Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952091205> ?p ?o ?g. }
- W2952091205 abstract "Deep learning has great potential for imaging classification by extracting low to high-level features. Our aim was to train a convolution neural network (CNN) with single T2-weighted FLAIR sequence to classify different cognitive performances in patients with subcortical ischemic vascular disease (SIVD). Totally 217 patients with SIVD (including 52 vascular dementia (VaD), 82 vascular mild cognitive impairment (VaMCI), 83 non-cognitive impairment (NCI)) and 46 matched healthy controls (HCs) underwent MRI scans and neuropsychological assessment. 2D and 3D CNNs were trained to classify VaD, VaMCI, NCI and HCs based on FLAIR data. For 3D-based model, loss curves of training set approached 0.017 after about 20 epochs, while the curves of testing set maintained at about 0.114. The accuracy of training set and testing set reached 99.7% and 96.9% after about 30 and 35 epochs, respectively. However, the accuracy of 2D-based model was only around 70%, which performed significantly worse than 3D-based model. This experiment suggests us that deep learning, is a powerful and convenient method to classify different cognitive performances in SIVD by extracting the shift and scale invariant features of neuroimaging data with single FLAIR sequence. 3D-CNN is superior to 2D-CNN which proposes clinical evaluation with MRI multiplanar reformation or volume scanning." @default.
- W2952091205 created "2019-06-27" @default.
- W2952091205 creator A5000970532 @default.
- W2952091205 creator A5009010657 @default.
- W2952091205 creator A5037106923 @default.
- W2952091205 creator A5043611587 @default.
- W2952091205 creator A5050974013 @default.
- W2952091205 creator A5056785665 @default.
- W2952091205 creator A5064168853 @default.
- W2952091205 creator A5079702840 @default.
- W2952091205 date "2019-06-19" @default.
- W2952091205 modified "2023-09-25" @default.
- W2952091205 title "Classification of Subcortical Vascular Cognitive Impairment Using Single MRI Sequence and Deep Learning Convolutional Neural Networks" @default.
- W2952091205 cites W1983364832 @default.
- W2952091205 cites W2035892177 @default.
- W2952091205 cites W2056092011 @default.
- W2952091205 cites W2060049009 @default.
- W2952091205 cites W2094879788 @default.
- W2952091205 cites W2104901197 @default.
- W2952091205 cites W2119017540 @default.
- W2952091205 cites W2294700319 @default.
- W2952091205 cites W2330945024 @default.
- W2952091205 cites W2343172899 @default.
- W2952091205 cites W2527609605 @default.
- W2952091205 cites W2579617530 @default.
- W2952091205 cites W2594257892 @default.
- W2952091205 cites W2602721434 @default.
- W2952091205 cites W2751538714 @default.
- W2952091205 cites W2765289999 @default.
- W2952091205 cites W2802159733 @default.
- W2952091205 cites W2805494981 @default.
- W2952091205 cites W4246904636 @default.
- W2952091205 doi "https://doi.org/10.3389/fnins.2019.00627" @default.
- W2952091205 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6593093" @default.
- W2952091205 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31275106" @default.
- W2952091205 hasPublicationYear "2019" @default.
- W2952091205 type Work @default.
- W2952091205 sameAs 2952091205 @default.
- W2952091205 citedByCount "9" @default.
- W2952091205 countsByYear W29520912052020 @default.
- W2952091205 countsByYear W29520912052021 @default.
- W2952091205 countsByYear W29520912052022 @default.
- W2952091205 countsByYear W29520912052023 @default.
- W2952091205 crossrefType "journal-article" @default.
- W2952091205 hasAuthorship W2952091205A5000970532 @default.
- W2952091205 hasAuthorship W2952091205A5009010657 @default.
- W2952091205 hasAuthorship W2952091205A5037106923 @default.
- W2952091205 hasAuthorship W2952091205A5043611587 @default.
- W2952091205 hasAuthorship W2952091205A5050974013 @default.
- W2952091205 hasAuthorship W2952091205A5056785665 @default.
- W2952091205 hasAuthorship W2952091205A5064168853 @default.
- W2952091205 hasAuthorship W2952091205A5079702840 @default.
- W2952091205 hasBestOaLocation W29520912051 @default.
- W2952091205 hasConcept C101070640 @default.
- W2952091205 hasConcept C108583219 @default.
- W2952091205 hasConcept C126838900 @default.
- W2952091205 hasConcept C142724271 @default.
- W2952091205 hasConcept C143409427 @default.
- W2952091205 hasConcept C153180895 @default.
- W2952091205 hasConcept C154945302 @default.
- W2952091205 hasConcept C15744967 @default.
- W2952091205 hasConcept C169760540 @default.
- W2952091205 hasConcept C169900460 @default.
- W2952091205 hasConcept C2777952318 @default.
- W2952091205 hasConcept C2779134260 @default.
- W2952091205 hasConcept C2779483572 @default.
- W2952091205 hasConcept C2984915365 @default.
- W2952091205 hasConcept C41008148 @default.
- W2952091205 hasConcept C58693492 @default.
- W2952091205 hasConcept C71924100 @default.
- W2952091205 hasConcept C81363708 @default.
- W2952091205 hasConceptScore W2952091205C101070640 @default.
- W2952091205 hasConceptScore W2952091205C108583219 @default.
- W2952091205 hasConceptScore W2952091205C126838900 @default.
- W2952091205 hasConceptScore W2952091205C142724271 @default.
- W2952091205 hasConceptScore W2952091205C143409427 @default.
- W2952091205 hasConceptScore W2952091205C153180895 @default.
- W2952091205 hasConceptScore W2952091205C154945302 @default.
- W2952091205 hasConceptScore W2952091205C15744967 @default.
- W2952091205 hasConceptScore W2952091205C169760540 @default.
- W2952091205 hasConceptScore W2952091205C169900460 @default.
- W2952091205 hasConceptScore W2952091205C2777952318 @default.
- W2952091205 hasConceptScore W2952091205C2779134260 @default.
- W2952091205 hasConceptScore W2952091205C2779483572 @default.
- W2952091205 hasConceptScore W2952091205C2984915365 @default.
- W2952091205 hasConceptScore W2952091205C41008148 @default.
- W2952091205 hasConceptScore W2952091205C58693492 @default.
- W2952091205 hasConceptScore W2952091205C71924100 @default.
- W2952091205 hasConceptScore W2952091205C81363708 @default.
- W2952091205 hasLocation W29520912051 @default.
- W2952091205 hasLocation W29520912052 @default.
- W2952091205 hasLocation W29520912053 @default.
- W2952091205 hasLocation W29520912054 @default.
- W2952091205 hasOpenAccess W2952091205 @default.
- W2952091205 hasPrimaryLocation W29520912051 @default.
- W2952091205 hasRelatedWork W2731899572 @default.
- W2952091205 hasRelatedWork W2738221750 @default.
- W2952091205 hasRelatedWork W3116150086 @default.
- W2952091205 hasRelatedWork W3133861977 @default.
- W2952091205 hasRelatedWork W3156786002 @default.