1
|
Levett JJ, Elkaim LM, Niazi F, Weber MH, Iorio-Morin C, Bonizzato M, Weil AG. Invasive Brain Computer Interface for Motor Restoration in Spinal Cord Injury: A Systematic Review. Neuromodulation 2024; 27:597-603. [PMID: 37943244 DOI: 10.1016/j.neurom.2023.10.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2023] [Revised: 09/10/2023] [Accepted: 10/09/2023] [Indexed: 11/10/2023]
Abstract
STUDY DESIGN Systematic review of the literature. OBJECTIVES In recent years, brain-computer interface (BCI) has emerged as a potential treatment for patients with spinal cord injury (SCI). This is the first systematic review of the literature on invasive closed-loop BCI technologies for the treatment of SCI in humans. MATERIALS AND METHODS A comprehensive search of PubMed MEDLINE, Web of Science, and Ovid EMBASE was conducted following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. RESULTS Of 8316 articles collected, 19 studies met all the inclusion criteria. Data from 21 patients were extracted from these studies. All patients sustained a cervical SCI and were treated using either a BCI with intracortical microelectrode arrays (n = 18, 85.7%) or electrocorticography (n = 3, 14.3%). To decode these neural signals, machine learning and statistical models were used: support vector machine in eight patients (38.1%), linear estimator in seven patients (33.3%), Hidden Markov Model in three patients (14.3%), and other in three patients (14.3%). As the outputs, ten patients (47.6%) underwent noninvasive functional electrical stimulation (FES) with a cuff; one (4.8%) had an invasive FES with percutaneous stimulation, and ten (47.6%) used an external device (neuroprosthesis or virtual avatar). Motor function was restored in all patients for each assigned task. Clinical outcome measures were heterogeneous across all studies. CONCLUSIONS Invasive techniques of BCI show promise for the treatment of SCI, but there is currently no technology that can restore complete functional autonomy in patients with SCI. The current techniques and outcomes of BCI vary greatly. Because invasive BCIs are still in the early stages of development, further clinical studies should be conducted to optimize the prognosis for patients with SCI.
Collapse
Affiliation(s)
- Jordan J Levett
- Faculty of Medicine, University of Montreal, Montreal, Quebec, Canada
| | - Lior M Elkaim
- Department of Neurology and Neurosurgery, McGill University, Montreal, Quebec, Canada
| | - Farbod Niazi
- Faculty of Medicine, University of Montreal, Montreal, Quebec, Canada
| | - Michael H Weber
- Department of Orthopaedic Surgery, McGill University, Montreal, Quebec, Canada
| | | | - Marco Bonizzato
- Department of Electrical Engineering and Institute of Biomedical Engineering, Polytechnique Montréal, Montreal, Quebec, Canada; Department of Neuroscience and Centre interdisciplinaire sur le cerveau et l'apprentissage, University of Montreal, Montreal, Quebec, Canada
| | - Alexander G Weil
- Division of Neurosurgery, St-Justine University Hospital, Montreal, Quebec, Canada.
| |
Collapse
|
3
|
Lorach H, Galvez A, Spagnolo V, Martel F, Karakas S, Intering N, Vat M, Faivre O, Harte C, Komi S, Ravier J, Collin T, Coquoz L, Sakr I, Baaklini E, Hernandez-Charpak SD, Dumont G, Buschman R, Buse N, Denison T, van Nes I, Asboth L, Watrin A, Struber L, Sauter-Starace F, Langar L, Auboiroux V, Carda S, Chabardes S, Aksenova T, Demesmaeker R, Charvet G, Bloch J, Courtine G. Walking naturally after spinal cord injury using a brain-spine interface. Nature 2023; 618:126-133. [PMID: 37225984 PMCID: PMC10232367 DOI: 10.1038/s41586-023-06094-5] [Citation(s) in RCA: 78] [Impact Index Per Article: 78.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2022] [Accepted: 04/17/2023] [Indexed: 05/26/2023]
Abstract
A spinal cord injury interrupts the communication between the brain and the region of the spinal cord that produces walking, leading to paralysis1,2. Here, we restored this communication with a digital bridge between the brain and spinal cord that enabled an individual with chronic tetraplegia to stand and walk naturally in community settings. This brain-spine interface (BSI) consists of fully implanted recording and stimulation systems that establish a direct link between cortical signals3 and the analogue modulation of epidural electrical stimulation targeting the spinal cord regions involved in the production of walking4-6. A highly reliable BSI is calibrated within a few minutes. This reliability has remained stable over one year, including during independent use at home. The participant reports that the BSI enables natural control over the movements of his legs to stand, walk, climb stairs and even traverse complex terrains. Moreover, neurorehabilitation supported by the BSI improved neurological recovery. The participant regained the ability to walk with crutches overground even when the BSI was switched off. This digital bridge establishes a framework to restore natural control of movement after paralysis.
Collapse
Affiliation(s)
- Henri Lorach
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Andrea Galvez
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Valeria Spagnolo
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Felix Martel
- Univ. Grenoble Alpes, CEA, LETI, Clinatec, Grenoble, France
| | - Serpil Karakas
- Univ. Grenoble Alpes, CEA, LETI, Clinatec, Grenoble, France
| | - Nadine Intering
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Molywan Vat
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Olivier Faivre
- Univ. Grenoble Alpes, CEA, LETI, Clinatec, Grenoble, France
| | - Cathal Harte
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Salif Komi
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Jimmy Ravier
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Thibault Collin
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Laure Coquoz
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Icare Sakr
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Edeny Baaklini
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Sergio Daniel Hernandez-Charpak
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | - Gregory Dumont
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | | | | | - Tim Denison
- Medtronic, Minneapolis, MN, USA
- Department of Engineering Science, University of Oxford, Oxford, UK
| | - Ilse van Nes
- Department of Rehabilitation, Sint Maartenskliniek, Nijmegen, the Netherlands
| | - Leonie Asboth
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | | | - Lucas Struber
- Univ. Grenoble Alpes, CEA, LETI, Clinatec, Grenoble, France
| | | | - Lilia Langar
- Univ. Grenoble Alpes, CHU Grenoble Alpes, Clinatec, Grenoble, France
| | | | - Stefano Carda
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
| | - Stephan Chabardes
- Univ. Grenoble Alpes, CEA, LETI, Clinatec, Grenoble, France
- Univ. Grenoble Alpes, CHU Grenoble Alpes, Clinatec, Grenoble, France
| | | | - Robin Demesmaeker
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland
| | | | - Jocelyne Bloch
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland.
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland.
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland.
| | - Grégoire Courtine
- NeuroX Institute, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland.
- Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland.
- NeuroRestore, Defitech Center for Interventional Neurotherapies, EPFL/CHUV/UNIL, Lausanne, Switzerland.
| |
Collapse
|
5
|
Śliwowski M, Martin M, Souloumiac A, Blanchart P, Aksenova T. Impact of dataset size and long-term ECoG-based BCI usage on deep learning decoders performance. Front Hum Neurosci 2023; 17:1111645. [PMID: 37007675 PMCID: PMC10061076 DOI: 10.3389/fnhum.2023.1111645] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2022] [Accepted: 02/27/2023] [Indexed: 03/18/2023] Open
Abstract
IntroductionIn brain-computer interfaces (BCI) research, recording data is time-consuming and expensive, which limits access to big datasets. This may influence the BCI system performance as machine learning methods depend strongly on the training dataset size. Important questions arise: taking into account neuronal signal characteristics (e.g., non-stationarity), can we achieve higher decoding performance with more data to train decoders? What is the perspective for further improvement with time in the case of long-term BCI studies? In this study, we investigated the impact of long-term recordings on motor imagery decoding from two main perspectives: model requirements regarding dataset size and potential for patient adaptation.MethodsWe evaluated the multilinear model and two deep learning (DL) models on a long-term BCI & Tetraplegia (ClinicalTrials.gov identifier: NCT02550522) clinical trial dataset containing 43 sessions of ECoG recordings performed with a tetraplegic patient. In the experiment, a participant executed 3D virtual hand translation using motor imagery patterns. We designed multiple computational experiments in which training datasets were increased or translated to investigate the relationship between models' performance and different factors influencing recordings.ResultsOur results showed that DL decoders showed similar requirements regarding the dataset size compared to the multilinear model while demonstrating higher decoding performance. Moreover, high decoding performance was obtained with relatively small datasets recorded later in the experiment, suggesting motor imagery patterns improvement and patient adaptation during the long-term experiment. Finally, we proposed UMAP embeddings and local intrinsic dimensionality as a way to visualize the data and potentially evaluate data quality.DiscussionDL-based decoding is a prospective approach in BCI which may be efficiently applied with real-life dataset size. Patient-decoder co-adaptation is an important factor to consider in long-term clinical BCI.
Collapse
Affiliation(s)
- Maciej Śliwowski
- Université Grenoble Alpes, CEA, LETI, Clinatec, Grenoble, France
- Université Paris-Saclay, CEA, List, Palaiseau, France
| | - Matthieu Martin
- Université Grenoble Alpes, CEA, LETI, Clinatec, Grenoble, France
| | | | | | - Tetiana Aksenova
- Université Grenoble Alpes, CEA, LETI, Clinatec, Grenoble, France
- *Correspondence: Tetiana Aksenova
| |
Collapse
|
8
|
Vansteensel MJ, Branco MP, Leinders S, Freudenburg ZF, Schippers A, Geukes SH, Gaytant MA, Gosselaar PH, Aarnoutse EJ, Ramsey NF. Methodological Recommendations for Studies on the Daily Life Implementation of Implantable Communication-Brain-Computer Interfaces for Individuals With Locked-in Syndrome. Neurorehabil Neural Repair 2022; 36:666-677. [PMID: 36124975 DOI: 10.1177/15459683221125788] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Implantable brain-computer interfaces (BCIs) promise to be a viable means to restore communication in individuals with locked-in syndrome (LIS). In 2016, we presented the world-first fully implantable BCI system that uses subdural electrocorticography electrodes to record brain signals and a subcutaneous amplifier to transmit the signals to the outside world, and that enabled an individual with LIS to communicate via a tablet computer by selecting icons in spelling software. For future clinical implementation of implantable communication-BCIs, however, much work is still needed, for example, to validate these systems in daily life settings with more participants, and to improve the speed of communication. We believe the design and execution of future studies on these and other topics may benefit from the experience we have gained. Therefore, based on relevant literature and our own experiences, we here provide an overview of procedures, as well as recommendations, for recruitment, screening, inclusion, imaging, hospital admission, implantation, training, and support of participants with LIS, for studies on daily life implementation of implantable communication-BCIs. With this article, we not only aim to inform the BCI community about important topics of concern, but also hope to contribute to improved methodological standardization of implantable BCI research.
Collapse
Affiliation(s)
- Mariska J Vansteensel
- UMC Utrecht Brain Center, Department of Neurology and Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Mariana P Branco
- UMC Utrecht Brain Center, Department of Neurology and Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Sacha Leinders
- UMC Utrecht Brain Center, Department of Neurology and Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Zac F Freudenburg
- UMC Utrecht Brain Center, Department of Neurology and Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Anouck Schippers
- UMC Utrecht Brain Center, Department of Neurology and Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Simon H Geukes
- UMC Utrecht Brain Center, Department of Neurology and Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Michael A Gaytant
- Department of Pulmonary Diseases/Home Mechanical Ventilation, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Peter H Gosselaar
- UMC Utrecht Brain Center, Department of Neurology and Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Erik J Aarnoutse
- UMC Utrecht Brain Center, Department of Neurology and Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Nick F Ramsey
- UMC Utrecht Brain Center, Department of Neurology and Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands
| |
Collapse
|
9
|
Śliwowski M, Martin M, Souloumiac A, Blanchart P, Aksenova T. Decoding ECoG signal into 3D hand translation using deep learning. J Neural Eng 2022; 19. [PMID: 35287119 DOI: 10.1088/1741-2552/ac5d69] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/08/2021] [Accepted: 03/14/2022] [Indexed: 12/29/2022]
Abstract
Objective.Motor brain-computer interfaces (BCIs) are a promising technology that may enable motor-impaired people to interact with their environment. BCIs would potentially compensate for arm and hand function loss, which is the top priority for individuals with tetraplegia. Designing real-time and accurate BCI is crucial to make such devices useful, safe, and easy to use by patients in a real-life environment. Electrocorticography (ECoG)-based BCIs emerge as a good compromise between invasiveness of the recording device and good spatial and temporal resolution of the recorded signal. However, most ECoG signal decoders used to predict continuous hand movements are linear models. These models have a limited representational capacity and may fail to capture the relationship between ECoG signal features and continuous hand movements. Deep learning (DL) models, which are state-of-the-art in many problems, could be a solution to better capture this relationship.Approach.In this study, we tested several DL-based architectures to predict imagined 3D continuous hand translation using time-frequency features extracted from ECoG signals. The dataset used in the analysis is a part of a long-term clinical trial (ClinicalTrials.gov identifier: NCT02550522) and was acquired during a closed-loop experiment with a tetraplegic subject. The proposed architectures include multilayer perceptron, convolutional neural networks (CNNs), and long short-term memory networks (LSTM). The accuracy of the DL-based and multilinear models was compared offline using cosine similarity.Main results.Our results show that CNN-based architectures outperform the current state-of-the-art multilinear model. The best architecture exploited the spatial correlation between neighboring electrodes with CNN and benefited from the sequential character of the desired hand trajectory by using LSTMs. Overall, DL increased the average cosine similarity, compared to the multilinear model, by up to 60%, from 0.189 to 0.302 and from 0.157 to 0.249 for the left and right hand, respectively.Significance.This study shows that DL-based models could increase the accuracy of BCI systems in the case of 3D hand translation prediction in a tetraplegic subject.
Collapse
Affiliation(s)
- Maciej Śliwowski
- Université Grenoble Alpes, CEA, LETI, Clinatec, F-38000 Grenoble, France.,Université Paris-Saclay, CEA, List, F-91120 Palaiseau, France
| | - Matthieu Martin
- Université Grenoble Alpes, CEA, LETI, Clinatec, F-38000 Grenoble, France
| | | | | | - Tetiana Aksenova
- Université Grenoble Alpes, CEA, LETI, Clinatec, F-38000 Grenoble, France
| |
Collapse
|