1
|
Sujatha Ravindran A, Contreras-Vidal J. An empirical comparison of deep learning explainability approaches for EEG using simulated ground truth. Sci Rep 2023; 13:17709. [PMID: 37853010 PMCID: PMC10584975 DOI: 10.1038/s41598-023-43871-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2023] [Accepted: 09/29/2023] [Indexed: 10/20/2023] Open
Abstract
Recent advancements in machine learning and deep learning (DL) based neural decoders have significantly improved decoding capabilities using scalp electroencephalography (EEG). However, the interpretability of DL models remains an under-explored area. In this study, we compared multiple model explanation methods to identify the most suitable method for EEG and understand when some of these approaches might fail. A simulation framework was developed to evaluate the robustness and sensitivity of twelve back-propagation-based visualization methods by comparing to ground truth features. Multiple methods tested here showed reliability issues after randomizing either model weights or labels: e.g., the saliency approach, which is the most used visualization technique in EEG, was not class or model-specific. We found that DeepLift was consistently accurate as well as robust to detect the three key attributes tested here (temporal, spatial, and spectral precision). Overall, this study provides a review of model explanation methods for DL-based neural decoders and recommendations to understand when some of these methods fail and what they can capture in EEG.
Collapse
Affiliation(s)
- Akshay Sujatha Ravindran
- Noninvasive Brain-Machine Interface System Laboratory, Department of Electrical and Computer Engineering, University of Houston, Houston, 77204, USA.
- IUCRC BRAIN, University of Houston, Houston, 77204, USA.
- Alto Neuroscience, Los Altos, CA, 94022, USA.
| | - Jose Contreras-Vidal
- Noninvasive Brain-Machine Interface System Laboratory, Department of Electrical and Computer Engineering, University of Houston, Houston, 77204, USA
- IUCRC BRAIN, University of Houston, Houston, 77204, USA
| |
Collapse
|
2
|
Sujatha Ravindran A, Malaya C, John I, Francisco GE, Layne C, Contreras-Vidal JL. Decoding Neural Activity Preceding Balance Loss During Standing with a Lower-limb Exoskeleton using an Interpretable Deep Learning Model. J Neural Eng 2022; 19. [PMID: 35508113 DOI: 10.1088/1741-2552/ac6ca9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2021] [Accepted: 05/04/2022] [Indexed: 11/11/2022]
Abstract
Falls are a leading cause of death in adults 65 and older. Recent efforts to restore lower-limb function in these populations have seen an increase in the use of wearable robotic systems; however, fall prevention measures in these systems require early detection of balance loss to be effective. Prior studies have investigated whether kinematic variables contain information about an impending fall, but few have examined the potential of using electroencephalography (EEG) as a fall-predicting signal and how the brain responds to avoid a fall. To address this, we decoded neural activity in a balance perturbation task while wearing an exoskeleton. We acquired EEG, electromyography (EMG), and center of pressure (COP) data from 7 healthy participants during mechanical perturbations while standing. The timing of the perturbations was randomized in all trials. We found perturbation evoked potentials (PEP) components as early as 75-134 ms after the onset of the external perturbation, which preceded both the peak in EMG (∼ 180 ms) and the COP (∼ 350 ms). A convolutional neural network trained to predict balance perturbations from single-trial EEG had a mean F-score of 75.0 ± 4.3 %. Clustering GradCAM-based model explanations demonstrated that the model utilized components in the PEP and was not driven by artifacts. Additionally, dynamic functional connectivity results agreed with model explanations; the nodal connectivity measured using phase difference derivative was higher in the occipital-parietal region in the early stage of perturbations, before shifting to the parietal, motor, and back to the frontal-parietal channels. Continuous-time decoding of COP trajectories from EEG, using a gated recurrent unit model, achieved a mean Pearson's correlation coefficient of 0.7 ± 0.06. Overall, our findings suggest that EEG signals contain short-latency neural information related to an impending fall, which may be useful for developing brain-machine interface systems for fall prevention in robotic exoskeletons.
Collapse
Affiliation(s)
- Akshay Sujatha Ravindran
- Department of Electrical and Computer Engineering, University of Houston, 4800 calhoun road, E413, Cullen Engineering Building 1, University of Houston, Houston, Texas, 77204, UNITED STATES
| | - Christopher Malaya
- Health and Human Performance, University of Houston, 4800 calhoun road, Houston, Houston, Texas, 77204, UNITED STATES
| | - Isaac John
- Health and Human Performance, University of Houston, 4800 calhoun road, Houston, Houston, Texas, 77204, UNITED STATES
| | - Gerard E Francisco
- Department of Physical Medicine and Rehabilitation, The University of Texas Health Science Center at Houston, 7000 Fannin St, Houston, Texas, 77030, UNITED STATES
| | - Charles Layne
- Health and Human Performance, University of Houston, 4800 calhoun road, Houston, Houston, Texas, 77204, UNITED STATES
| | - Jose Luis Contreras-Vidal
- Electrical and Computer Engineering, University of Houston, N308 Engineering Building I, Houston, Texas, 77204-4005, UNITED STATES
| |
Collapse
|
3
|
Cruz-Garza JG, Sujatha Ravindran A, Kopteva AE, Rivera Garza C, Contreras-Vidal JL. Characterization of the Stages of Creative Writing With Mobile EEG Using Generalized Partial Directed Coherence. Front Hum Neurosci 2021; 14:577651. [PMID: 33424562 PMCID: PMC7793781 DOI: 10.3389/fnhum.2020.577651] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2020] [Accepted: 11/10/2020] [Indexed: 11/13/2022] Open
Abstract
Two stages of the creative writing process were characterized through mobile scalp electroencephalography (EEG) in a 16-week creative writing workshop. Portable dry EEG systems (four channels: TP09, AF07, AF08, TP10) with synchronized head acceleration, video recordings, and journal entries, recorded mobile brain-body activity of Spanish heritage students. Each student's brain-body activity was recorded as they experienced spaces in Houston, Texas (“Preparation” stage), and while they worked on their creative texts (“Generation” stage). We used Generalized Partial Directed Coherence (gPDC) to compare the functional connectivity among both stages. There was a trend of higher gPDC in the Preparation stage from right temporo-parietal (TP10) to left anterior-frontal (AF07) brain scalp areas within 1–50 Hz, not reaching statistical significance. The opposite directionality was found for the Generation stage, with statistical significant differences (p < 0.05) restricted to the delta band (1–4 Hz). There was statistically higher gPDC observed for the inter-hemispheric connections AF07–AF08 in the delta and theta bands (1–8 Hz), and AF08 to TP09 in the alpha and beta (8–30 Hz) bands. The left anterior-frontal (AF07) recordings showed higher power localized to the gamma band (32–50 Hz) for the Generation stage. An ancillary analysis of Sample Entropy did not show significant difference. The information transfer from anterior-frontal to temporal-parietal areas of the scalp may reflect multisensory interpretation during the Preparation stage, while brain signals originating at temporal-parietal toward frontal locations during the Generation stage may reflect the final decision making process to translate the multisensory experience into a creative text.
Collapse
Affiliation(s)
- Jesus G Cruz-Garza
- Laboratory for Non-Invasive Brain-Machine Interface Systems, NSF IUCRC BRAIN, University of Houston, Houston, TX, United States
| | - Akshay Sujatha Ravindran
- Laboratory for Non-Invasive Brain-Machine Interface Systems, NSF IUCRC BRAIN, University of Houston, Houston, TX, United States
| | - Anastasiya E Kopteva
- Laboratory for Non-Invasive Brain-Machine Interface Systems, NSF IUCRC BRAIN, University of Houston, Houston, TX, United States
| | - Cristina Rivera Garza
- Laboratory for Non-Invasive Brain-Machine Interface Systems, NSF IUCRC BRAIN, University of Houston, Houston, TX, United States.,Department of Hispanic Studies, University of Houston, Houston, TX, United States
| | - Jose L Contreras-Vidal
- Laboratory for Non-Invasive Brain-Machine Interface Systems, NSF IUCRC BRAIN, University of Houston, Houston, TX, United States
| |
Collapse
|
4
|
Paek AY, Brantley JA, Sujatha Ravindran A, Nathan K, He Y, Eguren D, Cruz-Garza JG, Nakagome S, Wickramasuriya DS, Chang J, Rashed-Al-Mahfuz M, Amin MR, Bhagat NA, Contreras-Vidal JL. A Roadmap Towards Standards for Neurally Controlled End Effectors. IEEE Open J Eng Med Biol 2021; 2:84-90. [PMID: 35402986 PMCID: PMC8979628 DOI: 10.1109/ojemb.2021.3059161] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2020] [Revised: 12/24/2020] [Accepted: 02/09/2021] [Indexed: 12/02/2022] Open
Abstract
The control and manipulation of various types of end effectors such as powered exoskeletons, prostheses, and ‘neural’ cursors by brain-machine interface (BMI) systems has been the target of many research projects. A seamless “plug and play” interface between any BMI and end effector is desired, wherein similar user's intent cause similar end effectors to behave identically. This report is based on the outcomes of an IEEE Standards Association Industry Connections working group on End Effectors for Brain-Machine Interfacing that convened to identify and address gaps in the existing standards for BMI-based solutions with a focus on the end-effector component. A roadmap towards standardization of end effectors for BMI systems is discussed by identifying current device standards that are applicable for end effectors. While current standards address basic electrical and mechanical safety, and to some extent, performance requirements, several gaps exist pertaining to unified terminologies, data communication protocols, patient safety and risk mitigation.
Collapse
Affiliation(s)
| | - Justin A Brantley
- University of Houston Houston TX 77204 USA
- Department of BioengineeringUniversity of Pennsylvania Philadelphia PA 19104 USA
| | | | | | | | | | - Jesus G Cruz-Garza
- University of Houston Houston TX 77204 USA
- Department of Design and Environmental AnalysisCornell University Ithaca NY 14853 USA
| | | | | | | | - Md Rashed-Al-Mahfuz
- University of Houston Houston TX 77204 USA
- Department of Computer Science and EngineeringUniversity of Rajshahi Rajshahi 6205 Bangladesh
| | | | - Nikunj A Bhagat
- University of Houston Houston TX 77204 USA
- Feinstein Institutes for Medical Research Manhasset NY 11030 USA
| | | |
Collapse
|
5
|
Nakagome S, Luu TP, He Y, Ravindran AS, Contreras-Vidal JL. An empirical comparison of neural networks and machine learning algorithms for EEG gait decoding. Sci Rep 2020; 10:4372. [PMID: 32152333 PMCID: PMC7062700 DOI: 10.1038/s41598-020-60932-4] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2019] [Accepted: 02/03/2020] [Indexed: 11/09/2022] Open
Abstract
Previous studies of Brain Computer Interfaces (BCI) based on scalp electroencephalography (EEG) have demonstrated the feasibility of decoding kinematics for lower limb movements during walking. In this computational study, we investigated offline decoding analysis with different models and conditions to assess how they influence the performance and stability of the decoder. Specifically, we conducted three computational decoding experiments that investigated decoding accuracy: (1) based on delta band time-domain features, (2) when downsampling data, (3) of different frequency band features. In each experiment, eight different decoder algorithms were compared including the current state-of-the-art. Different tap sizes (sample window sizes) were also evaluated for a real-time applicability assessment. A feature of importance analysis was conducted to ascertain which features were most relevant for decoding; moreover, the stability to perturbations was assessed to quantify the robustness of the methods. Results indicated that generally the Gated Recurrent Unit (GRU) and Quasi Recurrent Neural Network (QRNN) outperformed other methods in terms of decoding accuracy and stability. Previous state-of-the-art Unscented Kalman Filter (UKF) still outperformed other decoders when using smaller tap sizes, with fast convergence in performance, but occurred at a cost to noise vulnerability. Downsampling and the inclusion of other frequency band features yielded overall improvement in performance. The results suggest that neural network-based decoders with downsampling or a wide range of frequency band features could not only improve decoder performance but also robustness with applications for stable use of BCIs.
Collapse
Affiliation(s)
- Sho Nakagome
- Non-Invasive Brain Machine Interface Laboratory, Electrical and Computer Engineering Department, Houston, 77004, USA
| | - Trieu Phat Luu
- Non-Invasive Brain Machine Interface Laboratory, Electrical and Computer Engineering Department, Houston, 77004, USA
| | - Yongtian He
- Non-Invasive Brain Machine Interface Laboratory, Electrical and Computer Engineering Department, Houston, 77004, USA
| | - Akshay Sujatha Ravindran
- Non-Invasive Brain Machine Interface Laboratory, Electrical and Computer Engineering Department, Houston, 77004, USA
| | - Jose L Contreras-Vidal
- Non-Invasive Brain Machine Interface Laboratory, Electrical and Computer Engineering Department, Houston, 77004, USA.
| |
Collapse
|
6
|
Sujatha Ravindran A, Mobiny A, Cruz-Garza JG, Paek A, Kopteva A, Contreras Vidal JL. Assaying neural activity of children during video game play in public spaces: a deep learning approach. J Neural Eng 2019; 16:036028. [PMID: 30974426 DOI: 10.1088/1741-2552/ab1876] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Abstract
OBJECTIVE Understanding neural activity patterns in the developing brain remains one of the grand challenges in neuroscience. Developing neural networks are likely to be endowed with functionally important variability associated with the environmental context, age, gender, and other variables. Therefore, we conducted experiments with typically developing children in a stimulating museum setting and tested the feasibility of using deep learning techniques to help identify patterns of brain activity associated with different conditions. APPROACH A four-channel dry EEG-based Mobile brain-body imaging data of children at rest and during videogame play (VGP) was acquired at the Children's Museum of Houston. A data-driven approach based on convolutional neural networks (CNN) was used to describe underlying feature representations in the EEG and their ability to discern task and gender. The variability of the spectral features of EEG during the rest condition as a function of age was also analyzed. MAIN RESULTS Alpha power (7-13 Hz) was higher during rest whereas theta power (4-7 Hz) was higher during VGP. Beta (13-18 Hz) power was the most significant feature, higher in females, when differentiating between males and females. Using data from both temporoparietal channels to classify between VGP and rest condition, leave-one-subject-out cross-validation accuracy of 67% was obtained. Age-related changes in EEG spectral content during rest were consistent with previous developmental studies conducted in laboratory settings showing an inverse relationship between age and EEG power. SIGNIFICANCE These findings are the first to acquire, quantify and explain brain patterns observed during VGP and rest in freely behaving children in a museum setting using a deep learning framework. The study shows how deep learning can be used as a data driven approach to identify patterns in the data and explores the issues and the potential of conducting experiments involving children in a natural and engaging environment.
Collapse
|