Interpretable many-class decoding for MEG
Multivariate pattern analysis (MVPA) of Magnetoencephalography (MEG) and Electroencephalography (EEG) data is a valuable tool for understanding how the brain represents and discriminates between different stimuli. Identifying the spatial and temporal signatures of stimuli is typically a crucial outp...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1053811923005475 |
| _version_ | 1827781817249300480 |
|---|---|
| author | Richard Csaky Mats W.J. van Es Oiwi Parker Jones Mark Woolrich |
| author_facet | Richard Csaky Mats W.J. van Es Oiwi Parker Jones Mark Woolrich |
| author_sort | Richard Csaky |
| collection | DOAJ |
| description | Multivariate pattern analysis (MVPA) of Magnetoencephalography (MEG) and Electroencephalography (EEG) data is a valuable tool for understanding how the brain represents and discriminates between different stimuli. Identifying the spatial and temporal signatures of stimuli is typically a crucial output of these analyses. Such analyses are mainly performed using linear, pairwise, sliding window decoding models. These allow for relative ease of interpretation, e.g. by estimating a time-course of decoding accuracy, but have limited decoding performance. On the other hand, full epoch multiclass decoding models, commonly used for brain–computer interface (BCI) applications, can provide better decoding performance. However interpretation methods for such models have been designed with a low number of classes in mind. In this paper, we propose an approach that combines a multiclass, full epoch decoding model with supervised dimensionality reduction, while still being able to reveal the contributions of spatiotemporal and spectral features using permutation feature importance. Crucially, we introduce a way of doing supervised dimensionality reduction of input features within a neural network optimised for the classification task, improving performance substantially. We demonstrate the approach on 3 different many-class task-MEG datasets using image presentations. Our results demonstrate that this approach consistently achieves higher accuracy than the peak accuracy of a sliding window decoder while estimating the relevant spatiotemporal features in the MEG signal. |
| first_indexed | 2024-03-11T15:24:16Z |
| format | Article |
| id | doaj.art-74221dcc105844a083df8af6f5458a95 |
| institution | Directory Open Access Journal |
| issn | 1095-9572 |
| language | English |
| last_indexed | 2024-03-11T15:24:16Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj.art-74221dcc105844a083df8af6f5458a952023-10-28T05:06:47ZengElsevierNeuroImage1095-95722023-11-01282120396Interpretable many-class decoding for MEGRichard Csaky0Mats W.J. van Es1Oiwi Parker Jones2Mark Woolrich3Oxford Centre for Human Brain Activity, Department of Psychiatry, University of Oxford, OX3 7JX, Oxford, UK; Wellcome Centre for Integrative Neuroimaging, OX3 9DU, Oxford, UK; Christ Church, OX1 1DP, Oxford, UK; Corresponding author at: Oxford Centre for Human Brain Activity, Department of Psychiatry, University of Oxford, OX3 7JX, Oxford, UK.Oxford Centre for Human Brain Activity, Department of Psychiatry, University of Oxford, OX3 7JX, Oxford, UK; Wellcome Centre for Integrative Neuroimaging, OX3 9DU, Oxford, UKWellcome Centre for Integrative Neuroimaging, OX3 9DU, Oxford, UK; Department of Engineering Science, University of Oxford, OX1 3PJ, Oxford, UK; Jesus College, OX1 3DW, Oxford, UKOxford Centre for Human Brain Activity, Department of Psychiatry, University of Oxford, OX3 7JX, Oxford, UK; Wellcome Centre for Integrative Neuroimaging, OX3 9DU, Oxford, UKMultivariate pattern analysis (MVPA) of Magnetoencephalography (MEG) and Electroencephalography (EEG) data is a valuable tool for understanding how the brain represents and discriminates between different stimuli. Identifying the spatial and temporal signatures of stimuli is typically a crucial output of these analyses. Such analyses are mainly performed using linear, pairwise, sliding window decoding models. These allow for relative ease of interpretation, e.g. by estimating a time-course of decoding accuracy, but have limited decoding performance. On the other hand, full epoch multiclass decoding models, commonly used for brain–computer interface (BCI) applications, can provide better decoding performance. However interpretation methods for such models have been designed with a low number of classes in mind. In this paper, we propose an approach that combines a multiclass, full epoch decoding model with supervised dimensionality reduction, while still being able to reveal the contributions of spatiotemporal and spectral features using permutation feature importance. Crucially, we introduce a way of doing supervised dimensionality reduction of input features within a neural network optimised for the classification task, improving performance substantially. We demonstrate the approach on 3 different many-class task-MEG datasets using image presentations. Our results demonstrate that this approach consistently achieves higher accuracy than the peak accuracy of a sliding window decoder while estimating the relevant spatiotemporal features in the MEG signal.http://www.sciencedirect.com/science/article/pii/S1053811923005475MEGNeuroimagingDecodingMachine learningPermutation feature importance |
| spellingShingle | Richard Csaky Mats W.J. van Es Oiwi Parker Jones Mark Woolrich Interpretable many-class decoding for MEG NeuroImage MEG Neuroimaging Decoding Machine learning Permutation feature importance |
| title | Interpretable many-class decoding for MEG |
| title_full | Interpretable many-class decoding for MEG |
| title_fullStr | Interpretable many-class decoding for MEG |
| title_full_unstemmed | Interpretable many-class decoding for MEG |
| title_short | Interpretable many-class decoding for MEG |
| title_sort | interpretable many class decoding for meg |
| topic | MEG Neuroimaging Decoding Machine learning Permutation feature importance |
| url | http://www.sciencedirect.com/science/article/pii/S1053811923005475 |
| work_keys_str_mv | AT richardcsaky interpretablemanyclassdecodingformeg AT matswjvanes interpretablemanyclassdecodingformeg AT oiwiparkerjones interpretablemanyclassdecodingformeg AT markwoolrich interpretablemanyclassdecodingformeg |