Matches in SemOpenAlex for { <https://semopenalex.org/work/W2903894955> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2903894955 endingPage "71" @default.
- W2903894955 startingPage "65" @default.
- W2903894955 abstract "PurposeThe recent explosion of artificial intelligence techniques in video analytics has highlighted the clinical relevance in capturing and quantifying semiology during epileptic seizures; however, we lack an automated anomaly identification system for aberrant behaviors. In this paper, we describe a novel system that is trained with known clinical manifestations from patients with mesial temporal and extra-temporal lobe epilepsy and presents aberrant semiology to physicians.MethodsWe propose a simple end-to-end-architecture based on convolutional and recurrent neural networks to extract spatiotemporal representations and to create motion capture libraries from 119 seizures of 28 patients. The cosine similarity distance between a test representation and the libraries from five aberrant seizures separate to the main dataset is subsequently used to identify test seizures with unusual patterns that do not conform to known behavior.ResultsCross-validation evaluations are performed to validate the quantification of motion features and to demonstrate the robustness of the motion capture libraries for identifying epilepsy types. The system to identify unusual epileptic seizures successfully detects out of the five seizures categorized as aberrant cases.ConclusionsThe proposed approach is capable of modeling clinical manifestations of known behaviors in natural clinical settings, and effectively identify aberrant seizures using a simple strategy based on motion capture libraries of spatiotemporal representations and similarities between hidden states. Detecting anomalies is essential to alert clinicians to the occurrence of unusual events, and we show how this can be achieved using pre-learned database of semiology stored in health records." @default.
- W2903894955 created "2018-12-22" @default.
- W2903894955 creator A5007030707 @default.
- W2903894955 creator A5029134472 @default.
- W2903894955 creator A5034095159 @default.
- W2903894955 creator A5038839161 @default.
- W2903894955 creator A5055128383 @default.
- W2903894955 creator A5083626840 @default.
- W2903894955 date "2019-02-01" @default.
- W2903894955 modified "2023-10-16" @default.
- W2903894955 title "Aberrant epileptic seizure identification: A computer vision perspective" @default.
- W2903894955 cites W1999755779 @default.
- W2903894955 cites W2034134202 @default.
- W2903894955 cites W2051902446 @default.
- W2903894955 cites W2064675550 @default.
- W2903894955 cites W2094674359 @default.
- W2903894955 cites W2762012795 @default.
- W2903894955 cites W2793070938 @default.
- W2903894955 cites W2888839432 @default.
- W2903894955 cites W2963150697 @default.
- W2903894955 doi "https://doi.org/10.1016/j.seizure.2018.12.017" @default.
- W2903894955 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30616221" @default.
- W2903894955 hasPublicationYear "2019" @default.
- W2903894955 type Work @default.
- W2903894955 sameAs 2903894955 @default.
- W2903894955 citedByCount "15" @default.
- W2903894955 countsByYear W29038949552019 @default.
- W2903894955 countsByYear W29038949552020 @default.
- W2903894955 countsByYear W29038949552021 @default.
- W2903894955 countsByYear W29038949552022 @default.
- W2903894955 countsByYear W29038949552023 @default.
- W2903894955 crossrefType "journal-article" @default.
- W2903894955 hasAuthorship W2903894955A5007030707 @default.
- W2903894955 hasAuthorship W2903894955A5029134472 @default.
- W2903894955 hasAuthorship W2903894955A5034095159 @default.
- W2903894955 hasAuthorship W2903894955A5038839161 @default.
- W2903894955 hasAuthorship W2903894955A5055128383 @default.
- W2903894955 hasAuthorship W2903894955A5083626840 @default.
- W2903894955 hasBestOaLocation W29038949551 @default.
- W2903894955 hasConcept C119857082 @default.
- W2903894955 hasConcept C12713177 @default.
- W2903894955 hasConcept C153180895 @default.
- W2903894955 hasConcept C154945302 @default.
- W2903894955 hasConcept C15744967 @default.
- W2903894955 hasConcept C169760540 @default.
- W2903894955 hasConcept C198951751 @default.
- W2903894955 hasConcept C2778186239 @default.
- W2903894955 hasConcept C2781099131 @default.
- W2903894955 hasConcept C41008148 @default.
- W2903894955 hasConcept C81363708 @default.
- W2903894955 hasConceptScore W2903894955C119857082 @default.
- W2903894955 hasConceptScore W2903894955C12713177 @default.
- W2903894955 hasConceptScore W2903894955C153180895 @default.
- W2903894955 hasConceptScore W2903894955C154945302 @default.
- W2903894955 hasConceptScore W2903894955C15744967 @default.
- W2903894955 hasConceptScore W2903894955C169760540 @default.
- W2903894955 hasConceptScore W2903894955C198951751 @default.
- W2903894955 hasConceptScore W2903894955C2778186239 @default.
- W2903894955 hasConceptScore W2903894955C2781099131 @default.
- W2903894955 hasConceptScore W2903894955C41008148 @default.
- W2903894955 hasConceptScore W2903894955C81363708 @default.
- W2903894955 hasLocation W29038949551 @default.
- W2903894955 hasLocation W29038949552 @default.
- W2903894955 hasLocation W29038949553 @default.
- W2903894955 hasOpenAccess W2903894955 @default.
- W2903894955 hasPrimaryLocation W29038949551 @default.
- W2903894955 hasRelatedWork W1991513523 @default.
- W2903894955 hasRelatedWork W1991853590 @default.
- W2903894955 hasRelatedWork W2118318118 @default.
- W2903894955 hasRelatedWork W2149935558 @default.
- W2903894955 hasRelatedWork W2154321347 @default.
- W2903894955 hasRelatedWork W2175746458 @default.
- W2903894955 hasRelatedWork W2732542196 @default.
- W2903894955 hasRelatedWork W3027997911 @default.
- W2903894955 hasRelatedWork W3093612317 @default.
- W2903894955 hasRelatedWork W4287776258 @default.
- W2903894955 hasVolume "65" @default.
- W2903894955 isParatext "false" @default.
- W2903894955 isRetracted "false" @default.
- W2903894955 magId "2903894955" @default.
- W2903894955 workType "article" @default.