Seizure detection by convolutional neural network-based analysis of scalp electroencephalography plot images
We hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze spectro-temporal features or complex, non-stationary features of EEG signals. If so, seizure detection could benefit from convolutional neural network...
Saved in:
| Published in | NeuroImage clinical Vol. 22; p. 101684 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Netherlands
Elsevier Inc
01.01.2019
Elsevier |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | We hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze spectro-temporal features or complex, non-stationary features of EEG signals. If so, seizure detection could benefit from convolutional neural networks because their visual recognition ability is comparable to that of humans. We explored image-based seizure detection by applying convolutional neural networks to long-term EEG that included epileptic seizures. After filtering, EEG data were divided into short segments based on a given time window and converted into plot EEG images, each of which was classified by convolutional neural networks as ‘seizure’ or ‘non-seizure’. These resultant labels were then used to design a clinically practical index for seizure detection. The best true positive rate was obtained using a 1-s time window. The median true positive rate of convolutional neural networks labelling by seconds was 74%, which was higher than that of commercially available seizure detection software (20% by BESA and 31% by Persyst). For practical use, the median of detected seizure rate by minutes was 100% by convolutional neural networks, which was higher than the 73.3% by BESA and 81.7% by Persyst. The false alarm of convolutional neural networks' seizure detection was issued at 0.2 per hour, which appears acceptable for clinical practice. Moreover, we demonstrated that seizure detection improved when training was performed using EEG patterns similar to those of testing data, suggesting that adding a variety of seizure patterns to the training dataset will improve our method. Thus, artificial visual recognition by convolutional neural networks allows for seizure detection, which otherwise currently relies on skillful visual inspection by expert epileptologists during clinical diagnosis.
[Display omitted]
•Artificial visual recognition of scalp EEG plot images successfully detects seizures.•CNN-based automatic detection performed better than commercial software.•Customized CNN learning using large datasets improves detection. |
|---|---|
| AbstractList | AbstractWe hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze spectro-temporal features or complex, non-stationary features of EEG signals. If so, seizure detection could benefit from convolutional neural networks because their visual recognition ability is comparable to that of humans. We explored image-based seizure detection by applying convolutional neural networks to long-term EEG that included epileptic seizures. After filtering, EEG data were divided into short segments based on a given time window and converted into plot EEG images, each of which was classified by convolutional neural networks as ‘seizure’ or ‘non-seizure’. These resultant labels were then used to design a clinically practical index for seizure detection. The best true positive rate was obtained using a 1-s time window. The median true positive rate of convolutional neural networks labelling by seconds was 74%, which was higher than that of commercially available seizure detection software (20% by BESA and 31% by Persyst). For practical use, the median of detected seizure rate by minutes was 100% by convolutional neural networks, which was higher than the 73.3% by BESA and 81.7% by Persyst. The false alarm of convolutional neural networks' seizure detection was issued at 0.2 per hour, which appears acceptable for clinical practice. Moreover, we demonstrated that seizure detection improved when training was performed using EEG patterns similar to those of testing data, suggesting that adding a variety of seizure patterns to the training dataset will improve our method. Thus, artificial visual recognition by convolutional neural networks allows for seizure detection, which otherwise currently relies on skillful visual inspection by expert epileptologists during clinical diagnosis. We hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze spectro-temporal features or complex, non-stationary features of EEG signals. If so, seizure detection could benefit from convolutional neural networks because their visual recognition ability is comparable to that of humans. We explored image-based seizure detection by applying convolutional neural networks to long-term EEG that included epileptic seizures. After filtering, EEG data were divided into short segments based on a given time window and converted into plot EEG images, each of which was classified by convolutional neural networks as 'seizure' or 'non-seizure'. These resultant labels were then used to design a clinically practical index for seizure detection. The best true positive rate was obtained using a 1-s time window. The median true positive rate of convolutional neural networks labelling by seconds was 74%, which was higher than that of commercially available seizure detection software (20% by BESA and 31% by Persyst). For practical use, the median of detected seizure rate by minutes was 100% by convolutional neural networks, which was higher than the 73.3% by BESA and 81.7% by Persyst. The false alarm of convolutional neural networks' seizure detection was issued at 0.2 per hour, which appears acceptable for clinical practice. Moreover, we demonstrated that seizure detection improved when training was performed using EEG patterns similar to those of testing data, suggesting that adding a variety of seizure patterns to the training dataset will improve our method. Thus, artificial visual recognition by convolutional neural networks allows for seizure detection, which otherwise currently relies on skillful visual inspection by expert epileptologists during clinical diagnosis.We hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze spectro-temporal features or complex, non-stationary features of EEG signals. If so, seizure detection could benefit from convolutional neural networks because their visual recognition ability is comparable to that of humans. We explored image-based seizure detection by applying convolutional neural networks to long-term EEG that included epileptic seizures. After filtering, EEG data were divided into short segments based on a given time window and converted into plot EEG images, each of which was classified by convolutional neural networks as 'seizure' or 'non-seizure'. These resultant labels were then used to design a clinically practical index for seizure detection. The best true positive rate was obtained using a 1-s time window. The median true positive rate of convolutional neural networks labelling by seconds was 74%, which was higher than that of commercially available seizure detection software (20% by BESA and 31% by Persyst). For practical use, the median of detected seizure rate by minutes was 100% by convolutional neural networks, which was higher than the 73.3% by BESA and 81.7% by Persyst. The false alarm of convolutional neural networks' seizure detection was issued at 0.2 per hour, which appears acceptable for clinical practice. Moreover, we demonstrated that seizure detection improved when training was performed using EEG patterns similar to those of testing data, suggesting that adding a variety of seizure patterns to the training dataset will improve our method. Thus, artificial visual recognition by convolutional neural networks allows for seizure detection, which otherwise currently relies on skillful visual inspection by expert epileptologists during clinical diagnosis. We hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze spectro-temporal features or complex, non-stationary features of EEG signals. If so, seizure detection could benefit from convolutional neural networks because their visual recognition ability is comparable to that of humans. We explored image-based seizure detection by applying convolutional neural networks to long-term EEG that included epileptic seizures. After filtering, EEG data were divided into short segments based on a given time window and converted into plot EEG images, each of which was classified by convolutional neural networks as ‘seizure’ or ‘non-seizure’. These resultant labels were then used to design a clinically practical index for seizure detection. The best true positive rate was obtained using a 1-s time window. The median true positive rate of convolutional neural networks labelling by seconds was 74%, which was higher than that of commercially available seizure detection software (20% by BESA and 31% by Persyst). For practical use, the median of detected seizure rate by minutes was 100% by convolutional neural networks, which was higher than the 73.3% by BESA and 81.7% by Persyst. The false alarm of convolutional neural networks' seizure detection was issued at 0.2 per hour, which appears acceptable for clinical practice. Moreover, we demonstrated that seizure detection improved when training was performed using EEG patterns similar to those of testing data, suggesting that adding a variety of seizure patterns to the training dataset will improve our method. Thus, artificial visual recognition by convolutional neural networks allows for seizure detection, which otherwise currently relies on skillful visual inspection by expert epileptologists during clinical diagnosis. [Display omitted] •Artificial visual recognition of scalp EEG plot images successfully detects seizures.•CNN-based automatic detection performed better than commercial software.•Customized CNN learning using large datasets improves detection. We hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze spectro-temporal features or complex, non-stationary features of EEG signals. If so, seizure detection could benefit from convolutional neural networks because their visual recognition ability is comparable to that of humans. We explored image-based seizure detection by applying convolutional neural networks to long-term EEG that included epileptic seizures. After filtering, EEG data were divided into short segments based on a given time window and converted into plot EEG images, each of which was classified by convolutional neural networks as 'seizure' or 'non-seizure'. These resultant labels were then used to design a clinically practical index for seizure detection. The best true positive rate was obtained using a 1-s time window. The median true positive rate of convolutional neural networks labelling by seconds was 74%, which was higher than that of commercially available seizure detection software (20% by BESA and 31% by Persyst). For practical use, the median of detected seizure rate by minutes was 100% by convolutional neural networks, which was higher than the 73.3% by BESA and 81.7% by Persyst. The false alarm of convolutional neural networks' seizure detection was issued at 0.2 per hour, which appears acceptable for clinical practice. Moreover, we demonstrated that seizure detection improved when training was performed using EEG patterns similar to those of testing data, suggesting that adding a variety of seizure patterns to the training dataset will improve our method. Thus, artificial visual recognition by convolutional neural networks allows for seizure detection, which otherwise currently relies on skillful visual inspection by expert epileptologists during clinical diagnosis. We hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze spectro-temporal features or complex, non-stationary features of EEG signals. If so, seizure detection could benefit from convolutional neural networks because their visual recognition ability is comparable to that of humans. We explored image-based seizure detection by applying convolutional neural networks to long-term EEG that included epileptic seizures. After filtering, EEG data were divided into short segments based on a given time window and converted into plot EEG images, each of which was classified by convolutional neural networks as ‘seizure’ or ‘non-seizure’. These resultant labels were then used to design a clinically practical index for seizure detection. The best true positive rate was obtained using a 1-s time window. The median true positive rate of convolutional neural networks labelling by seconds was 74%, which was higher than that of commercially available seizure detection software (20% by BESA and 31% by Persyst). For practical use, the median of detected seizure rate by minutes was 100% by convolutional neural networks, which was higher than the 73.3% by BESA and 81.7% by Persyst. The false alarm of convolutional neural networks' seizure detection was issued at 0.2 per hour, which appears acceptable for clinical practice. Moreover, we demonstrated that seizure detection improved when training was performed using EEG patterns similar to those of testing data, suggesting that adding a variety of seizure patterns to the training dataset will improve our method. Thus, artificial visual recognition by convolutional neural networks allows for seizure detection, which otherwise currently relies on skillful visual inspection by expert epileptologists during clinical diagnosis. Unlabelled Image • Artificial visual recognition of scalp EEG plot images successfully detects seizures. • CNN-based automatic detection performed better than commercial software. • Customized CNN learning using large datasets improves detection. We hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze spectro-temporal features or complex, non-stationary features of EEG signals. If so, seizure detection could benefit from convolutional neural networks because their visual recognition ability is comparable to that of humans. We explored image-based seizure detection by applying convolutional neural networks to long-term EEG that included epileptic seizures. After filtering, EEG data were divided into short segments based on a given time window and converted into plot EEG images, each of which was classified by convolutional neural networks as ‘seizure’ or ‘non-seizure’. These resultant labels were then used to design a clinically practical index for seizure detection. The best true positive rate was obtained using a 1-s time window. The median true positive rate of convolutional neural networks labelling by seconds was 74%, which was higher than that of commercially available seizure detection software (20% by BESA and 31% by Persyst). For practical use, the median of detected seizure rate by minutes was 100% by convolutional neural networks, which was higher than the 73.3% by BESA and 81.7% by Persyst. The false alarm of convolutional neural networks' seizure detection was issued at 0.2 per hour, which appears acceptable for clinical practice. Moreover, we demonstrated that seizure detection improved when training was performed using EEG patterns similar to those of testing data, suggesting that adding a variety of seizure patterns to the training dataset will improve our method. Thus, artificial visual recognition by convolutional neural networks allows for seizure detection, which otherwise currently relies on skillful visual inspection by expert epileptologists during clinical diagnosis. Keywords: Convolutional neural networks, Seizure detection, Deep learning, Scalp electroencephalogram, Epileptic seizure |
| ArticleNumber | 101684 |
| Author | Takahashi, Hirokazu Shinozaki, Takashi Matsuo, Takeshi Emami, Ali Kunii, Naoto Kawai, Kensuke |
| AuthorAffiliation | e Department of Neurosurgery, Jichi Medical University, Japan c Tokyo Metropolitan Neurological Hospital, Japan b Department of Neurosurgery, Graduate School of Medicine, The University of Tokyo, Japan d CiNet, National Institute of Information and Communications Technology, Japan a Research Center for Advanced Science and Technology, The University of Tokyo, Japan |
| AuthorAffiliation_xml | – name: d CiNet, National Institute of Information and Communications Technology, Japan – name: b Department of Neurosurgery, Graduate School of Medicine, The University of Tokyo, Japan – name: c Tokyo Metropolitan Neurological Hospital, Japan – name: a Research Center for Advanced Science and Technology, The University of Tokyo, Japan – name: e Department of Neurosurgery, Jichi Medical University, Japan |
| Author_xml | – sequence: 1 givenname: Ali orcidid: 0000-0002-3188-9805 surname: Emami fullname: Emami, Ali organization: Research Center for Advanced Science and Technology, The University of Tokyo, Japan – sequence: 2 givenname: Naoto surname: Kunii fullname: Kunii, Naoto organization: Department of Neurosurgery, Graduate School of Medicine, The University of Tokyo, Japan – sequence: 3 givenname: Takeshi surname: Matsuo fullname: Matsuo, Takeshi organization: Tokyo Metropolitan Neurological Hospital, Japan – sequence: 4 givenname: Takashi surname: Shinozaki fullname: Shinozaki, Takashi organization: CiNet, National Institute of Information and Communications Technology, Japan – sequence: 5 givenname: Kensuke surname: Kawai fullname: Kawai, Kensuke email: kenkawai-tky@umin.net organization: Department of Neurosurgery, Jichi Medical University, Japan – sequence: 6 givenname: Hirokazu surname: Takahashi fullname: Takahashi, Hirokazu email: takahashi@i.u-tokyo.ac.jp organization: Research Center for Advanced Science and Technology, The University of Tokyo, Japan |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30711680$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kk1v1DAQhiNUREvpH-CAcuSyy9jOh8MBCVV8VKrEoXAeOfZk11tvHOxk0fLrcbpb1CJRX_wxM88rz7wvs5Pe95RlrxksGbDq3WbZW-2WHFhz9yCLZ9kZ50wsWCn5yYPzaXYR4wbSkgB1Vb3ITgXULJXAWeZuyP6eAuWGRtKj9X3e7nPt-51303xVLu9pCnfb-MuH20WrIplcpcg-2pj7Lo9auSEnlwDBU69pWCvnV0EN630-OD_mdqtWFF9lzzvlIl0c9_Psx-dP3y-_Lq6_fbm6_Hi90FUB44IEVbwuOmqNaYkx0_COCARp1nUdcKipNKLVjSqhE11TmFoKZqQA04hKKHGeXR24xqsNDiGphz16ZfHuwYcVqjCm9hHWFZetZpLqhhUVMNWKFgxVqi6N5LpJrA8H1jC1WzKa-jE14xH0caS3a1z5HVairGUpEuDtERD8z4niiFsbNTmnevJTRM7qpgRZSJZS3zzU-ityP66UIA8JOvgYA3Wo7ajmMSVp65ABzl7ADc7mwNkceDBHKuX_lN7Tnyw6fp7StHaWAmpnU5Zyt7SnuPFTSDaIyDByBLyZPTdbjjUCQBQyAd7_H5CmYZ9S_wNSO-oJ |
| CitedBy_id | crossref_primary_10_1002_cnm_3573 crossref_primary_10_3390_brainsci11111530 crossref_primary_10_1002_cnm_3530 crossref_primary_10_3390_s20040969 crossref_primary_10_1016_j_cmpb_2021_106335 crossref_primary_10_1016_j_compbiomed_2020_104016 crossref_primary_10_1109_TCDS_2021_3079712 crossref_primary_10_1142_S0129065723500120 crossref_primary_10_3390_brainsci14111090 crossref_primary_10_3390_info15050256 crossref_primary_10_1109_TBME_2024_3441090 crossref_primary_10_1109_ACCESS_2024_3406332 crossref_primary_10_1098_rsos_230022 crossref_primary_10_1007_s11760_022_02164_9 crossref_primary_10_1038_s41598_022_23101_3 crossref_primary_10_1109_TNSRE_2021_3129467 crossref_primary_10_1080_03091902_2020_1791988 crossref_primary_10_3390_rs14132966 crossref_primary_10_1088_1742_6596_1577_1_012016 crossref_primary_10_53759_7669_jmc202404099 crossref_primary_10_3389_fneur_2020_00701 crossref_primary_10_1007_s11042_023_14995_w crossref_primary_10_1109_TIM_2022_3177747 crossref_primary_10_3390_s24092823 crossref_primary_10_1109_MCI_2021_3061875 crossref_primary_10_1016_j_procs_2019_09_469 crossref_primary_10_1007_s00034_024_02700_7 crossref_primary_10_1038_s41598_023_41537_z crossref_primary_10_1080_02522667_2020_1715564 crossref_primary_10_1088_1741_2552_acb089 crossref_primary_10_7887_jcns_32_128 crossref_primary_10_1109_JBHI_2022_3199206 crossref_primary_10_1155_2024_8835396 crossref_primary_10_1007_s00034_021_01686_w crossref_primary_10_3390_app13158747 crossref_primary_10_1007_s13198_022_01845_5 crossref_primary_10_1109_TII_2023_3274913 crossref_primary_10_1109_JBHI_2022_3208780 crossref_primary_10_1109_TNSRE_2022_3204540 crossref_primary_10_1109_OJIM_2022_3202555 crossref_primary_10_3390_s20216090 crossref_primary_10_1142_S0129065721500489 crossref_primary_10_3390_ijerph18115780 crossref_primary_10_3389_fnins_2023_1117340 crossref_primary_10_1155_2020_7902072 crossref_primary_10_1007_s12652_020_02185_7 crossref_primary_10_3345_cep_2021_00766 crossref_primary_10_1177_15500594231193511 crossref_primary_10_1109_ACCESS_2021_3132128 crossref_primary_10_3390_brainsci11050668 crossref_primary_10_1055_a_1370_3058 crossref_primary_10_1016_j_bspc_2021_102826 crossref_primary_10_1109_JTEHM_2021_3050925 crossref_primary_10_1007_s10462_021_09986_y crossref_primary_10_1007_s11042_024_19129_4 crossref_primary_10_1098_rsos_230601 crossref_primary_10_2174_1874120702115010090 crossref_primary_10_3389_fnins_2023_1291608 crossref_primary_10_3390_electronics8111208 crossref_primary_10_14581_jer_20003 crossref_primary_10_1007_s12652_020_01816_3 crossref_primary_10_1007_s11042_022_12702_9 crossref_primary_10_1016_j_bbe_2021_10_001 crossref_primary_10_1016_j_bspc_2022_104380 crossref_primary_10_1109_JBHI_2022_3159531 crossref_primary_10_1111_exsy_13447 crossref_primary_10_1055_a_1169_4254 crossref_primary_10_1109_TGRS_2022_3211010 crossref_primary_10_3390_app9235078 crossref_primary_10_1038_s41598_021_92805_9 crossref_primary_10_3389_fneur_2022_816294 crossref_primary_10_1109_TCE_2019_2917895 crossref_primary_10_3389_fnrgo_2024_1287794 crossref_primary_10_1016_j_heliyon_2020_e05580 crossref_primary_10_1007_s11831_023_09920_1 crossref_primary_10_1016_j_bspc_2021_102854 crossref_primary_10_1016_j_neuroscience_2020_12_001 crossref_primary_10_1016_j_bbe_2021_11_002 crossref_primary_10_1016_j_iot_2024_101098 crossref_primary_10_1142_S0129065720500562 crossref_primary_10_1016_j_compbiomed_2019_05_025 crossref_primary_10_3390_app14219712 crossref_primary_10_4015_S101623722250020X crossref_primary_10_4103_ijamr_ijamr_94_21 crossref_primary_10_1145_3552512 crossref_primary_10_3389_fnins_2024_1373515 |
| Cites_doi | 10.1007/s10072-012-0949-5 10.1109/TBME.2007.905490 10.1111/j.1528-1167.2007.00920.x 10.1109/TBME.2006.886855 10.1136/jnnp.2005.069245 10.1142/S0129065718500107 10.1016/j.seizure.2015.01.012 10.1142/S0129065717500058 10.1016/S0165-0270(02)00340-0 10.5405/jmbe.1463 10.1111/epi.13979 10.1142/S012906571850003X 10.1016/j.clinph.2004.05.018 10.1016/j.medengphy.2012.05.005 10.1016/0013-4694(90)90032-F 10.1007/s11263-015-0816-y 10.1016/S0920-1211(99)00107-2 10.1007/978-3-319-06764-3_33 10.1038/nature14539 10.1016/S1474-4422(03)00664-1 10.1002/hbm.23730 10.1001/archneurpsyc.1935.02250240002001 10.1586/ern.09.157 10.1016/S0013-4694(98)00043-1 10.1038/nature21056 10.1093/brain/aww198 10.1109/TBME.2007.891945 10.3233/ICA-2007-14301 10.1177/1550059414535465 10.1111/epi.13907 10.1016/j.media.2017.07.005 10.1016/j.neunet.2009.04.003 10.1016/j.clinph.2004.08.004 10.1093/brain/awx098 10.1016/j.clinph.2013.12.104 10.1016/j.compbiomed.2017.09.017 10.1371/journal.pone.0185852 10.1159/000100148 10.1155/2014/627892 |
| ContentType | Journal Article |
| Copyright | 2019 The Authors The Authors Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved. 2019 The Authors 2019 |
| Copyright_xml | – notice: 2019 The Authors – notice: The Authors – notice: Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved. – notice: 2019 The Authors 2019 |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 5PM DOA |
| DOI | 10.1016/j.nicl.2019.101684 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 2213-1582 |
| EndPage | 101684 |
| ExternalDocumentID | oai_doaj_org_article_7628bc18e7914601ab3b0de6a75d82c9 PMC6357853 30711680 10_1016_j_nicl_2019_101684 1_s2_0_S2213158219300348 S2213158219300348 |
| Genre | Research Support, Non-U.S. Gov't Journal Article |
| GroupedDBID | .1- .FO 0R~ 1P~ 457 53G 5VS AAEDT AAEDW AAIKJ AALRI AAXUO AAYWO ABMAC ACGFS ACVFH ADBBV ADCNI ADEZE ADRAZ ADVLN AEUPX AEXQZ AFJKZ AFPUW AFRHN AFTJW AGHFR AIGII AITUG AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ AOIJS APXCP BAWUL BCNDV DIK EBS EJD FDB GROUPED_DOAJ HYE HZ~ IPNFZ IXB KQ8 M41 M48 M~E O-L O9- OK1 RIG ROL RPM SSZ Z5R AFCTW AAYXX CITATION AACTN CGR CUY CVF ECM EIF NPM 7X8 5PM |
| ID | FETCH-LOGICAL-c640t-e3e6274febddbe11d92fee03ec1fff0207e5d3bc9a50f3f94d7831d830d9363a3 |
| IEDL.DBID | M48 |
| ISSN | 2213-1582 |
| IngestDate | Wed Aug 27 01:23:35 EDT 2025 Thu Aug 21 18:32:50 EDT 2025 Fri Jul 11 16:12:33 EDT 2025 Thu Apr 03 06:49:51 EDT 2025 Tue Jul 01 01:09:42 EDT 2025 Thu Apr 24 23:02:21 EDT 2025 Wed Jun 18 06:48:26 EDT 2025 Tue Aug 26 16:32:54 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | CNN STD Sz PLE OLE PFA TLE Epileptic seizure Deep learning rec Seizure detection FIAS MF DMF PWE RSA ROC Sup Sb RED FBTCS FAS Convolutional neural networks Scalp electroencephalogram FLE TS seizure subject rhythmic slow activity recording occipital lobe epilepsy multifocal suppression parietal lobe epilepsy receiver operating characteristic repetitive epileptiform discharge temporal lobe epilepsy patients with epilepsy paroxysmal fast activity focal aware seizure focal to bilateral tonic-clonic seizure frontal lobe epilepsy focal impaired awareness seizure diffuse multifocal tonic seizure standard deviation |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c640t-e3e6274febddbe11d92fee03ec1fff0207e5d3bc9a50f3f94d7831d830d9363a3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-3188-9805 |
| OpenAccessLink | http://journals.scholarsportal.info/openUrl.xqy?doi=10.1016/j.nicl.2019.101684 |
| PMID | 30711680 |
| PQID | 2179508481 |
| PQPubID | 23479 |
| PageCount | 1 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_7628bc18e7914601ab3b0de6a75d82c9 pubmedcentral_primary_oai_pubmedcentral_nih_gov_6357853 proquest_miscellaneous_2179508481 pubmed_primary_30711680 crossref_citationtrail_10_1016_j_nicl_2019_101684 crossref_primary_10_1016_j_nicl_2019_101684 elsevier_clinicalkeyesjournals_1_s2_0_S2213158219300348 elsevier_clinicalkey_doi_10_1016_j_nicl_2019_101684 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2019-01-01 |
| PublicationDateYYYYMMDD | 2019-01-01 |
| PublicationDate_xml | – month: 01 year: 2019 text: 2019-01-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | Netherlands |
| PublicationPlace_xml | – name: Netherlands |
| PublicationTitle | NeuroImage clinical |
| PublicationTitleAlternate | Neuroimage Clin |
| PublicationYear | 2019 |
| Publisher | Elsevier Inc Elsevier |
| Publisher_xml | – name: Elsevier Inc – name: Elsevier |
| References | Esteva, Kuprel, Novoa, Ko, Swetter, Blau, Thrun (bb0080) 2017; 546 AliMardani, Boostani, Blankertz (bb0035) 2016; 5 Acharya, Oh, Hagiwara, Tan, Adeli (bb0005) 2018; 100 Ahmedt-Aristizabal, Fookes, Dionisio, Nguyen, Cunha, Sridharan (bb0025) 2017; 58 Wilson, Scheuer, Emerson, Gabor (bb0275) 2004; 115 Ahmedt-Aristizabal, Fookes, Nguyen, Sridharan (bb0030) 2018 Foldvary, Caruso, Mascha, Perry, Klem, McCarthy, Qureshi, Dinner (bb0090) 2000; 23 Schirrmeister, Springenberg, Fiederer, Glasstetter, Eggensperger, Tangermann, Hutter, Burgard, Ball (bb0210) 2017; 38 Gao, Cai, Yang, Dong, Zhang (bb0100) 2017; 27 Varsavsky, Mareels, Cook (bb0255) 2016 Aminoff (bb0040) 2012 Baldassano, Brinkmann, Ung, Blevins, Conrad, Leyde, Cook, Khambhati, Wagenaar, Worrell, Litt (bb0055) 2017; 140 Venkataraman, Vlachos, Faith, Krishnan, Tsakalis, Treiman, Iasemidis (bb0265) 2014 Theodore, Fisher (bb0245) 2004; 3 Russakovsky, Deng, Su, Krause, Satheesh, Ma, Huang, Karpathy, Khosla, Bernstein, Berg, Fei-Fei (bb0195) 2015; 115 Lecun, Bengio, Hinton (bb0165) 2015 Anusha, Mathews, Puthankattil (bb0045) 2012 Henry, Sha (bb0135) 2012; 1 Saab, Gotman (bb0200) 2005; 116 Velis, Plouin, Gotman, Da Silva (bb0260) 2007; 48 Smith (bb0225) 2005; 76 Adeli, Ghosh-Dastidar, Dadmehr (bb0020) 2007; 54 Ghosh-Dastidar, Adeli (bb0110) 2009; 22 Ghosh-Dastidar, Adeli, Dadmehr (bb0115) 2007; 54 Orosco, Correa, Laciar (bb0190) 2013 Dvey-Aharon, Fogelson, Peled, Intrator (bb0075) 2017; 12 Kingma, Ba (bb0155) 2014 Manzano, Ragazzo, Tavares, Marino (bb0185) 1986; 49 Simonyan, Zisserman (bb0220) 2014 Dodge, Karam (bb0070) 2017 Faust, Acharya, Adeli, Adeli (bb0085) 2015; 26 Gabor (bb0095) 1998; 107 Yuan, Zhou, Xu, Leng, Wei (bb0280) 2018; 28 Satapathy, Dehuri, Jagadev (bb0205) 2016; 11 Ma, Minett, Blu, Wang (bb0180) 2015 Ghosh-Dastidar, Adeli, Dadmehr (bb0120) 2008; 55 Jirayucharoensak, Pan-Ngum, Israsena (bb0145) 2014; 2014 Li, Cui, Luo, Li, Wang (bb0170) 2018; 28 Thodoroff, Pineau, Lim (bb0250) 2016 Ghosh-Dastidar, Adeli (bb0105) 2007; 14 Tanaka, Khoo, Dubeau, Gotman (bb0240) 2017; 59 Wilson (bb0270) 2004 Cascino (bb0065) 2002 Gibbs, Davis, Lennox (bb0125) 1935; 34 Stein, Eder, Blum, Drachev, Research (bb0230) 2000; 39 Gotman (bb0130) 1990; 76 Lam, Zepeda, Cole, Cash (bb0160) 2016; 139 Hopfengärtner, Kasper, Graf, Gollwitzer, Kreiselmeyer, Stefan, Hamer (bb0140) 2014; 125 Adeli, Zhou, Dadmehr (bb0015) 2003; 123 Ayoubian, Lacoma, Gotman (bb0050) 2013; 35 Takahashi, Takahashi, Kanzaki, Kawai (bb0235) 2012; 33 Juárez-Guerra, Alarcon-Aquino, Gómez-Gil (bb0150) 2015; 312 Litjens, Kooi, Bejnordi, Arindra, Setio, Ciompi, Ghafoorian, Van Der Laak, Van Ginneken, Sánchez, Van Der Laak, Van Ginneken, Sánchez (bb0175) 2017; 42 Benbadis (bb0060) 2010; 10 Sharma, Khan, Farooq, Tripathi, Adeli (bb0215) 2014; 45 Adeli, Ghosh-Dastidar (bb0010) 2010 Anusha (10.1016/j.nicl.2019.101684_bb0045) 2012 Ghosh-Dastidar (10.1016/j.nicl.2019.101684_bb0105) 2007; 14 Jirayucharoensak (10.1016/j.nicl.2019.101684_bb0145) 2014; 2014 Venkataraman (10.1016/j.nicl.2019.101684_bb0265) 2014 Aminoff (10.1016/j.nicl.2019.101684_bb0040) 2012 Hopfengärtner (10.1016/j.nicl.2019.101684_bb0140) 2014; 125 Esteva (10.1016/j.nicl.2019.101684_bb0080) 2017; 546 Ghosh-Dastidar (10.1016/j.nicl.2019.101684_bb0110) 2009; 22 Gabor (10.1016/j.nicl.2019.101684_bb0095) 1998; 107 Takahashi (10.1016/j.nicl.2019.101684_bb0235) 2012; 33 Adeli (10.1016/j.nicl.2019.101684_bb0010) 2010 Adeli (10.1016/j.nicl.2019.101684_bb0015) 2003; 123 Smith (10.1016/j.nicl.2019.101684_bb0225) 2005; 76 Varsavsky (10.1016/j.nicl.2019.101684_bb0255) 2016 Ma (10.1016/j.nicl.2019.101684_bb0180) 2015 Orosco (10.1016/j.nicl.2019.101684_bb0190) 2013 Theodore (10.1016/j.nicl.2019.101684_bb0245) 2004; 3 Wilson (10.1016/j.nicl.2019.101684_bb0270) 2004 Lam (10.1016/j.nicl.2019.101684_bb0160) 2016; 139 Russakovsky (10.1016/j.nicl.2019.101684_bb0195) 2015; 115 Satapathy (10.1016/j.nicl.2019.101684_bb0205) 2016; 11 Juárez-Guerra (10.1016/j.nicl.2019.101684_bb0150) 2015; 312 Cascino (10.1016/j.nicl.2019.101684_bb0065) 2002 Saab (10.1016/j.nicl.2019.101684_bb0200) 2005; 116 Ayoubian (10.1016/j.nicl.2019.101684_bb0050) 2013; 35 Lecun (10.1016/j.nicl.2019.101684_bb0165) 2015 Dodge (10.1016/j.nicl.2019.101684_bb0070) 2017 Sharma (10.1016/j.nicl.2019.101684_bb0215) 2014; 45 Gotman (10.1016/j.nicl.2019.101684_bb0130) 1990; 76 Wilson (10.1016/j.nicl.2019.101684_bb0275) 2004; 115 Kingma (10.1016/j.nicl.2019.101684_bb0155) 2014 AliMardani (10.1016/j.nicl.2019.101684_bb0035) 2016; 5 Acharya (10.1016/j.nicl.2019.101684_bb0005) 2018; 100 Yuan (10.1016/j.nicl.2019.101684_bb0280) 2018; 28 Ghosh-Dastidar (10.1016/j.nicl.2019.101684_bb0115) 2007; 54 Manzano (10.1016/j.nicl.2019.101684_bb0185) 1986; 49 Simonyan (10.1016/j.nicl.2019.101684_bb0220) 2014 Litjens (10.1016/j.nicl.2019.101684_bb0175) 2017; 42 Schirrmeister (10.1016/j.nicl.2019.101684_bb0210) 2017; 38 Thodoroff (10.1016/j.nicl.2019.101684_bb0250) 2016 Gibbs (10.1016/j.nicl.2019.101684_bb0125) 1935; 34 Henry (10.1016/j.nicl.2019.101684_bb0135) 2012; 1 Foldvary (10.1016/j.nicl.2019.101684_bb0090) 2000; 23 Gao (10.1016/j.nicl.2019.101684_bb0100) 2017; 27 Baldassano (10.1016/j.nicl.2019.101684_bb0055) 2017; 140 Adeli (10.1016/j.nicl.2019.101684_bb0020) 2007; 54 Tanaka (10.1016/j.nicl.2019.101684_bb0240) 2017; 59 Ahmedt-Aristizabal (10.1016/j.nicl.2019.101684_bb0030) 2018 Velis (10.1016/j.nicl.2019.101684_bb0260) 2007; 48 Li (10.1016/j.nicl.2019.101684_bb0170) 2018; 28 Dvey-Aharon (10.1016/j.nicl.2019.101684_bb0075) 2017; 12 Faust (10.1016/j.nicl.2019.101684_bb0085) 2015; 26 Ghosh-Dastidar (10.1016/j.nicl.2019.101684_bb0120) 2008; 55 Stein (10.1016/j.nicl.2019.101684_bb0230) 2000; 39 Benbadis (10.1016/j.nicl.2019.101684_bb0060) 2010; 10 Ahmedt-Aristizabal (10.1016/j.nicl.2019.101684_bb0025) 2017; 58 |
| References_xml | – volume: 140 start-page: 1680 year: 2017 end-page: 1691 ident: bb0055 article-title: Crowdsourcing seizure detection: algorithm development and validation on human implanted device recordings publication-title: Brain – volume: 100 start-page: 270 year: 2018 end-page: 278 ident: bb0005 article-title: Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals publication-title: Comput. Biol. Med. – start-page: 1111 year: 2002 end-page: 1120 ident: bb0065 article-title: Clinical indications and diagnostic yield of video-electroencephalographic monitoring in patients with seizures and spells publication-title: Mayo Clinic Proceedings – volume: 27 start-page: 1750005 year: 2017 ident: bb0100 article-title: Visibility graph from adaptive optimal kernel time-frequency representation for classification of epileptiform EEG publication-title: Int. J. Neural Syst. – volume: 49 start-page: 213 year: 1986 end-page: 217 ident: bb0185 article-title: Anterior zygomatic electrodes: a special electrode for the study of temporal lobe epilepsy publication-title: Stereotact. Funct. Neurosurg. – volume: 22 start-page: 1419 year: 2009 end-page: 1431 ident: bb0110 article-title: A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection publication-title: Neural Netw. – volume: 48 start-page: 379 year: 2007 end-page: 384 ident: bb0260 article-title: Recommendations regarding the requirements and applications for long-term recordings in epilepsy publication-title: Epilepsia – volume: 26 start-page: 56 year: 2015 end-page: 64 ident: bb0085 article-title: Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis publication-title: Seizure – volume: 34 start-page: 1133 year: 1935 end-page: 1148 ident: bb0125 article-title: The electro-encephalogram in epilepsy and in conditions of impaired consciousness publication-title: Arch. Neurol. Psychiatr. – volume: 10 start-page: 343 year: 2010 end-page: 346 ident: bb0060 article-title: The tragedy of over-read EEGs and wrong diagnoses of epilepsy publication-title: Expert. Rev. Neurother. – volume: 139 start-page: 2679 year: 2016 end-page: 2693 ident: bb0160 article-title: Widespread changes in network activity allow non-invasive detection of mesial temporal lobe seizures publication-title: Brain – volume: 58 start-page: 1817 year: 2017 end-page: 1831 ident: bb0025 article-title: Automated analysis of seizure semiology and brain electrical activity in presurgery evaluation of epilepsy: a focused survey publication-title: Epilepsia – volume: 115 start-page: 2280 year: 2004 end-page: 2291 ident: bb0275 article-title: Seizure detection: evaluation of the Reveal algorithm publication-title: Clin. Neurophysiol. – volume: 59 start-page: 420 year: 2017 end-page: 430 ident: bb0240 article-title: Association between scalp and intracerebral electroencephalographic seizure-onset patterns: a study in different lesional pathological substrates publication-title: Epilepsia – volume: 39 start-page: 103 year: 2000 end-page: 114 ident: bb0230 article-title: An automated drug delivery system for focal epilepsy publication-title: Epilepsy Res. – volume: 54 start-page: 205 year: 2007 end-page: 211 ident: bb0020 article-title: A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epilepsy publication-title: IEEE Trans. Biomed. Eng. – year: 2014 ident: bb0155 article-title: Adam: a method for stochastic optimization publication-title: arXiv Prepr. – volume: 11 start-page: 973 year: 2016 end-page: 4562 ident: bb0205 article-title: An empirical analysis of different machine learning techniques for classification of EEG signal to detect epileptic seizure publication-title: Int. J. Appl. Eng. Res. – volume: 45 start-page: 274 year: 2014 end-page: 284 ident: bb0215 article-title: A wavelet-statistical features approach for nonconvulsive seizure detection publication-title: Clin. EEG Neurosci. – year: 2018 ident: bb0030 article-title: Deep classification of epileptic signals publication-title: arXiv Prepr. – volume: 76 start-page: 317 year: 1990 end-page: 324 ident: bb0130 article-title: Automatic seizure detection: improvements and evaluation publication-title: Electroencephalogr. Clin. Neurophysiol. – volume: 76 start-page: ii2 year: 2005 end-page: ii7 ident: bb0225 article-title: EEG in the diagnosis, classification, and management of patients with epilepsy publication-title: J. Neurol. Neurosurg. Psychiatry – volume: 12 year: 2017 ident: bb0075 article-title: Connectivity maps based analysis of EEG for the advanced diagnosis of schizophrenia attributes publication-title: PLoS One – start-page: 98 year: 2012 end-page: 101 ident: bb0045 article-title: Classification of normal and epileptic EEG signal using time & frequency domain features through artificial neural network publication-title: 2012 International Conference on advances in Computing and Communications (ICACC) – volume: 116 start-page: 427 year: 2005 end-page: 442 ident: bb0200 article-title: A system to detect the onset of epileptic seizures in scalp EEG publication-title: Clin. Neurophysiol. – volume: 546 start-page: 115 year: 2017 ident: bb0080 article-title: Dermatologist-level classification of skin cancer with deep neural networks publication-title: Nature – volume: 23 start-page: 1 year: 2000 end-page: 9 ident: bb0090 article-title: Identifying montages that best detect electrographic seizure activity during polysomnography publication-title: Sleep – year: 2015 ident: bb0165 article-title: Deep learning publication-title: Nature – year: 2014 ident: bb0220 article-title: Very deep convolutional networks for large-scale image recognition publication-title: arXiv – volume: 115 start-page: 211 year: 2015 end-page: 252 ident: bb0195 article-title: ImageNet large scale visual recognition challenge publication-title: Int. J. Comput. Vis. – volume: 14 start-page: 187 year: 2007 end-page: 212 ident: bb0105 article-title: Improved spiking neural networks for EEG classification and epilepsy and seizure detection publication-title: Integr. Comput. Aided. Eng. – volume: 54 start-page: 1545 year: 2007 end-page: 1551 ident: bb0115 article-title: Mixed-band wavelet-chaos-neural network methodology for epilepsy and epileptic seizure detection publication-title: IEEE Trans. Biomed. Eng. – volume: 5 start-page: 79 year: 2016 end-page: 85 ident: bb0035 article-title: Presenting a spatial-geometric EEG feature to classify BMD and schizophrenic patients publication-title: Int. J. Adv. Telecommun. Electrotech. Signals Syst. – year: 2016 ident: bb0255 article-title: Epileptic Seizures and the EEG : Measurement, Models, Detection and Prediction – start-page: 946 year: 2014 end-page: 949 ident: bb0265 article-title: Brain dynamics based automated epileptic seizure detection publication-title: 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society – start-page: 2848 year: 2015 end-page: 2851 ident: bb0180 article-title: Resting state EEG-based biometrics for individual identification using convolutional neural networks publication-title: 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) – volume: 38 start-page: 5391 year: 2017 end-page: 5420 ident: bb0210 article-title: Deep learning with convolutional neural networks for EEG decoding and visualization publication-title: Hum. Brain Mapp. – volume: 55 start-page: 512 year: 2008 end-page: 518 ident: bb0120 article-title: Principal component analysis-enhanced cosine radial basis function neural network for robust epilepsy and seizure detection publication-title: IEEE Trans. Biomed. Eng. – volume: 3 start-page: 111 year: 2004 end-page: 118 ident: bb0245 article-title: Brain stimulation for epilepsy publication-title: Lancet Neurol. – volume: 33 start-page: 1355 year: 2012 end-page: 1364 ident: bb0235 article-title: State-dependent precursors of seizures in correlation-based functional networks of electrocorticograms of patients with temporal lobe epilepsy publication-title: Neurol. Sci. – volume: 1 start-page: 1 year: 2012 end-page: 45 ident: bb0135 article-title: Seizures and epilepsy: electrophysiological diagnosis publication-title: Epilepsy Board Rev. Man. – volume: 312 start-page: 261 year: 2015 end-page: 269 ident: bb0150 article-title: Epilepsy seizure detection in EEG signals using wavelet transforms and neural networks publication-title: Lect. Notes Electr. Eng. – year: 2013 ident: bb0190 article-title: Review: a survey of performance and techniques for automatic epilepsy detection publication-title: J. Med. Biol. Eng. – volume: 35 start-page: 319 year: 2013 end-page: 328 ident: bb0050 article-title: Automatic seizure detection in SEEG using high frequency activities in wavelet domain publication-title: Med. Eng. Phys. – volume: 125 start-page: 1346 year: 2014 end-page: 1352 ident: bb0140 article-title: Automatic seizure detection in long-term scalp EEG using an adaptive thresholding technique: a validation study for clinical routine publication-title: Clin. Neurophysiol. – volume: 107 start-page: 27 year: 1998 end-page: 32 ident: bb0095 article-title: Seizures detection using a self organizing neural network: validation and comparison with other detection strategies publication-title: Electroencephalogr. Clin. Neurophysiol. – start-page: 178 year: 2016 end-page: 190 ident: bb0250 article-title: Learning Robust Features using Deep Learning for Automatic Seizure Detection publication-title: Proceedings of the 1st Machine Learning for Healthcare Conference, Proceedings of Machine Learning Research – volume: 123 start-page: 69 year: 2003 end-page: 87 ident: bb0015 article-title: Analysis of EEG records in an epileptic patient using wavelet transform publication-title: J. Neurosci. Methods – start-page: 1 year: 2017 end-page: 7 ident: bb0070 article-title: A study and comparison of human and deep learning recognition performance under visual distortions publication-title: 2017 26th International Conference on Computer Communication and Networks (ICCCN) – year: 2004 ident: bb0270 article-title: Method and System for Detecting Seizures Using Electroencephalograms – volume: 28 start-page: 1850010 year: 2018 ident: bb0280 article-title: Epileptic EEG Identification via LBP Operators on Wavelet Coefficients publication-title: Int. J. Neural Syst. – year: 2010 ident: bb0010 article-title: Automated EEG-Based Diagnosis of Neurological Disorders – year: 2012 ident: bb0040 article-title: Aminoff’s Electrodiagnosis in Clinical Neurology – volume: 28 start-page: 1850003 year: 2018 ident: bb0170 article-title: Epileptic seizure detection based on time-frequency images of EEG signals using Gaussian mixture model and gray level co-occurrence matrix features publication-title: Int. J. Neural Syst. – volume: 2014 year: 2014 ident: bb0145 article-title: EEG-based emotion recognition using deep learning network with principal component based covariate shift adaptation publication-title: Sci. World J. – volume: 42 start-page: 60 year: 2017 end-page: 88 ident: bb0175 article-title: A survey on deep learning in medical image analysis publication-title: Med. Image Anal. – volume: 33 start-page: 1355 year: 2012 ident: 10.1016/j.nicl.2019.101684_bb0235 article-title: State-dependent precursors of seizures in correlation-based functional networks of electrocorticograms of patients with temporal lobe epilepsy publication-title: Neurol. Sci. doi: 10.1007/s10072-012-0949-5 – volume: 55 start-page: 512 year: 2008 ident: 10.1016/j.nicl.2019.101684_bb0120 article-title: Principal component analysis-enhanced cosine radial basis function neural network for robust epilepsy and seizure detection publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2007.905490 – start-page: 1111 year: 2002 ident: 10.1016/j.nicl.2019.101684_bb0065 article-title: Clinical indications and diagnostic yield of video-electroencephalographic monitoring in patients with seizures and spells – volume: 48 start-page: 379 year: 2007 ident: 10.1016/j.nicl.2019.101684_bb0260 article-title: Recommendations regarding the requirements and applications for long-term recordings in epilepsy publication-title: Epilepsia doi: 10.1111/j.1528-1167.2007.00920.x – volume: 54 start-page: 205 year: 2007 ident: 10.1016/j.nicl.2019.101684_bb0020 article-title: A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epilepsy publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2006.886855 – volume: 76 start-page: ii2 year: 2005 ident: 10.1016/j.nicl.2019.101684_bb0225 article-title: EEG in the diagnosis, classification, and management of patients with epilepsy publication-title: J. Neurol. Neurosurg. Psychiatry doi: 10.1136/jnnp.2005.069245 – volume: 28 start-page: 1850010 year: 2018 ident: 10.1016/j.nicl.2019.101684_bb0280 article-title: Epileptic EEG Identification via LBP Operators on Wavelet Coefficients publication-title: Int. J. Neural Syst. doi: 10.1142/S0129065718500107 – volume: 26 start-page: 56 year: 2015 ident: 10.1016/j.nicl.2019.101684_bb0085 article-title: Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis publication-title: Seizure doi: 10.1016/j.seizure.2015.01.012 – volume: 27 start-page: 1750005 year: 2017 ident: 10.1016/j.nicl.2019.101684_bb0100 article-title: Visibility graph from adaptive optimal kernel time-frequency representation for classification of epileptiform EEG publication-title: Int. J. Neural Syst. doi: 10.1142/S0129065717500058 – volume: 123 start-page: 69 year: 2003 ident: 10.1016/j.nicl.2019.101684_bb0015 article-title: Analysis of EEG records in an epileptic patient using wavelet transform publication-title: J. Neurosci. Methods doi: 10.1016/S0165-0270(02)00340-0 – start-page: 2848 year: 2015 ident: 10.1016/j.nicl.2019.101684_bb0180 article-title: Resting state EEG-based biometrics for individual identification using convolutional neural networks – start-page: 946 year: 2014 ident: 10.1016/j.nicl.2019.101684_bb0265 article-title: Brain dynamics based automated epileptic seizure detection – year: 2013 ident: 10.1016/j.nicl.2019.101684_bb0190 article-title: Review: a survey of performance and techniques for automatic epilepsy detection publication-title: J. Med. Biol. Eng. doi: 10.5405/jmbe.1463 – volume: 1 start-page: 1 year: 2012 ident: 10.1016/j.nicl.2019.101684_bb0135 article-title: Seizures and epilepsy: electrophysiological diagnosis publication-title: Epilepsy Board Rev. Man. – volume: 59 start-page: 420 year: 2017 ident: 10.1016/j.nicl.2019.101684_bb0240 article-title: Association between scalp and intracerebral electroencephalographic seizure-onset patterns: a study in different lesional pathological substrates publication-title: Epilepsia doi: 10.1111/epi.13979 – volume: 28 start-page: 1850003 year: 2018 ident: 10.1016/j.nicl.2019.101684_bb0170 article-title: Epileptic seizure detection based on time-frequency images of EEG signals using Gaussian mixture model and gray level co-occurrence matrix features publication-title: Int. J. Neural Syst. doi: 10.1142/S012906571850003X – volume: 115 start-page: 2280 year: 2004 ident: 10.1016/j.nicl.2019.101684_bb0275 article-title: Seizure detection: evaluation of the Reveal algorithm publication-title: Clin. Neurophysiol. doi: 10.1016/j.clinph.2004.05.018 – volume: 35 start-page: 319 year: 2013 ident: 10.1016/j.nicl.2019.101684_bb0050 article-title: Automatic seizure detection in SEEG using high frequency activities in wavelet domain publication-title: Med. Eng. Phys. doi: 10.1016/j.medengphy.2012.05.005 – volume: 76 start-page: 317 year: 1990 ident: 10.1016/j.nicl.2019.101684_bb0130 article-title: Automatic seizure detection: improvements and evaluation publication-title: Electroencephalogr. Clin. Neurophysiol. doi: 10.1016/0013-4694(90)90032-F – volume: 115 start-page: 211 year: 2015 ident: 10.1016/j.nicl.2019.101684_bb0195 article-title: ImageNet large scale visual recognition challenge publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-015-0816-y – year: 2014 ident: 10.1016/j.nicl.2019.101684_bb0220 article-title: Very deep convolutional networks for large-scale image recognition publication-title: arXiv – start-page: 178 year: 2016 ident: 10.1016/j.nicl.2019.101684_bb0250 article-title: Learning Robust Features using Deep Learning for Automatic Seizure Detection – volume: 39 start-page: 103 year: 2000 ident: 10.1016/j.nicl.2019.101684_bb0230 article-title: An automated drug delivery system for focal epilepsy publication-title: Epilepsy Res. doi: 10.1016/S0920-1211(99)00107-2 – volume: 312 start-page: 261 year: 2015 ident: 10.1016/j.nicl.2019.101684_bb0150 article-title: Epilepsy seizure detection in EEG signals using wavelet transforms and neural networks publication-title: Lect. Notes Electr. Eng. doi: 10.1007/978-3-319-06764-3_33 – year: 2015 ident: 10.1016/j.nicl.2019.101684_bb0165 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – volume: 3 start-page: 111 year: 2004 ident: 10.1016/j.nicl.2019.101684_bb0245 article-title: Brain stimulation for epilepsy publication-title: Lancet Neurol. doi: 10.1016/S1474-4422(03)00664-1 – year: 2018 ident: 10.1016/j.nicl.2019.101684_bb0030 article-title: Deep classification of epileptic signals publication-title: arXiv Prepr. – volume: 38 start-page: 5391 year: 2017 ident: 10.1016/j.nicl.2019.101684_bb0210 article-title: Deep learning with convolutional neural networks for EEG decoding and visualization publication-title: Hum. Brain Mapp. doi: 10.1002/hbm.23730 – volume: 34 start-page: 1133 year: 1935 ident: 10.1016/j.nicl.2019.101684_bb0125 article-title: The electro-encephalogram in epilepsy and in conditions of impaired consciousness publication-title: Arch. Neurol. Psychiatr. doi: 10.1001/archneurpsyc.1935.02250240002001 – volume: 10 start-page: 343 year: 2010 ident: 10.1016/j.nicl.2019.101684_bb0060 article-title: The tragedy of over-read EEGs and wrong diagnoses of epilepsy publication-title: Expert. Rev. Neurother. doi: 10.1586/ern.09.157 – volume: 107 start-page: 27 year: 1998 ident: 10.1016/j.nicl.2019.101684_bb0095 article-title: Seizures detection using a self organizing neural network: validation and comparison with other detection strategies publication-title: Electroencephalogr. Clin. Neurophysiol. doi: 10.1016/S0013-4694(98)00043-1 – year: 2010 ident: 10.1016/j.nicl.2019.101684_bb0010 – volume: 546 start-page: 115 year: 2017 ident: 10.1016/j.nicl.2019.101684_bb0080 article-title: Dermatologist-level classification of skin cancer with deep neural networks publication-title: Nature doi: 10.1038/nature21056 – volume: 23 start-page: 1 year: 2000 ident: 10.1016/j.nicl.2019.101684_bb0090 article-title: Identifying montages that best detect electrographic seizure activity during polysomnography publication-title: Sleep – volume: 5 start-page: 79 year: 2016 ident: 10.1016/j.nicl.2019.101684_bb0035 article-title: Presenting a spatial-geometric EEG feature to classify BMD and schizophrenic patients publication-title: Int. J. Adv. Telecommun. Electrotech. Signals Syst. – year: 2014 ident: 10.1016/j.nicl.2019.101684_bb0155 article-title: Adam: a method for stochastic optimization publication-title: arXiv Prepr. – volume: 139 start-page: 2679 year: 2016 ident: 10.1016/j.nicl.2019.101684_bb0160 article-title: Widespread changes in network activity allow non-invasive detection of mesial temporal lobe seizures publication-title: Brain doi: 10.1093/brain/aww198 – start-page: 98 year: 2012 ident: 10.1016/j.nicl.2019.101684_bb0045 article-title: Classification of normal and epileptic EEG signal using time & frequency domain features through artificial neural network – volume: 54 start-page: 1545 year: 2007 ident: 10.1016/j.nicl.2019.101684_bb0115 article-title: Mixed-band wavelet-chaos-neural network methodology for epilepsy and epileptic seizure detection publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2007.891945 – year: 2004 ident: 10.1016/j.nicl.2019.101684_bb0270 – year: 2012 ident: 10.1016/j.nicl.2019.101684_bb0040 – volume: 14 start-page: 187 year: 2007 ident: 10.1016/j.nicl.2019.101684_bb0105 article-title: Improved spiking neural networks for EEG classification and epilepsy and seizure detection publication-title: Integr. Comput. Aided. Eng. doi: 10.3233/ICA-2007-14301 – volume: 45 start-page: 274 year: 2014 ident: 10.1016/j.nicl.2019.101684_bb0215 article-title: A wavelet-statistical features approach for nonconvulsive seizure detection publication-title: Clin. EEG Neurosci. doi: 10.1177/1550059414535465 – volume: 58 start-page: 1817 year: 2017 ident: 10.1016/j.nicl.2019.101684_bb0025 article-title: Automated analysis of seizure semiology and brain electrical activity in presurgery evaluation of epilepsy: a focused survey publication-title: Epilepsia doi: 10.1111/epi.13907 – volume: 42 start-page: 60 year: 2017 ident: 10.1016/j.nicl.2019.101684_bb0175 article-title: A survey on deep learning in medical image analysis publication-title: Med. Image Anal. doi: 10.1016/j.media.2017.07.005 – volume: 22 start-page: 1419 year: 2009 ident: 10.1016/j.nicl.2019.101684_bb0110 article-title: A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection publication-title: Neural Netw. doi: 10.1016/j.neunet.2009.04.003 – volume: 116 start-page: 427 year: 2005 ident: 10.1016/j.nicl.2019.101684_bb0200 article-title: A system to detect the onset of epileptic seizures in scalp EEG publication-title: Clin. Neurophysiol. doi: 10.1016/j.clinph.2004.08.004 – volume: 140 start-page: 1680 year: 2017 ident: 10.1016/j.nicl.2019.101684_bb0055 article-title: Crowdsourcing seizure detection: algorithm development and validation on human implanted device recordings publication-title: Brain doi: 10.1093/brain/awx098 – volume: 125 start-page: 1346 year: 2014 ident: 10.1016/j.nicl.2019.101684_bb0140 article-title: Automatic seizure detection in long-term scalp EEG using an adaptive thresholding technique: a validation study for clinical routine publication-title: Clin. Neurophysiol. doi: 10.1016/j.clinph.2013.12.104 – volume: 100 start-page: 270 year: 2018 ident: 10.1016/j.nicl.2019.101684_bb0005 article-title: Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2017.09.017 – volume: 12 year: 2017 ident: 10.1016/j.nicl.2019.101684_bb0075 article-title: Connectivity maps based analysis of EEG for the advanced diagnosis of schizophrenia attributes publication-title: PLoS One doi: 10.1371/journal.pone.0185852 – year: 2016 ident: 10.1016/j.nicl.2019.101684_bb0255 – start-page: 1 year: 2017 ident: 10.1016/j.nicl.2019.101684_bb0070 article-title: A study and comparison of human and deep learning recognition performance under visual distortions – volume: 49 start-page: 213 year: 1986 ident: 10.1016/j.nicl.2019.101684_bb0185 article-title: Anterior zygomatic electrodes: a special electrode for the study of temporal lobe epilepsy publication-title: Stereotact. Funct. Neurosurg. doi: 10.1159/000100148 – volume: 2014 year: 2014 ident: 10.1016/j.nicl.2019.101684_bb0145 article-title: EEG-based emotion recognition using deep learning network with principal component based covariate shift adaptation publication-title: Sci. World J. doi: 10.1155/2014/627892 – volume: 11 start-page: 973 year: 2016 ident: 10.1016/j.nicl.2019.101684_bb0205 article-title: An empirical analysis of different machine learning techniques for classification of EEG signal to detect epileptic seizure publication-title: Int. J. Appl. Eng. Res. |
| SSID | ssj0000800766 |
| Score | 2.523257 |
| Snippet | We hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze... AbstractWe hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze... |
| SourceID | doaj pubmedcentral proquest pubmed crossref elsevier |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 101684 |
| SubjectTerms | Adolescent Adult Child Convolutional neural networks Deep Learning Electroencephalography - methods Electroencephalography - standards Epilepsies, Partial - diagnosis Epileptic seizure Female Humans Image Processing, Computer-Assisted - methods Image Processing, Computer-Assisted - standards Male Middle Aged Radiology Regular Scalp Scalp electroencephalogram Seizure detection Seizures - diagnosis Sensitivity and Specificity Young Adult |
| SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELZQD4gL4k3KQ0bihiLi2EmcIyCqCqlcSqXeLDseq1st2VWTPcCvZ8ZxVhtA5cJppWy8lj3fvNbjbxh7K1GJnHVNXkLQuYLgco1xRK6lQmerbV2VdMH57Gt9eqG-XFaXB62-qCZsogeeNu49Kqt2ndDQtKjUhbBOusJDbZvK67KLV_fQ5x0kU9cpDmriQWVZCpmLSpfpxsxU3EWss1TX1cYHWi28UiTvXzinP4PP32soD5zSyQN2P0WT_MO0iofsDvSP2N2zdF7-mK3PYfVzdwPcwxhrrnrufnCqNE-Iw8HEaBk_Yj14Tm7Nc5u4Svgm8AHFuOWpXw4Zgu2VnZmu-Xa9GfnqO1ql4Qm7OPn87dNpnvor5F2tijEHCdR5J4Dz3oEQvi0DQCGhEyEEjCMbqLx0XWurIsjQKt9oKbyWhW9lLa18yo76TQ_PGceRVRNAVQFDEkxRbNthmoupjPSo9Z3KmJj313SJfJx6YKzNXGV2bUgmhmRiJplk7N1-zHai3rj17Y8ktv2bRJsdHyCYTAKT-ReYMiZnoZv5ZiraUvyh1a1TN38bBUMyB4MRZihNYc4JjIRFjJqJGEhn7M2MLINqTWc1tofNbjCYKVJ_XqVFxp5NSNsvDc2ywHkLnHeBwcXal9_0q6tIHV5HciN5_D826wW7R5sw_R_1kh2NNzt4hRHa6F5HZfwF1Io4rA priority: 102 providerName: Directory of Open Access Journals |
| Title | Seizure detection by convolutional neural network-based analysis of scalp electroencephalography plot images |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S2213158219300348 https://www.clinicalkey.es/playcontent/1-s2.0-S2213158219300348 https://www.ncbi.nlm.nih.gov/pubmed/30711680 https://www.proquest.com/docview/2179508481 https://pubmed.ncbi.nlm.nih.gov/PMC6357853 https://doaj.org/article/7628bc18e7914601ab3b0de6a75d82c9 |
| Volume | 22 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3db9QwDI_GkKa9IL4pH1OQeENFTdOP9AFNAzFNSMfLOGlvUdI47KZbe1x7EuOvx0nTg8Kxp1ZtnCq1Hdut_TMhbzgqkVa6jFOwIs7A6ligHxELnqGxFarIU1fgPPtSnM2zzxf5xR4Z2x2FF9jtDO1cP6n5evnux_ebY1T4979ztRyIrEvTqvwFkd0hd9EylU5RZ8HdvwreUVkUoXZmN-khOUCxZ3iaTEyVR_SfWKx_PdK_Eyv_sFSn98m94GLSk0EmHpA9aB6Sg1n4if6ILM9h8XOzBmqg94lYDdU31KWfBzFEYgdz6Q8-STx2ts5QFQBMaGtph7xd0dBEx-0Oq0s1wl_T1bLt6eIat6ruMZmffvr68SwOTRfiusiSPgYOrh2PBW2MBsZMlVqAhEPNrLXoXJaQG67rSuWJ5bbKTCk4M4InpuIFV_wJ2W_aBp4RipR5aSHLLfopGLeoqsbYF-MbbnArqLOIsPH9yjogkrvGGEs5pp5dScce6dgjB_ZE5O2WZjXgcdw6-oNj23akw9L2F9r1NxlUU6I5ELpmAsoKzUbClOY6MVCoMjcirauI8JHpcixXxQ0WJ1rc-uhyFxV0o4hLJrtUJvI8TRlnrl654g4tSETk9ShZEnXd_cBRDbSbTmL46Jr2ZoJF5OkgaduljUKLz53I4GTt0zvN4tLjiRce8Yg__--cL8ihW9nw5ekl2e_XG3iFvlivj_w3jCOvZr8Ac5EzTQ |
| linkProvider | Scholars Portal |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Seizure+detection+by+convolutional+neural+network-based+analysis+of+scalp+electroencephalography+plot+images&rft.jtitle=NeuroImage+clinical&rft.au=Emami%2C+Ali&rft.au=Kunii%2C+Naoto&rft.au=Matsuo%2C+Takeshi&rft.au=Shinozaki%2C+Takashi&rft.date=2019-01-01&rft.eissn=2213-1582&rft.volume=22&rft.spage=101684&rft_id=info:doi/10.1016%2Fj.nicl.2019.101684&rft_id=info%3Apmid%2F30711680&rft.externalDocID=30711680 |
| thumbnail_m | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F22131582%2FS2213158219X00029%2Fcov150h.gif |