TY - JOUR
T1 - Segmentation of brain magnetic resonance images based on multi-atlas likelihood fusion
T2 - Testing using data with a broad range of anatomical and photometric profiles
AU - Tang, Xiaoying
AU - Crocetti, Deana
AU - Kutten, Kwame
AU - Ceritoglu, Can
AU - Albert, Marilyn S.
AU - Mori, Susumu
AU - Mostofsky, Stewart H.
AU - Miller, Michael I.
N1 - Publisher Copyright:
© 2015 Tang, Crocetti, Kutten, Ceritoglu, Albert, Mori, Mostofsky and Miller.
PY - 2015/3/1
Y1 - 2015/3/1
N2 - We propose a hierarchical pipeline for skull-stripping and segmentation of anatomical structures of interest from T1-weighted images of the human brain. The pipeline is constructed based on a two-level Bayesian parameter estimation algorithm called multi-atlas likelihood fusion (MALF). In MALF, estimation of the parameter of interest is performed via maximum a posteriori estimation using the expectation-maximization (EM) algorithm. The likelihoods of multiple atlases are fused in the E-step while the optimal estimator, a single maximizer of the fused likelihoods, is then obtained in the M-step. There are two stages in the proposed pipeline; first the input T1-weighted image is automatically skull-stripped via a fast MALF, then internal brain structures of interest are automatically extracted using a regular MALF. We assess the performance of each of the two modules in the pipeline based on two sets of images with markedly different anatomical and photometric contrasts; 3T MPRAGE scans of pediatric subjects with developmental disorders vs. 1.5T SPGR scans of elderly subjects with dementia. Evaluation is performed quantitatively using the Dice overlap as well as qualitatively via visual inspections. As a result, we demonstrate subject-level differences in the performance of the proposed pipeline, which may be accounted for by age, diagnosis, or the imaging parameters (particularly the field strength). For the subcortical and ventricular structures of the two datasets, the hierarchical pipeline is capable of producing automated segmentations with Dice overlaps ranging from 0.8 to 0.964 when compared with the gold standard. Comparisons with other representative segmentation algorithms are presented, relative to which the proposed hierarchical pipeline demonstrates comparative or superior accuracy.
AB - We propose a hierarchical pipeline for skull-stripping and segmentation of anatomical structures of interest from T1-weighted images of the human brain. The pipeline is constructed based on a two-level Bayesian parameter estimation algorithm called multi-atlas likelihood fusion (MALF). In MALF, estimation of the parameter of interest is performed via maximum a posteriori estimation using the expectation-maximization (EM) algorithm. The likelihoods of multiple atlases are fused in the E-step while the optimal estimator, a single maximizer of the fused likelihoods, is then obtained in the M-step. There are two stages in the proposed pipeline; first the input T1-weighted image is automatically skull-stripped via a fast MALF, then internal brain structures of interest are automatically extracted using a regular MALF. We assess the performance of each of the two modules in the pipeline based on two sets of images with markedly different anatomical and photometric contrasts; 3T MPRAGE scans of pediatric subjects with developmental disorders vs. 1.5T SPGR scans of elderly subjects with dementia. Evaluation is performed quantitatively using the Dice overlap as well as qualitatively via visual inspections. As a result, we demonstrate subject-level differences in the performance of the proposed pipeline, which may be accounted for by age, diagnosis, or the imaging parameters (particularly the field strength). For the subcortical and ventricular structures of the two datasets, the hierarchical pipeline is capable of producing automated segmentations with Dice overlaps ranging from 0.8 to 0.964 when compared with the gold standard. Comparisons with other representative segmentation algorithms are presented, relative to which the proposed hierarchical pipeline demonstrates comparative or superior accuracy.
KW - Automated brain segmentation
KW - Likelihood-fusion
KW - Multi-atlas
KW - Skull-stripping
KW - Subcortical structures
KW - Ventricle
UR - http://www.scopus.com/inward/record.url?scp=84928017595&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84928017595&partnerID=8YFLogxK
U2 - 10.3389/fnins.2015.00061
DO - 10.3389/fnins.2015.00061
M3 - Article
C2 - 25784852
AN - SCOPUS:84928017595
SN - 1662-4548
VL - 9
JO - Frontiers in Neuroscience
JF - Frontiers in Neuroscience
IS - MAR
M1 - 061
ER -