Matches in SemOpenAlex for { <https://semopenalex.org/work/W3033015387> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3033015387 endingPage "3794" @default.
- W3033015387 startingPage "3794" @default.
- W3033015387 abstract "Liver and liver tumor segmentation based on abdomen computed tomography (CT) images is an essential step in computer-assisted clinical interventions. However, liver and tumor segmentation remains the difficult issue in the medical image processing field, which is ascribed to the anatomical complexity of the liver and the poor demarcation between the liver and other nearby organs on the image. The existing 3D automatic liver and tumor segmentation algorithms based on full convolutional networks, such as V-net, have utilized the loss functions on the basis of integration (summing) over a segmented region (like Dice or cross-entropy). Unfortunately, the number of foreground and background voxels is usually highly imbalanced in liver and tumor segmentation tasks. This greatly varies the value of regional loss between various segmentation classes, and affects the training stability and effect. In the present study, an improved V-net algorithm was applied for 3D liver and tumor segmentation based on region and distance metrics. The distance metric-based loss function utilized a distance metric of the contour (or shape) space rather than the area. The model was jointly trained by the original regional loss and the three distance-based loss functions (including Boundary (BD) loss, Hausdorff (HD) loss, and Signed Distance Map (SDM) loss) to solve the problem of the highly unbalanced liver and tumor segmentation. Besides, the algorithm was tested in two databases LiTS 2017 (Technical University of Munich, Munich, Germany, 2017) and 3D-IRCADb (Research Institute against Digestive Cancer, Strasbourg Cedex, France, 2009), and the results proved the effectiveness of improvement." @default.
- W3033015387 created "2020-06-12" @default.
- W3033015387 creator A5043174277 @default.
- W3033015387 creator A5044544424 @default.
- W3033015387 creator A5044917311 @default.
- W3033015387 creator A5065797055 @default.
- W3033015387 date "2020-05-29" @default.
- W3033015387 modified "2023-09-27" @default.
- W3033015387 title "3D Liver and Tumor Segmentation with CNNs Based on Region and Distance Metrics" @default.
- W3033015387 cites W1884191083 @default.
- W3033015387 cites W1966707541 @default.
- W3033015387 cites W2003258143 @default.
- W3033015387 cites W2037116875 @default.
- W3033015387 cites W2101608218 @default.
- W3033015387 cites W2138047924 @default.
- W3033015387 cites W2153431772 @default.
- W3033015387 cites W2301358467 @default.
- W3033015387 cites W2357815549 @default.
- W3033015387 cites W2582058104 @default.
- W3033015387 cites W2600979969 @default.
- W3033015387 cites W2897666251 @default.
- W3033015387 cites W2913637767 @default.
- W3033015387 cites W2962731543 @default.
- W3033015387 cites W2964227007 @default.
- W3033015387 cites W2965682404 @default.
- W3033015387 cites W3211330693 @default.
- W3033015387 cites W4250213818 @default.
- W3033015387 doi "https://doi.org/10.3390/app10113794" @default.
- W3033015387 hasPublicationYear "2020" @default.
- W3033015387 type Work @default.
- W3033015387 sameAs 3033015387 @default.
- W3033015387 citedByCount "9" @default.
- W3033015387 countsByYear W30330153872020 @default.
- W3033015387 countsByYear W30330153872021 @default.
- W3033015387 countsByYear W30330153872022 @default.
- W3033015387 countsByYear W30330153872023 @default.
- W3033015387 crossrefType "journal-article" @default.
- W3033015387 hasAuthorship W3033015387A5043174277 @default.
- W3033015387 hasAuthorship W3033015387A5044544424 @default.
- W3033015387 hasAuthorship W3033015387A5044917311 @default.
- W3033015387 hasAuthorship W3033015387A5065797055 @default.
- W3033015387 hasBestOaLocation W30330153871 @default.
- W3033015387 hasConcept C124504099 @default.
- W3033015387 hasConcept C141898687 @default.
- W3033015387 hasConcept C153180895 @default.
- W3033015387 hasConcept C154945302 @default.
- W3033015387 hasConcept C162324750 @default.
- W3033015387 hasConcept C176217482 @default.
- W3033015387 hasConcept C21547014 @default.
- W3033015387 hasConcept C22029948 @default.
- W3033015387 hasConcept C2524010 @default.
- W3033015387 hasConcept C31972630 @default.
- W3033015387 hasConcept C33923547 @default.
- W3033015387 hasConcept C41008148 @default.
- W3033015387 hasConcept C54170458 @default.
- W3033015387 hasConcept C89600930 @default.
- W3033015387 hasConceptScore W3033015387C124504099 @default.
- W3033015387 hasConceptScore W3033015387C141898687 @default.
- W3033015387 hasConceptScore W3033015387C153180895 @default.
- W3033015387 hasConceptScore W3033015387C154945302 @default.
- W3033015387 hasConceptScore W3033015387C162324750 @default.
- W3033015387 hasConceptScore W3033015387C176217482 @default.
- W3033015387 hasConceptScore W3033015387C21547014 @default.
- W3033015387 hasConceptScore W3033015387C22029948 @default.
- W3033015387 hasConceptScore W3033015387C2524010 @default.
- W3033015387 hasConceptScore W3033015387C31972630 @default.
- W3033015387 hasConceptScore W3033015387C33923547 @default.
- W3033015387 hasConceptScore W3033015387C41008148 @default.
- W3033015387 hasConceptScore W3033015387C54170458 @default.
- W3033015387 hasConceptScore W3033015387C89600930 @default.
- W3033015387 hasIssue "11" @default.
- W3033015387 hasLocation W30330153871 @default.
- W3033015387 hasLocation W30330153872 @default.
- W3033015387 hasOpenAccess W3033015387 @default.
- W3033015387 hasPrimaryLocation W30330153871 @default.
- W3033015387 hasRelatedWork W1669643531 @default.
- W3033015387 hasRelatedWork W2005437358 @default.
- W3033015387 hasRelatedWork W2008656436 @default.
- W3033015387 hasRelatedWork W2134924024 @default.
- W3033015387 hasRelatedWork W2517104666 @default.
- W3033015387 hasRelatedWork W2920218276 @default.
- W3033015387 hasRelatedWork W2971066617 @default.
- W3033015387 hasRelatedWork W3130357085 @default.
- W3033015387 hasRelatedWork W4319792695 @default.
- W3033015387 hasRelatedWork W4363650189 @default.
- W3033015387 hasVolume "10" @default.
- W3033015387 isParatext "false" @default.
- W3033015387 isRetracted "false" @default.
- W3033015387 magId "3033015387" @default.
- W3033015387 workType "article" @default.