FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308372413> ?p ?o ?g. }

• W4308372413 endingPage "1449" @default.
• W4308372413 startingPage "1436" @default.
• W4308372413 abstract "Abstract Background The growing adoption of magnetic resonance imaging (MRI)‐guided radiation therapy (RT) platforms and a focus on MRI‐only RT workflows have brought the technical challenge of synthetic computed tomography (sCT) reconstruction to the forefront. Unpaired‐data deep learning‐based approaches to the problem offer the attractive characteristic of not requiring paired training data, but the gap between paired‐ and unpaired‐data results can be limiting. Purpose We present two distinct approaches aimed at improving unpaired‐data sCT reconstruction results: a cascade ensemble that combines multiple models and a personalized training strategy originally designed for the paired‐data setting. Methods Comparisons are made between the following models: (1) the paired‐data fully convolutional DenseNet (FCDN), (2) the FCDN with the Intentional Deep Overfit Learning (IDOL) personalized training strategy, (3) the unpaired‐data CycleGAN, (4) the CycleGAN with the IDOL training strategy, and (5) the CycleGAN as an intermediate model in a cascade ensemble approach. Evaluation of the various models over 25 total patients is carried out using a five‐fold cross‐validation scheme, with the patient‐specific IDOL models being trained for the five patients of fold 3, chosen at random. Results In both the paired‐ and unpaired‐data settings, adopting the IDOL training strategy led to improvements in the mean absolute error (MAE) between true CT images and sCT outputs within the body contour (mean improvement, paired‐ and unpaired‐data approaches, respectively: 38%, 9%) and in regions of bone (52%, 5%), the peak signal‐to‐noise ratio (PSNR; 15%, 7%), and the structural similarity index (SSIM; 6%, <1%). The ensemble approach offered additional benefits over the IDOL approach in all three metrics (mean improvement over unpaired‐data approach in fold 3; MAE: 20%; bone MAE: 16%; PSNR: 10%; SSIM: 2%), and differences in body MAE between the ensemble approach and the paired‐data approach are statistically insignificant. Conclusions We have demonstrated that both a cascade ensemble approach and a personalized training strategy designed initially for the paired‐data setting offer significant improvements in image quality metrics for the unpaired‐data sCT reconstruction task. Closing the gap between paired‐ and unpaired‐data approaches is a step toward fully enabling these powerful and attractive unpaired‐data frameworks." @default.
• W4308372413 created "2022-11-11" @default.
• W4308372413 creator A5008428605 @default.
• W4308372413 creator A5010930852 @default.
• W4308372413 creator A5018120191 @default.
• W4308372413 creator A5052009971 @default.
• W4308372413 creator A5063975729 @default.
• W4308372413 creator A5074004018 @default.
• W4308372413 creator A5075169323 @default.
• W4308372413 creator A5078413369 @default.
• W4308372413 creator A5088565244 @default.
• W4308372413 date "2022-12-17" @default.
• W4308372413 modified "2023-10-13" @default.
• W4308372413 title "Ensemble learning and personalized training for the improvement of unsupervised deep learning‐based synthetic CT reconstruction" @default.
• W4308372413 cites W1696976950 @default.
• W4308372413 cites W1822713087 @default.
• W4308372413 cites W2003320146 @default.
• W4308372413 cites W2036334364 @default.
• W4308372413 cites W2040357326 @default.
• W4308372413 cites W2048841289 @default.
• W4308372413 cites W2086711590 @default.
• W4308372413 cites W2088396407 @default.
• W4308372413 cites W2124048271 @default.
• W4308372413 cites W2133665775 @default.
• W4308372413 cites W2167221711 @default.
• W4308372413 cites W2559597482 @default.
• W4308372413 cites W2591910347 @default.
• W4308372413 cites W2621391388 @default.
• W4308372413 cites W2771678676 @default.
• W4308372413 cites W2790517211 @default.
• W4308372413 cites W2890645020 @default.
• W4308372413 cites W2890938833 @default.
• W4308372413 cites W2891285439 @default.
• W4308372413 cites W2895910545 @default.
• W4308372413 cites W2896483746 @default.
• W4308372413 cites W2898871261 @default.
• W4308372413 cites W2932100613 @default.
• W4308372413 cites W2938615434 @default.
• W4308372413 cites W2945263066 @default.
• W4308372413 cites W2952935478 @default.
• W4308372413 cites W2955448382 @default.
• W4308372413 cites W2957014213 @default.
• W4308372413 cites W2962891897 @default.
• W4308372413 cites W2971604258 @default.
• W4308372413 cites W2982718246 @default.
• W4308372413 cites W3013025543 @default.
• W4308372413 cites W3038260786 @default.
• W4308372413 cites W3048439504 @default.
• W4308372413 cites W3088358581 @default.
• W4308372413 cites W3092871161 @default.
• W4308372413 cites W3093026731 @default.
• W4308372413 cites W3096732628 @default.
• W4308372413 cites W3101123465 @default.
• W4308372413 cites W3108462927 @default.
• W4308372413 cites W3115133834 @default.
• W4308372413 cites W3116201895 @default.
• W4308372413 cites W3194266415 @default.
• W4308372413 cites W3212480182 @default.
• W4308372413 cites W4252684946 @default.
• W4308372413 doi "https://doi.org/10.1002/mp.16087" @default.
• W4308372413 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36336718" @default.
• W4308372413 hasPublicationYear "2022" @default.
• W4308372413 type Work @default.
• W4308372413 citedByCount "1" @default.
• W4308372413 crossrefType "journal-article" @default.
• W4308372413 hasAuthorship W4308372413A5008428605 @default.
• W4308372413 hasAuthorship W4308372413A5010930852 @default.
• W4308372413 hasAuthorship W4308372413A5018120191 @default.
• W4308372413 hasAuthorship W4308372413A5052009971 @default.
• W4308372413 hasAuthorship W4308372413A5063975729 @default.
• W4308372413 hasAuthorship W4308372413A5074004018 @default.
• W4308372413 hasAuthorship W4308372413A5075169323 @default.
• W4308372413 hasAuthorship W4308372413A5078413369 @default.
• W4308372413 hasAuthorship W4308372413A5088565244 @default.
• W4308372413 hasConcept C108583219 @default.
• W4308372413 hasConcept C119857082 @default.
• W4308372413 hasConcept C153180895 @default.
• W4308372413 hasConcept C154945302 @default.
• W4308372413 hasConcept C22019652 @default.
• W4308372413 hasConcept C41008148 @default.
• W4308372413 hasConcept C50644808 @default.
• W4308372413 hasConceptScore W4308372413C108583219 @default.
• W4308372413 hasConceptScore W4308372413C119857082 @default.
• W4308372413 hasConceptScore W4308372413C153180895 @default.
• W4308372413 hasConceptScore W4308372413C154945302 @default.
• W4308372413 hasConceptScore W4308372413C22019652 @default.
• W4308372413 hasConceptScore W4308372413C41008148 @default.
• W4308372413 hasConceptScore W4308372413C50644808 @default.
• W4308372413 hasFunder F4320322120 @default.
• W4308372413 hasIssue "3" @default.
• W4308372413 hasLocation W43083724131 @default.
• W4308372413 hasLocation W43083724132 @default.
• W4308372413 hasOpenAccess W4308372413 @default.
• W4308372413 hasPrimaryLocation W43083724131 @default.
• W4308372413 hasRelatedWork W2989932438 @default.
• W4308372413 hasRelatedWork W3035162004 @default.
• W4308372413 hasRelatedWork W3099765033 @default.
• W4308372413 hasRelatedWork W4210794429 @default.

• next