FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294542672> ?p ?o ?g. }

• W4294542672 endingPage "195014" @default.
• W4294542672 startingPage "195014" @default.
• W4294542672 abstract "Abstract Objective . Neuroimaging uncovers important information about disease in the brain. Yet in Alzheimer’s disease (AD), there remains a clear clinical need for reliable tools to extract diagnoses from neuroimages. Significant work has been done to develop deep learning (DL) networks using neuroimaging for AD diagnosis. However, no particular model has emerged as optimal. Due to a lack of direct comparisons and evaluations on independent data, there is no consensus on which modality is best for diagnostic models or whether longitudinal information enhances performance. The purpose of this work was (1) to develop a generalizable DL model to distinguish neuroimaging scans of AD patients from controls and (2) to evaluate the influence of imaging modality and longitudinal data on performance. Approach . We trained a 2-class convolutional neural network (CNN) with and without a cascaded recurrent neural network (RNN). We used datasets of 772 ( N AD = 364, N control = 408) 3D 18 F-FDG PET scans and 780 ( N AD = 280, N control = 500) T1-weighted volumetric-3D MR images (containing 131 and 144 patients with multiple timepoints) from the Alzheimer’s Disease Neuroimaging Initiative, plus an independent set of 104 ( N AD = 63, N NC = 41) 18 F-FDG PET scans (one per patient) for validation. Main Results . ROC analysis showed that PET-trained models outperformed MRI-trained, achieving maximum AUC with the CNN + RNN model of 0.93 ± 0.08, with accuracy 82.5 ± 8.9%. Adding longitudinal information offered significant improvement to performance on 18 F-FDG PET, but not on T1-MRI. CNN model validation with an independent 18 F-FDG PET dataset achieved AUC of 0.99. Layer-wise relevance propagation heatmaps added CNN interpretability. Significance . The development of a high-performing tool for AD diagnosis, with the direct evaluation of key influences, reveals the advantage of using 18 F-FDG PET and longitudinal data over MRI and single timepoint analysis. This has significant implications for the potential of neuroimaging for future research on AD diagnosis and clinical management of suspected AD patients." @default.
• W4294542672 created "2022-09-04" @default.
• W4294542672 creator A5030203098 @default.
• W4294542672 creator A5051994581 @default.
• W4294542672 creator A5052737617 @default.
• W4294542672 creator A5058233829 @default.
• W4294542672 creator A5089876909 @default.
• W4294542672 date "2022-09-30" @default.
• W4294542672 modified "2023-10-18" @default.
• W4294542672 title "Development of a deep learning network for Alzheimer’s disease classification with evaluation of imaging modality and longitudinal data" @default.
• W4294542672 cites W1543528560 @default.
• W4294542672 cites W1594504409 @default.
• W4294542672 cites W1787224781 @default.
• W4294542672 cites W1829865020 @default.
• W4294542672 cites W1974300727 @default.
• W4294542672 cites W1992054897 @default.
• W4294542672 cites W1994605917 @default.
• W4294542672 cites W2000574253 @default.
• W4294542672 cites W2015259521 @default.
• W4294542672 cites W2052041752 @default.
• W4294542672 cites W2079073956 @default.
• W4294542672 cites W2079436233 @default.
• W4294542672 cites W2095448457 @default.
• W4294542672 cites W2112282608 @default.
• W4294542672 cites W2115017507 @default.
• W4294542672 cites W2157331557 @default.
• W4294542672 cites W2240067561 @default.
• W4294542672 cites W2318136407 @default.
• W4294542672 cites W2473213662 @default.
• W4294542672 cites W2531409750 @default.
• W4294542672 cites W2586179392 @default.
• W4294542672 cites W2591527562 @default.
• W4294542672 cites W2605106061 @default.
• W4294542672 cites W2606546398 @default.
• W4294542672 cites W2762081760 @default.
• W4294542672 cites W2776207810 @default.
• W4294542672 cites W2784075654 @default.
• W4294542672 cites W2787666045 @default.
• W4294542672 cites W2795824182 @default.
• W4294542672 cites W2798054687 @default.
• W4294542672 cites W2805773775 @default.
• W4294542672 cites W2884124469 @default.
• W4294542672 cites W2899635607 @default.
• W4294542672 cites W2901799306 @default.
• W4294542672 cites W2908469802 @default.
• W4294542672 cites W2912541111 @default.
• W4294542672 cites W2914209001 @default.
• W4294542672 cites W2916257687 @default.
• W4294542672 cites W2936290332 @default.
• W4294542672 cites W2936503027 @default.
• W4294542672 cites W2939845202 @default.
• W4294542672 cites W2950680182 @default.
• W4294542672 cites W2956993163 @default.
• W4294542672 cites W2958884855 @default.
• W4294542672 cites W2960986212 @default.
• W4294542672 cites W2964171289 @default.
• W4294542672 cites W2964629181 @default.
• W4294542672 cites W3002097015 @default.
• W4294542672 cites W3021241070 @default.
• W4294542672 cites W3033804370 @default.
• W4294542672 cites W3158108213 @default.
• W4294542672 cites W4211050998 @default.
• W4294542672 cites W4285032751 @default.
• W4294542672 doi "https://doi.org/10.1088/1361-6560/ac8f10" @default.
• W4294542672 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36055243" @default.
• W4294542672 hasPublicationYear "2022" @default.
• W4294542672 type Work @default.
• W4294542672 citedByCount "0" @default.
• W4294542672 crossrefType "journal-article" @default.
• W4294542672 hasAuthorship W4294542672A5030203098 @default.
• W4294542672 hasAuthorship W4294542672A5051994581 @default.
• W4294542672 hasAuthorship W4294542672A5052737617 @default.
• W4294542672 hasAuthorship W4294542672A5058233829 @default.
• W4294542672 hasAuthorship W4294542672A5089876909 @default.
• W4294542672 hasConcept C108583219 @default.
• W4294542672 hasConcept C119857082 @default.
• W4294542672 hasConcept C126838900 @default.
• W4294542672 hasConcept C142724271 @default.
• W4294542672 hasConcept C154945302 @default.
• W4294542672 hasConcept C15744967 @default.
• W4294542672 hasConcept C169760540 @default.
• W4294542672 hasConcept C177264268 @default.
• W4294542672 hasConcept C199360897 @default.
• W4294542672 hasConcept C2778373026 @default.
• W4294542672 hasConcept C2779134260 @default.
• W4294542672 hasConcept C2780226545 @default.
• W4294542672 hasConcept C2989005 @default.
• W4294542672 hasConcept C41008148 @default.
• W4294542672 hasConcept C502032728 @default.
• W4294542672 hasConcept C534262118 @default.
• W4294542672 hasConcept C58693492 @default.
• W4294542672 hasConcept C71924100 @default.
• W4294542672 hasConcept C81363708 @default.
• W4294542672 hasConceptScore W4294542672C108583219 @default.
• W4294542672 hasConceptScore W4294542672C119857082 @default.
• W4294542672 hasConceptScore W4294542672C126838900 @default.
• W4294542672 hasConceptScore W4294542672C142724271 @default.
• W4294542672 hasConceptScore W4294542672C154945302 @default.

• next