FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292581577> ?p ?o ?g. }

• W4292581577 endingPage "104092" @default.
• W4292581577 startingPage "104092" @default.
• W4292581577 abstract "• Imbalanced class samples using machine learning model accuracy is biased to majority sample class. • Build transfer learning model using balanced random forest for the classification of healthy aging controls, mild cognitive impairment and Alzheimer’s disease based on diffusion tensor and kurtosis features such as fractional anisotropy and mean diffusivity. • Among existing imbalanced classifiers, ensemble of structural expansion reduction and structure transfer with thresholding using balanced random forest outperformed compared to existing random oversampling and undersampling models. • Transfer learning classifier achieved an overall accuracy of 0.79 for tensor as source and kurtosis features as target. Automated classification of dementia stage using imaging will be useful for clinical diagnosis and the classification accuracy will be biased for highly imbalanced samples in each class. Hence, we propose a novel approach using transfer learning-based structural significance (TLSS) for the classification of cognitively normal controls (CN), mild cognitive impairment (MCI) and Alzheimer’s disease (AD) patients based on white matter Gaussian diffusion (tensor) indices and non-Gaussian diffusion (kurtosis) indices. The structural T1-weighted magnetic resonance imaging and diffusion images were taken from ADNI dataset with 44 CN, 84 MCI and 22 AD patients. We estimate the regional Gaussian diffusion indices such as tensor fractional anisotropy (TFA) and mean diffusivity (TMD) as well as non-Gaussian diffusion indices such as kurtosis fractional anisotropy (KFA) and kurtosis mean diffusivity (KMD) in white matter regions. Further, we build transfer learning model using various balanced classifiers with structural expansion reduction (SER) and structure transfer using threshold (STT) and ensemble of majority voting of both SER and STT algorithms. We build two models by training the source model using kurtosis indices, refine the model on target tensor indices and vice versa. Transfer learning model using balanced random forest classifier was able to classify and predict all the groups with an overall accuracy about 0.79 using ensemble of SER and STT forests rather than individual algorithms (SER and STT). Our results conclude that the proposed model using kurtosis indices as source model classified and predicted with accuracies of 0.96, 0.72 and 0.7 in classifying CN vs AD, CN vs MCI and AD vs MCI respectively. To conclude, the proposed approach has improved the classification accuracy and its potential applicability for imbalanced data sample datasets." @default.
• W4292581577 created "2022-08-22" @default.
• W4292581577 creator A5067966408 @default.
• W4292581577 creator A5087331272 @default.
• W4292581577 date "2023-01-01" @default.
• W4292581577 modified "2023-10-17" @default.
• W4292581577 title "Classification of cognitively normal controls, mild cognitive impairment and Alzheimer’s disease using transfer learning approach" @default.
• W4292581577 cites W1549913927 @default.
• W4292581577 cites W1889554236 @default.
• W4292581577 cites W1922152597 @default.
• W4292581577 cites W1931116562 @default.
• W4292581577 cites W1964802316 @default.
• W4292581577 cites W1974874858 @default.
• W4292581577 cites W1983485726 @default.
• W4292581577 cites W2006096283 @default.
• W4292581577 cites W2024366952 @default.
• W4292581577 cites W2028748733 @default.
• W4292581577 cites W2033088751 @default.
• W4292581577 cites W2034957516 @default.
• W4292581577 cites W2051568462 @default.
• W4292581577 cites W2056756297 @default.
• W4292581577 cites W2081237186 @default.
• W4292581577 cites W2096945460 @default.
• W4292581577 cites W2116823839 @default.
• W4292581577 cites W2117987496 @default.
• W4292581577 cites W2126598020 @default.
• W4292581577 cites W2142554529 @default.
• W4292581577 cites W2148143831 @default.
• W4292581577 cites W2150667092 @default.
• W4292581577 cites W2151712416 @default.
• W4292581577 cites W2156040424 @default.
• W4292581577 cites W2229387242 @default.
• W4292581577 cites W2282204559 @default.
• W4292581577 cites W2307232592 @default.
• W4292581577 cites W2413582275 @default.
• W4292581577 cites W2516294107 @default.
• W4292581577 cites W2587671911 @default.
• W4292581577 cites W2749592990 @default.
• W4292581577 cites W2776959505 @default.
• W4292581577 cites W2780705833 @default.
• W4292581577 cites W2791831747 @default.
• W4292581577 cites W2793804994 @default.
• W4292581577 cites W2799428269 @default.
• W4292581577 cites W2804823091 @default.
• W4292581577 cites W2805773775 @default.
• W4292581577 cites W281036081 @default.
• W4292581577 cites W2887206520 @default.
• W4292581577 cites W2895106932 @default.
• W4292581577 cites W2899335103 @default.
• W4292581577 cites W2900207682 @default.
• W4292581577 cites W2900386946 @default.
• W4292581577 cites W2904590633 @default.
• W4292581577 cites W2905035821 @default.
• W4292581577 cites W2911964244 @default.
• W4292581577 cites W2951488689 @default.
• W4292581577 cites W2957629889 @default.
• W4292581577 cites W2962681100 @default.
• W4292581577 cites W2963168174 @default.
• W4292581577 cites W2964899219 @default.
• W4292581577 cites W2969356652 @default.
• W4292581577 cites W2972411153 @default.
• W4292581577 cites W2972532822 @default.
• W4292581577 cites W2977087659 @default.
• W4292581577 cites W2981493641 @default.
• W4292581577 cites W2991561240 @default.
• W4292581577 cites W2995495466 @default.
• W4292581577 cites W2996722826 @default.
• W4292581577 cites W2997873617 @default.
• W4292581577 cites W2998642388 @default.
• W4292581577 cites W3000134386 @default.
• W4292581577 cites W3006901343 @default.
• W4292581577 cites W3007568584 @default.
• W4292581577 cites W3012701165 @default.
• W4292581577 cites W3026272888 @default.
• W4292581577 cites W3045895067 @default.
• W4292581577 cites W3046162593 @default.
• W4292581577 cites W3124084750 @default.
• W4292581577 cites W3147281958 @default.
• W4292581577 cites W3184921360 @default.
• W4292581577 cites W4235770099 @default.
• W4292581577 doi "https://doi.org/10.1016/j.bspc.2022.104092" @default.
• W4292581577 hasPublicationYear "2023" @default.
• W4292581577 type Work @default.
• W4292581577 citedByCount "2" @default.
• W4292581577 countsByYear W42925815772022 @default.
• W4292581577 crossrefType "journal-article" @default.
• W4292581577 hasAuthorship W4292581577A5067966408 @default.
• W4292581577 hasAuthorship W4292581577A5087331272 @default.
• W4292581577 hasConcept C126322002 @default.
• W4292581577 hasConcept C150899416 @default.
• W4292581577 hasConcept C154945302 @default.
• W4292581577 hasConcept C15744967 @default.
• W4292581577 hasConcept C169760540 @default.
• W4292581577 hasConcept C169900460 @default.
• W4292581577 hasConcept C180747234 @default.
• W4292581577 hasConcept C2779134260 @default.
• W4292581577 hasConcept C2984915365 @default.
• W4292581577 hasConcept C41008148 @default.

• next