FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3167570948> ?p ?o ?g. }

• W3167570948 endingPage "5258" @default.
• W3167570948 startingPage "5244" @default.
• W3167570948 abstract "The developments of PET/CT and PET/MR scanners provide opportunities for improving PET image quality by using anatomical information. In this paper, we propose a novel co-learning three-dimensional (3D) convolutional neural network (CNN) to extract modality-specific features from PET/CT image pairs and integrate complementary features into an iterative reconstruction framework to improve PET image reconstruction.We used a pretrained deep neural network to represent PET images. The network was trained using low-count PET and CT image pairs as inputs and high-count PET images as labels. This network was then incorporated into a constrained maximum likelihood framework to regularize PET image reconstruction. Two different network structures were investigated for the integration of anatomical information from CT images. One was a multichannel CNN, which treated PET and CT volumes as separate channels of the input. The other one was multibranch CNN, which implemented separate encoders for PET and CT images to extract latent features and fed the combined latent features into a decoder. Using computer-based Monte Carlo simulations and two real patient datasets, the proposed method has been compared with existing methods, including the maximum likelihood expectation maximization (MLEM) reconstruction, a kernel-based reconstruction and a CNN-based deep penalty method with and without anatomical guidance.Reconstructed images showed that the proposed constrained ML reconstruction approach produced higher quality images than the competing methods. The tumors in the lung region have higher contrast in the proposed constrained ML reconstruction than in the CNN-based deep penalty reconstruction. The image quality was further improved by incorporating the anatomical information. Moreover, the liver standard deviation was lower in the proposed approach than all the competing methods at a matched lesion contrast.The supervised co-learning strategy can improve the performance of constrained maximum likelihood reconstruction. Compared with existing techniques, the proposed method produced a better lesion contrast versus background standard deviation trade-off curve, which can potentially improve lesion detection." @default.
• W3167570948 created "2021-06-22" @default.
• W3167570948 creator A5004655343 @default.
• W3167570948 creator A5008203694 @default.
• W3167570948 creator A5010507422 @default.
• W3167570948 creator A5010514255 @default.
• W3167570948 creator A5046906321 @default.
• W3167570948 creator A5062955030 @default.
• W3167570948 date "2021-07-28" @default.
• W3167570948 modified "2023-10-13" @default.
• W3167570948 title "Anatomically aided PET image reconstruction using deep neural networks" @default.
• W3167570948 cites W1901129140 @default.
• W3167570948 cites W1970453159 @default.
• W3167570948 cites W1980288291 @default.
• W3167570948 cites W1983281817 @default.
• W3167570948 cites W2014351445 @default.
• W3167570948 cites W2017162022 @default.
• W3167570948 cites W2043680485 @default.
• W3167570948 cites W2068100966 @default.
• W3167570948 cites W2082526668 @default.
• W3167570948 cites W2089050201 @default.
• W3167570948 cites W2096556620 @default.
• W3167570948 cites W2138643603 @default.
• W3167570948 cites W2152693305 @default.
• W3167570948 cites W2156994346 @default.
• W3167570948 cites W2383601426 @default.
• W3167570948 cites W2442117232 @default.
• W3167570948 cites W2517088289 @default.
• W3167570948 cites W2611467245 @default.
• W3167570948 cites W2729145866 @default.
• W3167570948 cites W2758460516 @default.
• W3167570948 cites W2761090034 @default.
• W3167570948 cites W2766840568 @default.
• W3167570948 cites W2770686150 @default.
• W3167570948 cites W2798538010 @default.
• W3167570948 cites W2801585709 @default.
• W3167570948 cites W2803224943 @default.
• W3167570948 cites W2902972155 @default.
• W3167570948 cites W2906587342 @default.
• W3167570948 cites W2909887812 @default.
• W3167570948 cites W2911290743 @default.
• W3167570948 cites W2918247176 @default.
• W3167570948 cites W2919115771 @default.
• W3167570948 cites W2921467067 @default.
• W3167570948 cites W2947679489 @default.
• W3167570948 cites W2963385325 @default.
• W3167570948 cites W2970280802 @default.
• W3167570948 cites W2972851413 @default.
• W3167570948 cites W2974786312 @default.
• W3167570948 cites W2975696535 @default.
• W3167570948 cites W3011544148 @default.
• W3167570948 cites W3016100956 @default.
• W3167570948 cites W3041500444 @default.
• W3167570948 cites W3100730608 @default.
• W3167570948 cites W3103921058 @default.
• W3167570948 cites W3106286734 @default.
• W3167570948 cites W4241578155 @default.
• W3167570948 cites W4292363360 @default.
• W3167570948 doi "https://doi.org/10.1002/mp.15051" @default.
• W3167570948 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8510002" @default.
• W3167570948 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34129690" @default.
• W3167570948 hasPublicationYear "2021" @default.
• W3167570948 type Work @default.
• W3167570948 sameAs 3167570948 @default.
• W3167570948 citedByCount "11" @default.
• W3167570948 countsByYear W31675709482021 @default.
• W3167570948 countsByYear W31675709482022 @default.
• W3167570948 countsByYear W31675709482023 @default.
• W3167570948 crossrefType "journal-article" @default.
• W3167570948 hasAuthorship W3167570948A5004655343 @default.
• W3167570948 hasAuthorship W3167570948A5008203694 @default.
• W3167570948 hasAuthorship W3167570948A5010507422 @default.
• W3167570948 hasAuthorship W3167570948A5010514255 @default.
• W3167570948 hasAuthorship W3167570948A5046906321 @default.
• W3167570948 hasAuthorship W3167570948A5062955030 @default.
• W3167570948 hasBestOaLocation W31675709482 @default.
• W3167570948 hasConcept C108583219 @default.
• W3167570948 hasConcept C114614502 @default.
• W3167570948 hasConcept C115961682 @default.
• W3167570948 hasConcept C141379421 @default.
• W3167570948 hasConcept C153180895 @default.
• W3167570948 hasConcept C154945302 @default.
• W3167570948 hasConcept C31601959 @default.
• W3167570948 hasConcept C31972630 @default.
• W3167570948 hasConcept C33923547 @default.
• W3167570948 hasConcept C41008148 @default.
• W3167570948 hasConcept C55020928 @default.
• W3167570948 hasConcept C74193536 @default.
• W3167570948 hasConcept C81363708 @default.
• W3167570948 hasConceptScore W3167570948C108583219 @default.
• W3167570948 hasConceptScore W3167570948C114614502 @default.
• W3167570948 hasConceptScore W3167570948C115961682 @default.
• W3167570948 hasConceptScore W3167570948C141379421 @default.
• W3167570948 hasConceptScore W3167570948C153180895 @default.
• W3167570948 hasConceptScore W3167570948C154945302 @default.
• W3167570948 hasConceptScore W3167570948C31601959 @default.
• W3167570948 hasConceptScore W3167570948C31972630 @default.
• W3167570948 hasConceptScore W3167570948C33923547 @default.

• next