Comparing fully automated state-of-the-art cerebellum parcellation from magnetic resonance images
Comparing fully automated state-of-the-art cerebellum parcellation from magnetic resonance images
Carass, Aaron and Cuzzocreo, Jennifer L. and Han, Shuo and Hernandez-Castillo, Carlos R. and Rasser, Paul E. and Ganz, Melanie and Beliveau, Vincent and Dolz, Jose and Ben Ayed, Ismail and Desrosiers, Christian and Thyreau, Benjamin and Romero, José E. and Coupé, Pierrick and Manjón, José V. and Fonov, Vladimir S. and Collins, D. Louis and Ying, Sarah H. and Onyike, Chiadi U. and Crocetti, Deana and Landman, Bennett A. and Mostofsky, Stewart H. and Thompson, Paul M. and Prince, Jerry L.
NeuroImage 2018
Abstract : 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.
