Unraveling somatotopic organization in the human brain using machine learning and adaptive supervoxel-based parcellations

In addition to the well-established somatotopy in the pre- and post-central gyrus, there is now strong evidence that somatotopic organization is evident across other regions in the sensorimotor network. This raises several experimental questions: To what extent is activity in the sensorimotor networ...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kyle B. See, David J. Arpin, David E. Vaillancourt, Ruogu Fang, Stephen A. Coombes
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/c072346fe3664048beaf34da64f4277d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c072346fe3664048beaf34da64f4277d
record_format	dspace
spelling	oai:doaj.org-article:c072346fe3664048beaf34da64f4277d2021-11-20T04:56:08ZUnraveling somatotopic organization in the human brain using machine learning and adaptive supervoxel-based parcellations1095-957210.1016/j.neuroimage.2021.118710https://doaj.org/article/c072346fe3664048beaf34da64f4277d2021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1053811921009824https://doaj.org/toc/1095-9572In addition to the well-established somatotopy in the pre- and post-central gyrus, there is now strong evidence that somatotopic organization is evident across other regions in the sensorimotor network. This raises several experimental questions: To what extent is activity in the sensorimotor network effector-dependent and effector-independent? How important is the sensorimotor cortex when predicting the motor effector? Is there redundancy in the distributed somatotopically organized network such that removing one region has little impact on classification accuracy? To answer these questions, we developed a novel experimental approach. fMRI data were collected while human subjects performed a precisely controlled force generation task separately with their hand, foot, and mouth. We used a simple linear iterative clustering (SLIC) algorithm to segment whole-brain beta coefficient maps to build an adaptive brain parcellation and then classified effectors using extreme gradient boosting (XGBoost) based on parcellations at various spatial resolutions. This allowed us to understand how data-driven adaptive brain parcellation granularity altered classification accuracy. Results revealed effector-dependent activity in regions of the post-central gyrus, precentral gyrus, and paracentral lobule. SMA, regions of the inferior and superior parietal lobule, and cerebellum each contained effector-dependent and effector-independent representations. Machine learning analyses showed that increasing the spatial resolution of the data-driven model increased classification accuracy, which reached 94% with 1755 supervoxels. Our SLIC-based supervoxel parcellation outperformed classification analyses using established brain templates and random simulations. Occlusion experiments further demonstrated redundancy across the sensorimotor network when classifying effectors. Our observations extend our understanding of effector-dependent and effector-independent organization within the human brain and provide new insight into the functional neuroanatomy required to predict the motor effector used in a motor control task.Kyle B. SeeDavid J. ArpinDavid E. VaillancourtRuogu FangStephen A. CoombesElsevierarticleNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENNeuroImage, Vol 245, Iss , Pp 118710- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Kyle B. See David J. Arpin David E. Vaillancourt Ruogu Fang Stephen A. Coombes Unraveling somatotopic organization in the human brain using machine learning and adaptive supervoxel-based parcellations
description	In addition to the well-established somatotopy in the pre- and post-central gyrus, there is now strong evidence that somatotopic organization is evident across other regions in the sensorimotor network. This raises several experimental questions: To what extent is activity in the sensorimotor network effector-dependent and effector-independent? How important is the sensorimotor cortex when predicting the motor effector? Is there redundancy in the distributed somatotopically organized network such that removing one region has little impact on classification accuracy? To answer these questions, we developed a novel experimental approach. fMRI data were collected while human subjects performed a precisely controlled force generation task separately with their hand, foot, and mouth. We used a simple linear iterative clustering (SLIC) algorithm to segment whole-brain beta coefficient maps to build an adaptive brain parcellation and then classified effectors using extreme gradient boosting (XGBoost) based on parcellations at various spatial resolutions. This allowed us to understand how data-driven adaptive brain parcellation granularity altered classification accuracy. Results revealed effector-dependent activity in regions of the post-central gyrus, precentral gyrus, and paracentral lobule. SMA, regions of the inferior and superior parietal lobule, and cerebellum each contained effector-dependent and effector-independent representations. Machine learning analyses showed that increasing the spatial resolution of the data-driven model increased classification accuracy, which reached 94% with 1755 supervoxels. Our SLIC-based supervoxel parcellation outperformed classification analyses using established brain templates and random simulations. Occlusion experiments further demonstrated redundancy across the sensorimotor network when classifying effectors. Our observations extend our understanding of effector-dependent and effector-independent organization within the human brain and provide new insight into the functional neuroanatomy required to predict the motor effector used in a motor control task.
format	article
author	Kyle B. See David J. Arpin David E. Vaillancourt Ruogu Fang Stephen A. Coombes
author_facet	Kyle B. See David J. Arpin David E. Vaillancourt Ruogu Fang Stephen A. Coombes
author_sort	Kyle B. See
title	Unraveling somatotopic organization in the human brain using machine learning and adaptive supervoxel-based parcellations
title_short	Unraveling somatotopic organization in the human brain using machine learning and adaptive supervoxel-based parcellations
title_full	Unraveling somatotopic organization in the human brain using machine learning and adaptive supervoxel-based parcellations
title_fullStr	Unraveling somatotopic organization in the human brain using machine learning and adaptive supervoxel-based parcellations
title_full_unstemmed	Unraveling somatotopic organization in the human brain using machine learning and adaptive supervoxel-based parcellations
title_sort	unraveling somatotopic organization in the human brain using machine learning and adaptive supervoxel-based parcellations
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/c072346fe3664048beaf34da64f4277d
work_keys_str_mv	AT kylebsee unravelingsomatotopicorganizationinthehumanbrainusingmachinelearningandadaptivesupervoxelbasedparcellations AT davidjarpin unravelingsomatotopicorganizationinthehumanbrainusingmachinelearningandadaptivesupervoxelbasedparcellations AT davidevaillancourt unravelingsomatotopicorganizationinthehumanbrainusingmachinelearningandadaptivesupervoxelbasedparcellations AT ruogufang unravelingsomatotopicorganizationinthehumanbrainusingmachinelearningandadaptivesupervoxelbasedparcellations AT stephenacoombes unravelingsomatotopicorganizationinthehumanbrainusingmachinelearningandadaptivesupervoxelbasedparcellations
_version_	1718419737872957440

Unraveling somatotopic organization in the human brain using machine learning and adaptive supervoxel-based parcellations

Ejemplares similares