TY - JOUR

T1 - Comparing fully automated state-of-the-art cerebellum parcellation from magnetic resonance images

AU - Carass, Aaron

AU - Cuzzocreo, Jennifer L.

AU - Han, Shuo

AU - Hernandez-Castillo, Carlos R.

AU - Rasser, Paul E.

AU - Ganz, Melanie

AU - Beliveau, Vincent

AU - Dolz, Jose

AU - Ben Ayed, Ismail

AU - Desrosiers, Christian

AU - Thyreau, Benjamin

AU - Romero, José E.

AU - Coupé, Pierrick

AU - Manjón, José V.

AU - Fonov, Vladimir S.

AU - Collins, D. Louis

AU - Ying, Sarah H.

AU - Onyike, Chiadi U.

AU - Crocetti, Deana

AU - Landman, Bennett A.

AU - Mostofsky, Stewart H.

AU - Thompson, Paul M.

AU - Prince, Jerry L.

PY - 2018

Y1 - 2018

N2 - The human cerebellum plays an essential role in motor control, is involved in cognitive function (i.e., attention, working memory, and language), and helps to regulate emotional responses. Quantitative in-vivo assessment of the cerebellum is important in the study of several neurological diseases including cerebellar ataxia, autism, and schizophrenia. Different structural subdivisions of the cerebellum have been shown to correlate with differing pathologies. To further understand these pathologies, it is helpful to automatically parcellate the cerebellum at the highest fidelity possible. In this paper, we coordinated with colleagues around the world to evaluate automated cerebellum parcellation algorithms on two clinical cohorts showing that the cerebellum can be parcellated to a high accuracy by newer methods. We characterize these various methods at four hierarchical levels: coarse (i.e., whole cerebellum and gross structures), lobe, subdivisions of the vermis, and the lobules. Due to the number of labels, the hierarchy of labels, the number of algorithms, and the two cohorts, we have restricted our analyses to the Dice measure of overlap. Under these conditions, machine learning based methods provide a collection of strategies that are efficient and deliver parcellations of a high standard across both cohorts, surpassing previous work in the area. In conjunction with the rank-sum computation, we identified an overall winning method.

AB - The human cerebellum plays an essential role in motor control, is involved in cognitive function (i.e., attention, working memory, and language), and helps to regulate emotional responses. Quantitative in-vivo assessment of the cerebellum is important in the study of several neurological diseases including cerebellar ataxia, autism, and schizophrenia. Different structural subdivisions of the cerebellum have been shown to correlate with differing pathologies. To further understand these pathologies, it is helpful to automatically parcellate the cerebellum at the highest fidelity possible. In this paper, we coordinated with colleagues around the world to evaluate automated cerebellum parcellation algorithms on two clinical cohorts showing that the cerebellum can be parcellated to a high accuracy by newer methods. We characterize these various methods at four hierarchical levels: coarse (i.e., whole cerebellum and gross structures), lobe, subdivisions of the vermis, and the lobules. Due to the number of labels, the hierarchy of labels, the number of algorithms, and the two cohorts, we have restricted our analyses to the Dice measure of overlap. Under these conditions, machine learning based methods provide a collection of strategies that are efficient and deliver parcellations of a high standard across both cohorts, surpassing previous work in the area. In conjunction with the rank-sum computation, we identified an overall winning method.

KW - Attention deficit hyperactivity disorder

KW - Autism

KW - Cerebellar ataxia

KW - Magnetic resonance imaging

UR - http://www.scopus.com/inward/record.url?scp=85051711072&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2018.08.003

DO - 10.1016/j.neuroimage.2018.08.003

M3 - Journal article

C2 - 30099076

AN - SCOPUS:85051711072

VL - 183

SP - 150

EP - 172

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -