Classifying Multiple Types of Hand Motions Using Electrocorticography During Intraoperative Awake Craniotomy & Seizure Monitoring Processes - Case Studies
In this work, some case studies were conducted toclassify several kinds of hand motions from electrocorticography(ECoG) signals during intraoperative awake craniotomy &extraoperative seizure monitoring processes. Four subjects (P1,P2 with intractable epilepsy during seizure monitoring and P3,P4...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2015-10-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fnins.2015.00353/full |
| _version_ | 1819041836885344256 |
|---|---|
| author | Tao eXie Dingguo eZhang Zhehan eWu Liang eChen Xiangyang eZhu |
| author_facet | Tao eXie Dingguo eZhang Zhehan eWu Liang eChen Xiangyang eZhu |
| author_sort | Tao eXie |
| collection | DOAJ |
| description | In this work, some case studies were conducted toclassify several kinds of hand motions from electrocorticography(ECoG) signals during intraoperative awake craniotomy &extraoperative seizure monitoring processes. Four subjects (P1,P2 with intractable epilepsy during seizure monitoring and P3,P4 with brain tumor during awake craniotomy) participatedin the experiments. Subjects performed three types of handmotions (Grasp, Thumb-finger motion and Index-finger motion)contralateral to the motor cortex covered with ECoG electrodes.Two methods were used for signal processing. Method I:autoregressive (AR) model with burg method was applied toextract features, and additional waveform length (WL) featurehas been considered, finally the linear discriminative analysis(LDA) was used as the classifier. Method II: stationary subspaceanalysis (SSA) was applied for data preprocessing, and thecommon spatial pattern (CSP) was used for feature extractionbefore LDA decoding process. Applying method I, the threeclassaccuracy of P1□P4 were 90.17%, 96.00%, 91.77% and92.95% respectively. For method II, the three-class accuracy ofP1□P4 were 72.00%, 93.17%, 95.22% and 90.36% respectively.This study verified the possibility of decoding multiple handmotion types during an awake craniotomy, which is the firststep towards dexterous neuroprosthetic control during surgicalimplantation, in order to verify the optimal placement of electrodes.The accuracy during awake craniotomy was comparableto results during seizure monitoring. This study also indicatedthat ECoG was a promising approach for precise identificationof eloquent cortex during awake craniotomy, and might forma promising BCI system that could benefit both patients andneurosurgeons. |
| first_indexed | 2024-12-21T09:31:20Z |
| format | Article |
| id | doaj.art-2c33fbd685b04aaf95802cc549cbef07 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-21T09:31:20Z |
| publishDate | 2015-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-2c33fbd685b04aaf95802cc549cbef072022-12-21T19:08:44ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2015-10-01910.3389/fnins.2015.00353160000Classifying Multiple Types of Hand Motions Using Electrocorticography During Intraoperative Awake Craniotomy & Seizure Monitoring Processes - Case StudiesTao eXie0Dingguo eZhang1Zhehan eWu2Liang eChen3Xiangyang eZhu4Shanghai Jiao Tong UniversityShanghai Jiao Tong UniversityHuashan Hospital, Fudan UniversityHuashan Hospital, Fudan UniversityShanghai Jiao Tong UniversityIn this work, some case studies were conducted toclassify several kinds of hand motions from electrocorticography(ECoG) signals during intraoperative awake craniotomy &extraoperative seizure monitoring processes. Four subjects (P1,P2 with intractable epilepsy during seizure monitoring and P3,P4 with brain tumor during awake craniotomy) participatedin the experiments. Subjects performed three types of handmotions (Grasp, Thumb-finger motion and Index-finger motion)contralateral to the motor cortex covered with ECoG electrodes.Two methods were used for signal processing. Method I:autoregressive (AR) model with burg method was applied toextract features, and additional waveform length (WL) featurehas been considered, finally the linear discriminative analysis(LDA) was used as the classifier. Method II: stationary subspaceanalysis (SSA) was applied for data preprocessing, and thecommon spatial pattern (CSP) was used for feature extractionbefore LDA decoding process. Applying method I, the threeclassaccuracy of P1□P4 were 90.17%, 96.00%, 91.77% and92.95% respectively. For method II, the three-class accuracy ofP1□P4 were 72.00%, 93.17%, 95.22% and 90.36% respectively.This study verified the possibility of decoding multiple handmotion types during an awake craniotomy, which is the firststep towards dexterous neuroprosthetic control during surgicalimplantation, in order to verify the optimal placement of electrodes.The accuracy during awake craniotomy was comparableto results during seizure monitoring. This study also indicatedthat ECoG was a promising approach for precise identificationof eloquent cortex during awake craniotomy, and might forma promising BCI system that could benefit both patients andneurosurgeons.http://journal.frontiersin.org/Journal/10.3389/fnins.2015.00353/fullClassificationelectrocorticography (ECoG)feature extractionbrain-computer interface (BCI)hand movements |
| spellingShingle | Tao eXie Dingguo eZhang Zhehan eWu Liang eChen Xiangyang eZhu Classifying Multiple Types of Hand Motions Using Electrocorticography During Intraoperative Awake Craniotomy & Seizure Monitoring Processes - Case Studies Frontiers in Neuroscience Classification electrocorticography (ECoG) feature extraction brain-computer interface (BCI) hand movements |
| title | Classifying Multiple Types of Hand Motions Using Electrocorticography During Intraoperative Awake Craniotomy & Seizure Monitoring Processes - Case Studies |
| title_full | Classifying Multiple Types of Hand Motions Using Electrocorticography During Intraoperative Awake Craniotomy & Seizure Monitoring Processes - Case Studies |
| title_fullStr | Classifying Multiple Types of Hand Motions Using Electrocorticography During Intraoperative Awake Craniotomy & Seizure Monitoring Processes - Case Studies |
| title_full_unstemmed | Classifying Multiple Types of Hand Motions Using Electrocorticography During Intraoperative Awake Craniotomy & Seizure Monitoring Processes - Case Studies |
| title_short | Classifying Multiple Types of Hand Motions Using Electrocorticography During Intraoperative Awake Craniotomy & Seizure Monitoring Processes - Case Studies |
| title_sort | classifying multiple types of hand motions using electrocorticography during intraoperative awake craniotomy amp seizure monitoring processes case studies |
| topic | Classification electrocorticography (ECoG) feature extraction brain-computer interface (BCI) hand movements |
| url | http://journal.frontiersin.org/Journal/10.3389/fnins.2015.00353/full |
| work_keys_str_mv | AT taoexie classifyingmultipletypesofhandmotionsusingelectrocorticographyduringintraoperativeawakecraniotomyampseizuremonitoringprocessescasestudies AT dingguoezhang classifyingmultipletypesofhandmotionsusingelectrocorticographyduringintraoperativeawakecraniotomyampseizuremonitoringprocessescasestudies AT zhehanewu classifyingmultipletypesofhandmotionsusingelectrocorticographyduringintraoperativeawakecraniotomyampseizuremonitoringprocessescasestudies AT liangechen classifyingmultipletypesofhandmotionsusingelectrocorticographyduringintraoperativeawakecraniotomyampseizuremonitoringprocessescasestudies AT xiangyangezhu classifyingmultipletypesofhandmotionsusingelectrocorticographyduringintraoperativeawakecraniotomyampseizuremonitoringprocessescasestudies |