Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200259769> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4200259769 abstract "Purpose To determine which types of magnetic resonance images give the best performance when used to train convolutional neural networks for liver segmentation and volumetry. Methods Abdominal MRI scans were performed on 42 adolescents with obesity. Scans included Dixon imaging (giving water, fat, and T2* images) and low-resolution T2-weighted anatomical scans. Multiple convolutional neural network models using a 3D U-Net architecture were trained with different input images. Whole-liver manual segmentations were used for reference. Segmentation performance was measured using the Dice similarity coefficient (DSC) and 95% Hausdorff distance. Liver volume accuracy was evaluated using bias, precision, and normalized root mean square error (NRMSE). Results The models trained using both water and fat images performed best, giving DSC = 0.94 and NRMSE = 4.2%. Models trained without the water image as input all performed worse, including in participants with elevated liver fat. Models using the T2-weighted anatomical images underperformed the Dixon-based models, but provided acceptable performance (DSC ≥ 0.92, NMRSE ≤ 6.6%) for use in longitudinal pediatric obesity interventions. Conclusion The model using Dixon water and fat images as input gave the best performance, with results comparable to inter-reader variability and state-of-the-art methods." @default.
- W4200259769 created "2021-12-31" @default.
- W4200259769 creator A5014973874 @default.
- W4200259769 creator A5036273026 @default.
- W4200259769 creator A5037626452 @default.
- W4200259769 creator A5047017171 @default.
- W4200259769 creator A5058561021 @default.
- W4200259769 creator A5068265574 @default.
- W4200259769 date "2021-12-05" @default.
- W4200259769 modified "2023-10-16" @default.
- W4200259769 title "Liver Volumetry from Magnetic Resonance Images with Convolutional Neural Networks" @default.
- W4200259769 doi "https://doi.org/10.1101/2021.12.01.21267152" @default.
- W4200259769 hasPublicationYear "2021" @default.
- W4200259769 type Work @default.
- W4200259769 citedByCount "0" @default.
- W4200259769 crossrefType "posted-content" @default.
- W4200259769 hasAuthorship W4200259769A5014973874 @default.
- W4200259769 hasAuthorship W4200259769A5036273026 @default.
- W4200259769 hasAuthorship W4200259769A5037626452 @default.
- W4200259769 hasAuthorship W4200259769A5047017171 @default.
- W4200259769 hasAuthorship W4200259769A5058561021 @default.
- W4200259769 hasAuthorship W4200259769A5068265574 @default.
- W4200259769 hasBestOaLocation W42002597691 @default.
- W4200259769 hasConcept C105795698 @default.
- W4200259769 hasConcept C124504099 @default.
- W4200259769 hasConcept C126838900 @default.
- W4200259769 hasConcept C139945424 @default.
- W4200259769 hasConcept C141898687 @default.
- W4200259769 hasConcept C143409427 @default.
- W4200259769 hasConcept C153180895 @default.
- W4200259769 hasConcept C154945302 @default.
- W4200259769 hasConcept C163892561 @default.
- W4200259769 hasConcept C33923547 @default.
- W4200259769 hasConcept C41008148 @default.
- W4200259769 hasConcept C50644808 @default.
- W4200259769 hasConcept C71924100 @default.
- W4200259769 hasConcept C81363708 @default.
- W4200259769 hasConcept C89600930 @default.
- W4200259769 hasConceptScore W4200259769C105795698 @default.
- W4200259769 hasConceptScore W4200259769C124504099 @default.
- W4200259769 hasConceptScore W4200259769C126838900 @default.
- W4200259769 hasConceptScore W4200259769C139945424 @default.
- W4200259769 hasConceptScore W4200259769C141898687 @default.
- W4200259769 hasConceptScore W4200259769C143409427 @default.
- W4200259769 hasConceptScore W4200259769C153180895 @default.
- W4200259769 hasConceptScore W4200259769C154945302 @default.
- W4200259769 hasConceptScore W4200259769C163892561 @default.
- W4200259769 hasConceptScore W4200259769C33923547 @default.
- W4200259769 hasConceptScore W4200259769C41008148 @default.
- W4200259769 hasConceptScore W4200259769C50644808 @default.
- W4200259769 hasConceptScore W4200259769C71924100 @default.
- W4200259769 hasConceptScore W4200259769C81363708 @default.
- W4200259769 hasConceptScore W4200259769C89600930 @default.
- W4200259769 hasLocation W42002597691 @default.
- W4200259769 hasOpenAccess W4200259769 @default.
- W4200259769 hasPrimaryLocation W42002597691 @default.
- W4200259769 hasRelatedWork W2769435486 @default.
- W4200259769 hasRelatedWork W2789246122 @default.
- W4200259769 hasRelatedWork W2897195263 @default.
- W4200259769 hasRelatedWork W2900677237 @default.
- W4200259769 hasRelatedWork W2999964212 @default.
- W4200259769 hasRelatedWork W3007126806 @default.
- W4200259769 hasRelatedWork W3152950745 @default.
- W4200259769 hasRelatedWork W3198334642 @default.
- W4200259769 hasRelatedWork W3201793090 @default.
- W4200259769 hasRelatedWork W4200528772 @default.
- W4200259769 isParatext "false" @default.
- W4200259769 isRetracted "false" @default.
- W4200259769 workType "article" @default.