A system approach for closed-loop assessment of neuro-visual function based on convolutional neural network analysis of EEG signals
© 2020 SPIE. We propose a generalized, modular, closed-loop system for objective assessment of human visual parameters. Our system presents periodical visual stimuli to the patient's field of view and analyses the consequent evoked brain potentials elicited in the occipital lobe and recorded th...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
SPIE
2021
|
| Online Access: | https://hdl.handle.net/1721.1/136990 |
| _version_ | 1826204480812613632 |
|---|---|
| author | Stock, Simon C. Armengol-Urpi, Alexandre Kovacs, Balint Maier, Heiko Gerdes, Marius Stork, Wilhelm Sarma, Sanjay E. |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Stock, Simon C. Armengol-Urpi, Alexandre Kovacs, Balint Maier, Heiko Gerdes, Marius Stork, Wilhelm Sarma, Sanjay E. |
| author_sort | Stock, Simon C. |
| collection | MIT |
| description | © 2020 SPIE. We propose a generalized, modular, closed-loop system for objective assessment of human visual parameters. Our system presents periodical visual stimuli to the patient's field of view and analyses the consequent evoked brain potentials elicited in the occipital lobe and recorded through EEG. The analysis of the monitored EEG data is performed in an end-to-end fashion by a convolutional neural network (CNN). We propose a novel CNN architecture for EEG signal analysis that can be trained utilizing the benefits of multi-task learning. The closedloop attribute of our system allows for a real-time adaptation of the subsequent stimuli to further examine a potentially damaged area or increase the granularity of the exploration. Interchangeability is provided in terms of software modules, stimulus type, visual hardware, EEG acquisition device and EEG electrodes. Initially, the system is designed to monitor visual field loss originating from glaucoma or damage to the optic nerve using a virtual reality (VR) headset for the stimuli presentation. The modular architecture of our system paves the way for the assessment and monitoring of other neuro-visual functions. |
| first_indexed | 2024-09-23T12:56:16Z |
| format | Article |
| id | mit-1721.1/136990 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T12:56:16Z |
| publishDate | 2021 |
| publisher | SPIE |
| record_format | dspace |
| spelling | mit-1721.1/1369902023-04-10T19:41:32Z A system approach for closed-loop assessment of neuro-visual function based on convolutional neural network analysis of EEG signals Stock, Simon C. Armengol-Urpi, Alexandre Kovacs, Balint Maier, Heiko Gerdes, Marius Stork, Wilhelm Sarma, Sanjay E. Massachusetts Institute of Technology. Department of Mechanical Engineering © 2020 SPIE. We propose a generalized, modular, closed-loop system for objective assessment of human visual parameters. Our system presents periodical visual stimuli to the patient's field of view and analyses the consequent evoked brain potentials elicited in the occipital lobe and recorded through EEG. The analysis of the monitored EEG data is performed in an end-to-end fashion by a convolutional neural network (CNN). We propose a novel CNN architecture for EEG signal analysis that can be trained utilizing the benefits of multi-task learning. The closedloop attribute of our system allows for a real-time adaptation of the subsequent stimuli to further examine a potentially damaged area or increase the granularity of the exploration. Interchangeability is provided in terms of software modules, stimulus type, visual hardware, EEG acquisition device and EEG electrodes. Initially, the system is designed to monitor visual field loss originating from glaucoma or damage to the optic nerve using a virtual reality (VR) headset for the stimuli presentation. The modular architecture of our system paves the way for the assessment and monitoring of other neuro-visual functions. 2021-11-01T17:22:12Z 2021-11-01T17:22:12Z 2020-04-01 2020-08-04T19:07:00Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/136990 Stock, Simon C., Armengol-Urpi, Alexandre, Kovacs, Balint, Maier, Heiko, Gerdes, Marius et al. 2020. "A system approach for closed-loop assessment of neuro-visual function based on convolutional neural network analysis of EEG signals." Proceedings of SPIE - The International Society for Optical Engineering, 11360. en 10.1117/12.2554417 Proceedings of SPIE - The International Society for Optical Engineering Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf SPIE SPIE |
| spellingShingle | Stock, Simon C. Armengol-Urpi, Alexandre Kovacs, Balint Maier, Heiko Gerdes, Marius Stork, Wilhelm Sarma, Sanjay E. A system approach for closed-loop assessment of neuro-visual function based on convolutional neural network analysis of EEG signals |
| title | A system approach for closed-loop assessment of neuro-visual function based on convolutional neural network analysis of EEG signals |
| title_full | A system approach for closed-loop assessment of neuro-visual function based on convolutional neural network analysis of EEG signals |
| title_fullStr | A system approach for closed-loop assessment of neuro-visual function based on convolutional neural network analysis of EEG signals |
| title_full_unstemmed | A system approach for closed-loop assessment of neuro-visual function based on convolutional neural network analysis of EEG signals |
| title_short | A system approach for closed-loop assessment of neuro-visual function based on convolutional neural network analysis of EEG signals |
| title_sort | system approach for closed loop assessment of neuro visual function based on convolutional neural network analysis of eeg signals |
| url | https://hdl.handle.net/1721.1/136990 |
| work_keys_str_mv | AT stocksimonc asystemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT armengolurpialexandre asystemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT kovacsbalint asystemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT maierheiko asystemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT gerdesmarius asystemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT storkwilhelm asystemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT sarmasanjaye asystemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT stocksimonc systemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT armengolurpialexandre systemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT kovacsbalint systemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT maierheiko systemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT gerdesmarius systemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT storkwilhelm systemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals AT sarmasanjaye systemapproachforclosedloopassessmentofneurovisualfunctionbasedonconvolutionalneuralnetworkanalysisofeegsignals |