FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3166650482> ?p ?o ?g. }

• W3166650482 endingPage "2265" @default.
• W3166650482 startingPage "2250" @default.
• W3166650482 abstract "Purpose Earlier work showed that IVIM-NETorig, an unsupervised physics-informed deep neural network, was faster and more accurate than other state-of-the-art intravoxel-incoherent motion (IVIM) fitting approaches to diffusion-weighted imaging (DWI). This study presents a substantially improved version, IVIM-NEToptim, and characterizes its superior performance in pancreatic cancer patients. Method In simulations (signal-to-noise ratio [SNR] = 20), the accuracy, independence, and consistency of IVIM-NET were evaluated for combinations of hyperparameters (fit S0, constraints, network architecture, number of hidden layers, dropout, batch normalization, learning rate), by calculating the normalized root-mean-square error (NRMSE), Spearman’s ρ, and the coefficient of variation (CVNET), respectively. The best performing network, IVIM-NEToptim was compared to least squares (LS) and a Bayesian approach at different SNRs. IVIM-NEToptim’s performance was evaluated in an independent dataset of 23 patients with pancreatic ductal adenocarcinoma. Fourteen of the patients received no treatment between two repeated scan sessions and nine received chemoradiotherapy between the repeated sessions. Intersession within-subject standard deviations (wSD) and treatment-induced changes were assessed. Results In simulations (SNR = 20), IVIM-NEToptim outperformed IVIM-NETorig in accuracy (NRMSE(D) = 0.177 vs 0.196; NMRSE(f) = 0.220 vs 0.267; NMRSE(D*) = 0.386 vs 0.393), independence (ρ(D*, f) = 0.22 vs 0.74), and consistency (CVNET(D) = 0.013 vs 0.104; CVNET(f) = 0.020 vs 0.054; CVNET(D*) = 0.036 vs 0.110). IVIM-NEToptim showed superior performance to the LS and Bayesian approaches at SNRs < 50. In vivo, IVIM-NEToptim showed significantly less noisy parameter maps with lower wSD for D and f than the alternatives. In the treated cohort, IVIM-NEToptim detected the most individual patients with significant parameter changes compared to day-to-day variations. Conclusion IVIM-NEToptim is recommended for accurate, informative, and consistent IVIM fitting to DWI data." @default.
• W3166650482 created "2021-06-22" @default.
• W3166650482 creator A5001020783 @default.
• W3166650482 creator A5012050627 @default.
• W3166650482 creator A5033997225 @default.
• W3166650482 creator A5036513594 @default.
• W3166650482 creator A5051806723 @default.
• W3166650482 creator A5060506055 @default.
• W3166650482 creator A5070504139 @default.
• W3166650482 creator A5073552513 @default.
• W3166650482 date "2021-06-09" @default.
• W3166650482 modified "2023-10-17" @default.
• W3166650482 title "Improved unsupervised physics‐informed deep learning for intravoxel incoherent motion modeling and evaluation in pancreatic cancer patients" @default.
• W3166650482 cites W1588500259 @default.
• W3166650482 cites W1593778750 @default.
• W3166650482 cites W1600280496 @default.
• W3166650482 cites W1892086843 @default.
• W3166650482 cites W1909415290 @default.
• W3166650482 cites W1980842095 @default.
• W3166650482 cites W1988909308 @default.
• W3166650482 cites W1994973885 @default.
• W3166650482 cites W1995305800 @default.
• W3166650482 cites W2023173554 @default.
• W3166650482 cites W2087070363 @default.
• W3166650482 cites W2108358495 @default.
• W3166650482 cites W2119951714 @default.
• W3166650482 cites W2133287637 @default.
• W3166650482 cites W2139794744 @default.
• W3166650482 cites W2164757470 @default.
• W3166650482 cites W2167475776 @default.
• W3166650482 cites W2196064850 @default.
• W3166650482 cites W2217483959 @default.
• W3166650482 cites W2256578114 @default.
• W3166650482 cites W2265208154 @default.
• W3166650482 cites W2269740635 @default.
• W3166650482 cites W2515445163 @default.
• W3166650482 cites W2580767461 @default.
• W3166650482 cites W2594758671 @default.
• W3166650482 cites W2600460036 @default.
• W3166650482 cites W2604388535 @default.
• W3166650482 cites W2745896849 @default.
• W3166650482 cites W2757241032 @default.
• W3166650482 cites W2771070570 @default.
• W3166650482 cites W2793290272 @default.
• W3166650482 cites W2795556240 @default.
• W3166650482 cites W2802322200 @default.
• W3166650482 cites W2802808371 @default.
• W3166650482 cites W2887887303 @default.
• W3166650482 cites W2888552388 @default.
• W3166650482 cites W2888918056 @default.
• W3166650482 cites W2911733085 @default.
• W3166650482 cites W2940107474 @default.
• W3166650482 cites W2960106194 @default.
• W3166650482 cites W2966242695 @default.
• W3166650482 cites W3008190574 @default.
• W3166650482 cites W3015389052 @default.
• W3166650482 cites W3022519457 @default.
• W3166650482 cites W4248808158 @default.
• W3166650482 doi "https://doi.org/10.1002/mrm.28852" @default.
• W3166650482 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8362093" @default.
• W3166650482 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34105184" @default.
• W3166650482 hasPublicationYear "2021" @default.
• W3166650482 type Work @default.
• W3166650482 sameAs 3166650482 @default.
• W3166650482 citedByCount "32" @default.
• W3166650482 countsByYear W31666504822021 @default.
• W3166650482 countsByYear W31666504822022 @default.
• W3166650482 countsByYear W31666504822023 @default.
• W3166650482 crossrefType "journal-article" @default.
• W3166650482 hasAuthorship W3166650482A5001020783 @default.
• W3166650482 hasAuthorship W3166650482A5012050627 @default.
• W3166650482 hasAuthorship W3166650482A5033997225 @default.
• W3166650482 hasAuthorship W3166650482A5036513594 @default.
• W3166650482 hasAuthorship W3166650482A5051806723 @default.
• W3166650482 hasAuthorship W3166650482A5060506055 @default.
• W3166650482 hasAuthorship W3166650482A5070504139 @default.
• W3166650482 hasAuthorship W3166650482A5073552513 @default.
• W3166650482 hasBestOaLocation W31666504821 @default.
• W3166650482 hasConcept C121608353 @default.
• W3166650482 hasConcept C126322002 @default.
• W3166650482 hasConcept C126838900 @default.
• W3166650482 hasConcept C143409427 @default.
• W3166650482 hasConcept C154945302 @default.
• W3166650482 hasConcept C2780210213 @default.
• W3166650482 hasConcept C2989005 @default.
• W3166650482 hasConcept C33923547 @default.
• W3166650482 hasConcept C41008148 @default.
• W3166650482 hasConcept C70816921 @default.
• W3166650482 hasConcept C71924100 @default.
• W3166650482 hasConcept C82641631 @default.
• W3166650482 hasConceptScore W3166650482C121608353 @default.
• W3166650482 hasConceptScore W3166650482C126322002 @default.
• W3166650482 hasConceptScore W3166650482C126838900 @default.
• W3166650482 hasConceptScore W3166650482C143409427 @default.
• W3166650482 hasConceptScore W3166650482C154945302 @default.
• W3166650482 hasConceptScore W3166650482C2780210213 @default.
• W3166650482 hasConceptScore W3166650482C2989005 @default.
• W3166650482 hasConceptScore W3166650482C33923547 @default.

• next