Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285803128> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4285803128 abstract "Automatic liver tumor segmentation can facilitate the planning of liver interventions. For diagnosis of hepatocellular carcinoma, dynamic contrast-enhanced MRI (DCE-MRI) can yield a higher sensitivity than contrast-enhanced CT. However, most studies on automatic liver lesion segmentation have focused on CT. In this study, we present a deep learning-based approach for liver tumor segmentation in the late hepatocellular phase of DCE-MRI, using an anisotropic 3D U-Net architecture and a multi-model training strategy. The 3D architecture improves the segmentation performance compared to a previous study using a 2D U-Net (mean Dice 0.70 vs. 0.65). A further significant improvement is achieved by a multi-model training approach (0.74), which is close to the inter-rater agreement (0.78). A qualitative expert rating of the automatically generated contours confirms the benefit of the multi-model training strategy, with 66 % of contours rated as good or very good, compared to only 43 % when performing a single training. The lesion detection performance with a mean F1-score of 0.59 is inferior to human raters (0.76). Overall, this study shows that correctly detected liver lesions in late-phase DCE-MRI data can be automatically segmented with high accuracy, but the detection, in particular of smaller lesions, can still be improved." @default.
- W4285803128 created "2022-07-19" @default.
- W4285803128 creator A5013052892 @default.
- W4285803128 creator A5014470024 @default.
- W4285803128 creator A5017023349 @default.
- W4285803128 creator A5026098790 @default.
- W4285803128 creator A5033927818 @default.
- W4285803128 creator A5053216721 @default.
- W4285803128 creator A5058852755 @default.
- W4285803128 creator A5059738241 @default.
- W4285803128 date "2022-07-18" @default.
- W4285803128 modified "2023-10-13" @default.
- W4285803128 title "Improving automatic liver tumor segmentation in late-phase MRI using multi-model training and 3D convolutional neural networks" @default.
- W4285803128 cites W1488765683 @default.
- W4285803128 cites W1901129140 @default.
- W4285803128 cites W2080628940 @default.
- W4285803128 cites W2110065044 @default.
- W4285803128 cites W2153431772 @default.
- W4285803128 cites W2768270891 @default.
- W4285803128 cites W2806070179 @default.
- W4285803128 cites W2897666251 @default.
- W4285803128 cites W2945683845 @default.
- W4285803128 cites W2962914239 @default.
- W4285803128 cites W2963150697 @default.
- W4285803128 cites W3009773997 @default.
- W4285803128 cites W3033347459 @default.
- W4285803128 cites W3101381711 @default.
- W4285803128 cites W3103145119 @default.
- W4285803128 cites W3107770003 @default.
- W4285803128 cites W3112701542 @default.
- W4285803128 cites W3176861478 @default.
- W4285803128 cites W3201782492 @default.
- W4285803128 cites W3203598313 @default.
- W4285803128 cites W4252684946 @default.
- W4285803128 doi "https://doi.org/10.1038/s41598-022-16388-9" @default.
- W4285803128 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35851322" @default.
- W4285803128 hasPublicationYear "2022" @default.
- W4285803128 type Work @default.
- W4285803128 citedByCount "6" @default.
- W4285803128 countsByYear W42858031282022 @default.
- W4285803128 countsByYear W42858031282023 @default.
- W4285803128 crossrefType "journal-article" @default.
- W4285803128 hasAuthorship W4285803128A5013052892 @default.
- W4285803128 hasAuthorship W4285803128A5014470024 @default.
- W4285803128 hasAuthorship W4285803128A5017023349 @default.
- W4285803128 hasAuthorship W4285803128A5026098790 @default.
- W4285803128 hasAuthorship W4285803128A5033927818 @default.
- W4285803128 hasAuthorship W4285803128A5053216721 @default.
- W4285803128 hasAuthorship W4285803128A5058852755 @default.
- W4285803128 hasAuthorship W4285803128A5059738241 @default.
- W4285803128 hasBestOaLocation W42858031281 @default.
- W4285803128 hasConcept C108583219 @default.
- W4285803128 hasConcept C126322002 @default.
- W4285803128 hasConcept C126838900 @default.
- W4285803128 hasConcept C153180895 @default.
- W4285803128 hasConcept C154945302 @default.
- W4285803128 hasConcept C2778019345 @default.
- W4285803128 hasConcept C41008148 @default.
- W4285803128 hasConcept C71924100 @default.
- W4285803128 hasConcept C81363708 @default.
- W4285803128 hasConcept C89600930 @default.
- W4285803128 hasConceptScore W4285803128C108583219 @default.
- W4285803128 hasConceptScore W4285803128C126322002 @default.
- W4285803128 hasConceptScore W4285803128C126838900 @default.
- W4285803128 hasConceptScore W4285803128C153180895 @default.
- W4285803128 hasConceptScore W4285803128C154945302 @default.
- W4285803128 hasConceptScore W4285803128C2778019345 @default.
- W4285803128 hasConceptScore W4285803128C41008148 @default.
- W4285803128 hasConceptScore W4285803128C71924100 @default.
- W4285803128 hasConceptScore W4285803128C81363708 @default.
- W4285803128 hasConceptScore W4285803128C89600930 @default.
- W4285803128 hasIssue "1" @default.
- W4285803128 hasLocation W42858031281 @default.
- W4285803128 hasLocation W42858031282 @default.
- W4285803128 hasLocation W42858031283 @default.
- W4285803128 hasOpenAccess W4285803128 @default.
- W4285803128 hasPrimaryLocation W42858031281 @default.
- W4285803128 hasRelatedWork W2417822880 @default.
- W4285803128 hasRelatedWork W2809701302 @default.
- W4285803128 hasRelatedWork W3029198973 @default.
- W4285803128 hasRelatedWork W3133861977 @default.
- W4285803128 hasRelatedWork W3167935049 @default.
- W4285803128 hasRelatedWork W3193565141 @default.
- W4285803128 hasRelatedWork W4226493464 @default.
- W4285803128 hasRelatedWork W4312417841 @default.
- W4285803128 hasRelatedWork W4315434538 @default.
- W4285803128 hasRelatedWork W628600844 @default.
- W4285803128 hasVolume "12" @default.
- W4285803128 isParatext "false" @default.
- W4285803128 isRetracted "false" @default.
- W4285803128 workType "article" @default.