FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200508664> ?p ?o ?g. }

• W4200508664 endingPage "1230" @default.
• W4200508664 startingPage "1216" @default.
• W4200508664 abstract "Abstract Purpose Current methods for patient‐specific voxel‐level dosimetry in radionuclide therapy suffer from a trade‐off between accuracy and computational efficiency. Monte Carlo (MC) radiation transport algorithms are considered the gold standard for voxel‐level dosimetry but can be computationally expensive, whereas faster dose voxel kernel (DVK) convolution can be suboptimal in the presence of tissue heterogeneities. Furthermore, the accuracies of both these methods are limited by the spatial resolution of the reconstructed emission image. To overcome these limitations, this paper considers a single deep convolutional neural network (CNN) with residual learning (named DblurDoseNet) that learns to produce dose‐rate maps while compensating for the limited resolution of SPECT images. Methods We trained our CNN using MC‐generated dose‐rate maps that directly corresponded to the true activity maps in virtual patient phantoms. Residual learning was applied such that our CNN learned only the difference between the true dose‐rate map and DVK dose‐rate map with density scaling. Our CNN consists of a 3D depth feature extractor followed by a 2D U‐Net, where the input was 11 slices (3.3 cm) of a given Lu‐177 SPECT/CT image and density map, and the output was the dose‐rate map corresponding to the center slice. The CNN was trained with nine virtual patient phantoms and tested on five different phantoms plus 42 SPECT/CT scans of patients who underwent Lu‐177 DOTATATE therapy. Results When testing on virtual patient phantoms, the lesion/organ mean dose‐rate error and the normalized root mean square error (NRMSE) relative to the ground truth of the CNN method was consistently lower than DVK and MC, when applied to SPECT images. Compared to DVK/MC, the average improvement for the CNN in mean dose‐rate error was 55%/53% and 66%/56%; and in NRMSE was 18%/17% and 10%/11% for lesion and kidney regions, respectively. Line profiles and dose–volume histograms demonstrated compensation for SPECT resolution effects in the CNN‐generated dose‐rate maps. The ensemble noise standard deviation, determined from multiple Poisson realizations, was improved by 21%/27% compared to DVK/MC. In patients, potential improvements from CNN dose‐rate maps compared to DVK/MC were illustrated qualitatively, due to the absence of ground truth. The trained residual CNN took about 30 s on a single GPU (Tesla V100) to generate a 512 512 130 dose‐rate map for a patient. Conclusion The proposed residual CNN, trained using phantoms generated from patient images, has potential for real‐time patient‐specific dosimetry in clinical treatment planning due to its demonstrated improvement in accuracy, resolution, noise, and speed over the DVK/MC approaches." @default.
• W4200508664 created "2021-12-31" @default.
• W4200508664 creator A5027207271 @default.
• W4200508664 creator A5034458018 @default.
• W4200508664 creator A5041795578 @default.
• W4200508664 creator A5048841657 @default.
• W4200508664 creator A5065982764 @default.
• W4200508664 date "2021-12-22" @default.
• W4200508664 modified "2023-10-17" @default.
• W4200508664 title "DblurDoseNet: A deep residual learning network for voxel radionuclide dosimetry compensating for single‐photon emission computerized tomography imaging resolution" @default.
• W4200508664 cites W1635042605 @default.
• W4200508664 cites W1853837235 @default.
• W4200508664 cites W1901129140 @default.
• W4200508664 cites W1964713829 @default.
• W4200508664 cites W1983281817 @default.
• W4200508664 cites W2023676835 @default.
• W4200508664 cites W2099216222 @default.
• W4200508664 cites W2103328396 @default.
• W4200508664 cites W2113286062 @default.
• W4200508664 cites W2156084498 @default.
• W4200508664 cites W2168122655 @default.
• W4200508664 cites W2194775991 @default.
• W4200508664 cites W2259239971 @default.
• W4200508664 cites W2508457857 @default.
• W4200508664 cites W2542549468 @default.
• W4200508664 cites W2584483805 @default.
• W4200508664 cites W2592929672 @default.
• W4200508664 cites W2752756902 @default.
• W4200508664 cites W2756327922 @default.
• W4200508664 cites W2773845120 @default.
• W4200508664 cites W2818710890 @default.
• W4200508664 cites W2898197178 @default.
• W4200508664 cites W2901308062 @default.
• W4200508664 cites W2905525600 @default.
• W4200508664 cites W2913985588 @default.
• W4200508664 cites W2955164461 @default.
• W4200508664 cites W2961264277 @default.
• W4200508664 cites W2972168296 @default.
• W4200508664 cites W2979410457 @default.
• W4200508664 cites W2980047233 @default.
• W4200508664 cites W2990075274 @default.
• W4200508664 cites W2998208444 @default.
• W4200508664 cites W3082693122 @default.
• W4200508664 cites W3084540266 @default.
• W4200508664 cites W3088009272 @default.
• W4200508664 cites W3088719758 @default.
• W4200508664 cites W3093519236 @default.
• W4200508664 cites W3095034359 @default.
• W4200508664 cites W3105282616 @default.
• W4200508664 doi "https://doi.org/10.1002/mp.15397" @default.
• W4200508664 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34882821" @default.
• W4200508664 hasPublicationYear "2021" @default.
• W4200508664 type Work @default.
• W4200508664 citedByCount "7" @default.
• W4200508664 countsByYear W42005086642022 @default.
• W4200508664 countsByYear W42005086642023 @default.
• W4200508664 crossrefType "journal-article" @default.
• W4200508664 hasAuthorship W4200508664A5027207271 @default.
• W4200508664 hasAuthorship W4200508664A5034458018 @default.
• W4200508664 hasAuthorship W4200508664A5041795578 @default.
• W4200508664 hasAuthorship W4200508664A5048841657 @default.
• W4200508664 hasAuthorship W4200508664A5065982764 @default.
• W4200508664 hasBestOaLocation W42005086641 @default.
• W4200508664 hasConcept C104293457 @default.
• W4200508664 hasConcept C105795698 @default.
• W4200508664 hasConcept C11413529 @default.
• W4200508664 hasConcept C114614502 @default.
• W4200508664 hasConcept C138885662 @default.
• W4200508664 hasConcept C141379421 @default.
• W4200508664 hasConcept C154945302 @default.
• W4200508664 hasConcept C155512373 @default.
• W4200508664 hasConcept C19499675 @default.
• W4200508664 hasConcept C205372480 @default.
• W4200508664 hasConcept C2775842073 @default.
• W4200508664 hasConcept C2776401178 @default.
• W4200508664 hasConcept C2780441642 @default.
• W4200508664 hasConcept C2989005 @default.
• W4200508664 hasConcept C31601959 @default.
• W4200508664 hasConcept C33923547 @default.
• W4200508664 hasConcept C41008148 @default.
• W4200508664 hasConcept C41895202 @default.
• W4200508664 hasConcept C54170458 @default.
• W4200508664 hasConcept C71924100 @default.
• W4200508664 hasConcept C74193536 @default.
• W4200508664 hasConcept C75088862 @default.
• W4200508664 hasConcept C81363708 @default.
• W4200508664 hasConceptScore W4200508664C104293457 @default.
• W4200508664 hasConceptScore W4200508664C105795698 @default.
• W4200508664 hasConceptScore W4200508664C11413529 @default.
• W4200508664 hasConceptScore W4200508664C114614502 @default.
• W4200508664 hasConceptScore W4200508664C138885662 @default.
• W4200508664 hasConceptScore W4200508664C141379421 @default.
• W4200508664 hasConceptScore W4200508664C154945302 @default.
• W4200508664 hasConceptScore W4200508664C155512373 @default.
• W4200508664 hasConceptScore W4200508664C19499675 @default.
• W4200508664 hasConceptScore W4200508664C205372480 @default.
• W4200508664 hasConceptScore W4200508664C2775842073 @default.
• W4200508664 hasConceptScore W4200508664C2776401178 @default.

• next