TY - JOUR
T1 - Decoding executed and imagined grasping movements from distributed non-motor brain areas using a Riemannian decoder
AU - Ottenhoff, Maarten C
AU - Verwoert, Maxime
AU - Goulis, Sophocles
AU - Colon, Albert J
AU - Wagner, Louis
AU - Tousseyn, Simon
AU - van Dijk, Johannes P
AU - Kubben, Pieter L
AU - Herff, Christian
N1 - Data source: Movement data and intracranial brain recordings from epileptic patients acquired on a voluntary basis at Epilepsy Center Kempenhaeghe in collaboration with Maastricht University.
PY - 2023/11/23
Y1 - 2023/11/23
N2 - Using brain activity directly as input for assistive tool control can circumventmuscular dysfunction and increase functional independence for physically impaired people. The motor cortex is commonly targeted for recordings, while growing evidence shows that there exists decodable movement-related neural activity outside of the motor cortex. Several decoding studies demonstrated significant decoding from distributed areas separately. Here, we combine information from all recorded non-motor brain areas and decode executed and imagined movements using a Riemannian decoder. We recorded neural activity from 8 epilepsy patients implanted with stereotactic-electroencephalographic electrodes (sEEG), while they performed an executed and imagined grasping tasks. Before decoding, we excluded all contacts in or adjacent to the central sulcus. The decoder extracts a low-dimensional representation of varying number of components, and classified move/no-move using a minimum-distance-to-geometric-mean Riemannian classifier. We show that executed and imagined movements can be decoded from distributed non-motor brain areas using a Riemannian decoder, reaching an area under the receiver operator characteristic of 0.83?±?0.11. Furthermore, we highlight the distributedness of the movement-related neural activity, as no single brain area is the main driver of performance. Our decoding results demonstrate a first application of a Riemannian decoder on sEEG data and show that it is able to decode from distributed brain-wide recordings outside of the motor cortex. This brief report highlights the perspective to explore motor-related neural activity beyond the motor cortex, as many areas contain decodable information.
AB - Using brain activity directly as input for assistive tool control can circumventmuscular dysfunction and increase functional independence for physically impaired people. The motor cortex is commonly targeted for recordings, while growing evidence shows that there exists decodable movement-related neural activity outside of the motor cortex. Several decoding studies demonstrated significant decoding from distributed areas separately. Here, we combine information from all recorded non-motor brain areas and decode executed and imagined movements using a Riemannian decoder. We recorded neural activity from 8 epilepsy patients implanted with stereotactic-electroencephalographic electrodes (sEEG), while they performed an executed and imagined grasping tasks. Before decoding, we excluded all contacts in or adjacent to the central sulcus. The decoder extracts a low-dimensional representation of varying number of components, and classified move/no-move using a minimum-distance-to-geometric-mean Riemannian classifier. We show that executed and imagined movements can be decoded from distributed non-motor brain areas using a Riemannian decoder, reaching an area under the receiver operator characteristic of 0.83?±?0.11. Furthermore, we highlight the distributedness of the movement-related neural activity, as no single brain area is the main driver of performance. Our decoding results demonstrate a first application of a Riemannian decoder on sEEG data and show that it is able to decode from distributed brain-wide recordings outside of the motor cortex. This brief report highlights the perspective to explore motor-related neural activity beyond the motor cortex, as many areas contain decodable information.
KW - Riemannian geometry
KW - brain-computer interfaces
KW - distributed recordings
KW - low-dimensional representation
KW - motor decoding
U2 - 10.3389/fnins.2023.1283491
DO - 10.3389/fnins.2023.1283491
M3 - Article
SN - 1662-453X
VL - 17
JO - Frontiers in Neuroscience
JF - Frontiers in Neuroscience
M1 - 1283491
ER -