FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4235741312> ?p ?o ?g. }

• W4235741312 abstract "Classification of dementia based on measures of brain volume has been studied previously. However, many of these studies use clinical diagnosis as the gold standard and/or investigate group separation of particular dementias from healthy controls. In this study, we investigate the more clinically important problem of differential diagnosis of cases with pathologically confirmed Alzheimer's disease (AD), dementia with Lewy bodies (DLB), frontotemporal lobar degeneration (FTLD) or other pathology. Using retrospective data from patients who attended clinics in three different European centres (VUMC-Amsterdam, DRC-London, IAH-Newcastle) we evaluated the diagnostic utility of applying automated segmentation and machine learning to this clinically realistic dataset. Multi-label segmentation propagation, based on 83 manually segmented regions from 30 subjects, was applied to T1-weighted volumetric MRI scans from 305 patients with pathologically-confirmed dementia (127 AD, 49 DLB, 80 FTLD, 49 other). Segmented volumes were corrected for age, gender, total intracranial volume and scanner, then scaled to zero mean and unit variance over subjects. The dataset was then divided into training (n=153) and testing sets (n=152), preserving pathology proportions. Univariate feature selection was applied such that only the top 10% of regions most important for prediction were used in the models. Group separation was quantified using a linear support vector machine with cross-validation. Class weighting was applied to adjust for unbalanced groups. Three classifiers were trained to separate each of the three main dementia groups from the pooled group of all other dementias. A further three classifiers were trained to discriminate each pair of the main dementia groups. Feature selection demonstrated higher accuracies for group separation than using all features. Central structures including the putamen, thalamus and substantia nigra, and temporal lobe regions helped to distinguish FTLD from DLB. AD and FTLD were best distinguished using frontal/occipital lobe regions, and AD and DLB using temporal/parietal regions (Table1). Classification accuracy was greatest for AD pathology in all models (Figure1). Classification of dementia pathology based on brain substructure volumes may help to maximise the diagnostic information available from clinical T1-weighted MRI. Performing feature selection using these volumes in autopsy-confirmed subjects could identify brain regions with diagnostic specificity for particular pathologies. A) 3 separate SVMs trained to classify each of the 3 main dementia groups from the pooled group of other dementias. B) A further 3 classifiers trained to discriminate each pair of the main dementia groups. Performance of each SVM is summarised by the area under the curve of the receiver operator characteristic with 95% confidence intervals in brackets." @default.
• W4235741312 created "2022-05-12" @default.
• W4235741312 creator A5018836358 @default.
• W4235741312 creator A5034672217 @default.
• W4235741312 creator A5038279757 @default.
• W4235741312 creator A5039782136 @default.
• W4235741312 creator A5044054341 @default.
• W4235741312 creator A5072840179 @default.
• W4235741312 creator A5076585111 @default.
• W4235741312 creator A5083858846 @default.
• W4235741312 creator A5084764704 @default.
• W4235741312 creator A5090278707 @default.
• W4235741312 date "2014-07-01" @default.
• W4235741312 modified "2023-10-17" @default.
• W4235741312 title "P2-190: CLASSIFICATION OF PATHOLOGY USING BRAIN SUBSTRUCTURE VOLUMES IN POSTMORTEM CONFIRMED DEMENTIAS" @default.
• W4235741312 doi "https://doi.org/10.1016/j.jalz.2014.05.866" @default.
• W4235741312 hasPublicationYear "2014" @default.
• W4235741312 type Work @default.
• W4235741312 citedByCount "0" @default.
• W4235741312 crossrefType "journal-article" @default.
• W4235741312 hasAuthorship W4235741312A5018836358 @default.
• W4235741312 hasAuthorship W4235741312A5034672217 @default.
• W4235741312 hasAuthorship W4235741312A5038279757 @default.
• W4235741312 hasAuthorship W4235741312A5039782136 @default.
• W4235741312 hasAuthorship W4235741312A5044054341 @default.
• W4235741312 hasAuthorship W4235741312A5072840179 @default.
• W4235741312 hasAuthorship W4235741312A5076585111 @default.
• W4235741312 hasAuthorship W4235741312A5083858846 @default.
• W4235741312 hasAuthorship W4235741312A5084764704 @default.
• W4235741312 hasAuthorship W4235741312A5090278707 @default.
• W4235741312 hasConcept C142724271 @default.
• W4235741312 hasConcept C153180895 @default.
• W4235741312 hasConcept C154945302 @default.
• W4235741312 hasConcept C2776939681 @default.
• W4235741312 hasConcept C2778548049 @default.
• W4235741312 hasConcept C2778641062 @default.
• W4235741312 hasConcept C2779134260 @default.
• W4235741312 hasConcept C2779483572 @default.
• W4235741312 hasConcept C41008148 @default.
• W4235741312 hasConcept C71924100 @default.
• W4235741312 hasConceptScore W4235741312C142724271 @default.
• W4235741312 hasConceptScore W4235741312C153180895 @default.
• W4235741312 hasConceptScore W4235741312C154945302 @default.
• W4235741312 hasConceptScore W4235741312C2776939681 @default.
• W4235741312 hasConceptScore W4235741312C2778548049 @default.
• W4235741312 hasConceptScore W4235741312C2778641062 @default.
• W4235741312 hasConceptScore W4235741312C2779134260 @default.
• W4235741312 hasConceptScore W4235741312C2779483572 @default.
• W4235741312 hasConceptScore W4235741312C41008148 @default.
• W4235741312 hasConceptScore W4235741312C71924100 @default.
• W4235741312 hasIssue "4S_Part_14" @default.
• W4235741312 hasLocation W42357413121 @default.
• W4235741312 hasOpenAccess W4235741312 @default.
• W4235741312 hasPrimaryLocation W42357413121 @default.
• W4235741312 hasRelatedWork W171937741 @default.
• W4235741312 hasRelatedWork W1982087296 @default.
• W4235741312 hasRelatedWork W2012509939 @default.
• W4235741312 hasRelatedWork W2049309389 @default.
• W4235741312 hasRelatedWork W2099557977 @default.
• W4235741312 hasRelatedWork W2134845175 @default.
• W4235741312 hasRelatedWork W2169680091 @default.
• W4235741312 hasRelatedWork W4237705864 @default.
• W4235741312 hasRelatedWork W4238328882 @default.
• W4235741312 hasRelatedWork W4292580283 @default.
• W4235741312 hasVolume "10" @default.
• W4235741312 isParatext "false" @default.
• W4235741312 isRetracted "false" @default.
• W4235741312 workType "article" @default.