducibility was assessed by comparing the automatic segmentations of 30 subjects (mean age 57.0 ± 3.7. years) who were scanned twice within a short time interval. All methods showed good accuracy and reproducibility, with only small differences between methods. The conventional kNN classifier was the most accurate method with similarity indices of 0.82/0.90/0.94 for cerebrospinal fluid/gray matter/white matter, but it showed the lowest reproducibility. FAST yielded the most reproducible segmentation volumes with volume difference standard deviations of 0.55/0.49/0.38 (percentage of intracranial volume) respectively. The results of the reproducibility experiment can be used to calculate the required number of subjects in the design of a longitudinal study with sufficient power to detect changes over time in brain (tissue) volume. Example sample size calculations demonstrate a rather large effect of the choice of segmentation method on the required number of subjects.

Additional Metadata
Keywords Accuracy, Brain tissue segmentation, MRI, Reliability, Reproducibility, Sample size estimates
Persistent URL,
Journal NeuroImage
de Boer, R, Vrooman, H.A, Ikram, M.A, Vernooij, M.W, Breteler, M.M.B, van der Lugt, A, & Niessen, W.J. (2010). Accuracy and reproducibility study of automatic MRI brain tissue segmentation methods. NeuroImage, 51(3), 1047–1056. doi:10.1016/j.neuroimage.2010.03.012