FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4316127112> ?p ?o ?g. }

• W4316127112 endingPage "106539" @default.
• W4316127112 startingPage "106539" @default.
• W4316127112 abstract "Model-based reconstruction employing the time separation technique (TST) was found to improve dynamic perfusion imaging of the liver using C-arm cone-beam computed tomography (CBCT). To apply TST using prior knowledge extracted from CT perfusion data, the liver should be accurately segmented from the CT scans. Reconstructions of primary and model-based CBCT data need to be segmented for proper visualisation and interpretation of perfusion maps. This research proposes Turbolift learning, which trains a modified version of the multi-scale Attention UNet on different liver segmentation tasks serially, following the order of the trainings CT, CBCT, CBCT TST - making the previous trainings act as pre-training stages for the subsequent ones - addressing the problem of limited number of datasets for training. For the final task of liver segmentation from CBCT TST, the proposed method achieved an overall Dice scores of 0.874±0.031 and 0.905±0.007 in 6-fold and 4-fold cross-validation experiments, respectively - securing statistically significant improvements over the model, which was trained only for that task. Experiments revealed that Turbolift not only improves the overall performance of the model but also makes it robust against artefacts originating from the embolisation materials and truncation artefacts. Additionally, in-depth analyses confirmed the order of the segmentation tasks. This paper shows the potential of segmenting the liver from CT, CBCT, and CBCT TST, learning from the available limited training data, which can possibly be used in the future for the visualisation and evaluation of the perfusion maps for the treatment evaluation of liver diseases." @default.
• W4316127112 created "2023-01-14" @default.
• W4316127112 creator A5005058303 @default.
• W4316127112 creator A5018585865 @default.
• W4316127112 creator A5022172450 @default.
• W4316127112 creator A5037062088 @default.
• W4316127112 creator A5055725293 @default.
• W4316127112 creator A5067703063 @default.
• W4316127112 creator A5072325586 @default.
• W4316127112 creator A5075663234 @default.
• W4316127112 creator A5076491808 @default.
• W4316127112 creator A5079774186 @default.
• W4316127112 creator A5087929832 @default.
• W4316127112 creator A5088938129 @default.
• W4316127112 date "2023-03-01" @default.
• W4316127112 modified "2023-09-27" @default.
• W4316127112 title "Liver segmentation using Turbolift learning for CT and cone-beam C-arm perfusion imaging" @default.
• W4316127112 cites W1677182931 @default.
• W4316127112 cites W1972978214 @default.
• W4316127112 cites W1993105593 @default.
• W4316127112 cites W2006788795 @default.
• W4316127112 cites W2094936277 @default.
• W4316127112 cites W2126559523 @default.
• W4316127112 cites W2140135814 @default.
• W4316127112 cites W2157809796 @default.
• W4316127112 cites W2158479150 @default.
• W4316127112 cites W2340027277 @default.
• W4316127112 cites W2595638662 @default.
• W4316127112 cites W2767972003 @default.
• W4316127112 cites W2786808285 @default.
• W4316127112 cites W2792381036 @default.
• W4316127112 cites W2794022343 @default.
• W4316127112 cites W2982303713 @default.
• W4316127112 cites W3002569343 @default.
• W4316127112 cites W3039883906 @default.
• W4316127112 cites W3207963994 @default.
• W4316127112 cites W4220700457 @default.
• W4316127112 cites W4223598593 @default.
• W4316127112 cites W4245648248 @default.
• W4316127112 cites W4306661813 @default.
• W4316127112 doi "https://doi.org/10.1016/j.compbiomed.2023.106539" @default.
• W4316127112 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36689856" @default.
• W4316127112 hasPublicationYear "2023" @default.
• W4316127112 type Work @default.
• W4316127112 citedByCount "0" @default.
• W4316127112 crossrefType "journal-article" @default.
• W4316127112 hasAuthorship W4316127112A5005058303 @default.
• W4316127112 hasAuthorship W4316127112A5018585865 @default.
• W4316127112 hasAuthorship W4316127112A5022172450 @default.
• W4316127112 hasAuthorship W4316127112A5037062088 @default.
• W4316127112 hasAuthorship W4316127112A5055725293 @default.
• W4316127112 hasAuthorship W4316127112A5067703063 @default.
• W4316127112 hasAuthorship W4316127112A5072325586 @default.
• W4316127112 hasAuthorship W4316127112A5075663234 @default.
• W4316127112 hasAuthorship W4316127112A5076491808 @default.
• W4316127112 hasAuthorship W4316127112A5079774186 @default.
• W4316127112 hasAuthorship W4316127112A5087929832 @default.
• W4316127112 hasAuthorship W4316127112A5088938129 @default.
• W4316127112 hasBestOaLocation W43161271122 @default.
• W4316127112 hasConcept C126838900 @default.
• W4316127112 hasConcept C146957229 @default.
• W4316127112 hasConcept C153180895 @default.
• W4316127112 hasConcept C154945302 @default.
• W4316127112 hasConcept C2779813781 @default.
• W4316127112 hasConcept C2989005 @default.
• W4316127112 hasConcept C31972630 @default.
• W4316127112 hasConcept C36464697 @default.
• W4316127112 hasConcept C41008148 @default.
• W4316127112 hasConcept C544519230 @default.
• W4316127112 hasConcept C71924100 @default.
• W4316127112 hasConcept C89600930 @default.
• W4316127112 hasConceptScore W4316127112C126838900 @default.
• W4316127112 hasConceptScore W4316127112C146957229 @default.
• W4316127112 hasConceptScore W4316127112C153180895 @default.
• W4316127112 hasConceptScore W4316127112C154945302 @default.
• W4316127112 hasConceptScore W4316127112C2779813781 @default.
• W4316127112 hasConceptScore W4316127112C2989005 @default.
• W4316127112 hasConceptScore W4316127112C31972630 @default.
• W4316127112 hasConceptScore W4316127112C36464697 @default.
• W4316127112 hasConceptScore W4316127112C41008148 @default.
• W4316127112 hasConceptScore W4316127112C544519230 @default.
• W4316127112 hasConceptScore W4316127112C71924100 @default.
• W4316127112 hasConceptScore W4316127112C89600930 @default.
• W4316127112 hasLocation W43161271121 @default.
• W4316127112 hasLocation W43161271122 @default.
• W4316127112 hasLocation W43161271123 @default.
• W4316127112 hasOpenAccess W4316127112 @default.
• W4316127112 hasPrimaryLocation W43161271121 @default.
• W4316127112 hasRelatedWork W1669643531 @default.
• W4316127112 hasRelatedWork W2005437358 @default.
• W4316127112 hasRelatedWork W2008656436 @default.
• W4316127112 hasRelatedWork W2023558673 @default.
• W4316127112 hasRelatedWork W2039154422 @default.
• W4316127112 hasRelatedWork W2110230079 @default.
• W4316127112 hasRelatedWork W2122581818 @default.
• W4316127112 hasRelatedWork W2134924024 @default.
• W4316127112 hasRelatedWork W2517104666 @default.
• W4316127112 hasRelatedWork W2182382398 @default.

• next