FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280521107> ?p ?o ?g. }

• W4280521107 endingPage "115010" @default.
• W4280521107 startingPage "115010" @default.
• W4280521107 abstract "Proton therapy requires accurate dose calculation for treatment planning to ensure the conformal doses are precisely delivered to the targets. The conversion of CT numbers to material properties is a significant source of uncertainty for dose calculation. The aim of this study is to develop a physics-informed deep learning (PIDL) framework to derive accurate mass density and relative stopping power maps from dual-energy computed tomography (DECT) images. The PIDL framework allows deep learning (DL) models to be trained with a physics loss function, which includes a physics model to constrain DL models. Five DL models were implemented including a fully connected neural network (FCNN), dual-FCNN (DFCNN), and three variants of residual networks (ResNet): ResNet-v1 (RN-v1), ResNet-v2 (RN-v2), and dual-ResNet-v2 (DRN-v2). An artificial neural network (ANN) and the five DL models trained with and without physics loss were explored to evaluate the PIDL framework. Two empirical DECT models were implemented to compare with the PIDL method. DL training data were from CIRS electron density phantom 062M (Computerized Imaging Reference Systems, Inc., Norfolk, VA). The performance of DL models was tested by CIRS adult male, adult female, and 5-year-old child anthropomorphic phantoms. For density map inference, the physics-informed RN-v2 was 3.3%, 2.9% and 1.9% more accurate than ANN for the adult male, adult female, and child phantoms. The physics-informed DRN-v2 was 0.7%, 0.6%, and 0.8% more accurate than DRN-v2 without physics training for the three phantoms, respectfully. The results indicated that physics-informed training could reduce uncertainty when ANN/DL models without physics training were insufficient to capture data structures or derived significant errors. DL models could also achieve better image noise control compared to the empirical DECT parametric mapping methods. The proposed PIDL framework can potentially improve proton range uncertainty by offering accurate material properties conversion from DECT." @default.
• W4280521107 created "2022-05-22" @default.
• W4280521107 creator A5005298316 @default.
• W4280521107 creator A5006051150 @default.
• W4280521107 creator A5006765797 @default.
• W4280521107 creator A5010012421 @default.
• W4280521107 creator A5011903902 @default.
• W4280521107 creator A5030054597 @default.
• W4280521107 creator A5032192226 @default.
• W4280521107 creator A5046225712 @default.
• W4280521107 creator A5049656223 @default.
• W4280521107 creator A5055677011 @default.
• W4280521107 creator A5055954787 @default.
• W4280521107 creator A5062115647 @default.
• W4280521107 date "2022-05-26" @default.
• W4280521107 modified "2023-10-13" @default.
• W4280521107 title "Dual-energy CT based mass density and relative stopping power estimation for proton therapy using physics-informed deep learning" @default.
• W4280521107 cites W1761022139 @default.
• W4280521107 cites W1899504021 @default.
• W4280521107 cites W1926920987 @default.
• W4280521107 cites W1978369884 @default.
• W4280521107 cites W1986760892 @default.
• W4280521107 cites W1998088861 @default.
• W4280521107 cites W1999189079 @default.
• W4280521107 cites W2001583012 @default.
• W4280521107 cites W2001881071 @default.
• W4280521107 cites W2002025007 @default.
• W4280521107 cites W2015282797 @default.
• W4280521107 cites W2022717269 @default.
• W4280521107 cites W2026421256 @default.
• W4280521107 cites W2040337964 @default.
• W4280521107 cites W2045415729 @default.
• W4280521107 cites W2070902649 @default.
• W4280521107 cites W2076063813 @default.
• W4280521107 cites W2085188303 @default.
• W4280521107 cites W2089573650 @default.
• W4280521107 cites W2101926813 @default.
• W4280521107 cites W2111001758 @default.
• W4280521107 cites W2111938309 @default.
• W4280521107 cites W2137983211 @default.
• W4280521107 cites W2145700610 @default.
• W4280521107 cites W2194775991 @default.
• W4280521107 cites W2195164371 @default.
• W4280521107 cites W2386623903 @default.
• W4280521107 cites W2536323247 @default.
• W4280521107 cites W2598431361 @default.
• W4280521107 cites W2740406916 @default.
• W4280521107 cites W2747734032 @default.
• W4280521107 cites W2755347499 @default.
• W4280521107 cites W2784795157 @default.
• W4280521107 cites W2787348589 @default.
• W4280521107 cites W2803663917 @default.
• W4280521107 cites W2885150276 @default.
• W4280521107 cites W2895945500 @default.
• W4280521107 cites W2903413206 @default.
• W4280521107 cites W2911733495 @default.
• W4280521107 cites W2919115771 @default.
• W4280521107 cites W2945426957 @default.
• W4280521107 cites W2980501212 @default.
• W4280521107 cites W2981906852 @default.
• W4280521107 cites W2999653270 @default.
• W4280521107 cites W3087119976 @default.
• W4280521107 cites W3099147628 @default.
• W4280521107 cites W3163993681 @default.
• W4280521107 cites W3165785688 @default.
• W4280521107 cites W3174518097 @default.
• W4280521107 cites W3202641460 @default.
• W4280521107 doi "https://doi.org/10.1088/1361-6560/ac6ebc" @default.
• W4280521107 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35545078" @default.
• W4280521107 hasPublicationYear "2022" @default.
• W4280521107 type Work @default.
• W4280521107 citedByCount "9" @default.
• W4280521107 countsByYear W42805211072022 @default.
• W4280521107 countsByYear W42805211072023 @default.
• W4280521107 crossrefType "journal-article" @default.
• W4280521107 hasAuthorship W4280521107A5005298316 @default.
• W4280521107 hasAuthorship W4280521107A5006051150 @default.
• W4280521107 hasAuthorship W4280521107A5006765797 @default.
• W4280521107 hasAuthorship W4280521107A5010012421 @default.
• W4280521107 hasAuthorship W4280521107A5011903902 @default.
• W4280521107 hasAuthorship W4280521107A5030054597 @default.
• W4280521107 hasAuthorship W4280521107A5032192226 @default.
• W4280521107 hasAuthorship W4280521107A5046225712 @default.
• W4280521107 hasAuthorship W4280521107A5049656223 @default.
• W4280521107 hasAuthorship W4280521107A5055677011 @default.
• W4280521107 hasAuthorship W4280521107A5055954787 @default.
• W4280521107 hasAuthorship W4280521107A5062115647 @default.
• W4280521107 hasBestOaLocation W42805211072 @default.
• W4280521107 hasConcept C104293457 @default.
• W4280521107 hasConcept C108583219 @default.
• W4280521107 hasConcept C11413529 @default.
• W4280521107 hasConcept C120665830 @default.
• W4280521107 hasConcept C121332964 @default.
• W4280521107 hasConcept C146904657 @default.
• W4280521107 hasConcept C154945302 @default.
• W4280521107 hasConcept C155512373 @default.
• W4280521107 hasConcept C185544564 @default.
• W4280521107 hasConcept C19527891 @default.

• next