Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386352783> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4386352783 abstract "The development of medical image segmentation using deep learning can significantly support doctors’ diagnoses. Deep learning needs large amounts of data for training, which also requires data augmentation to extend diversity for preventing overfitting. However, the existing methods for data augmentation of medical image segmentation are mainly based on models which need to update parameters and cost extra computing resources. We proposed data augmentation methods designed to train a high-accuracy deep learning network for medical image segmentation. The proposed data augmentation approaches are called KeepMask and KeepMix, which can create medical images by better identifying the boundary of the organ with no more parameters. Our methods achieved better performance and obtained more precise boundaries for medical image segmentation on datasets. The dice coefficient of our methods achieved 94.15% (3.04% higher than baseline) on CHAOS and 74.70% (5.25% higher than baseline) on MSD spleen with Unet." @default.
- W4386352783 created "2023-09-02" @default.
- W4386352783 creator A5002096737 @default.
- W4386352783 creator A5042566789 @default.
- W4386352783 creator A5064312777 @default.
- W4386352783 date "2023-04-18" @default.
- W4386352783 modified "2023-09-27" @default.
- W4386352783 title "Mixing Data Augmentation with Preserving Foreground Regions in Medical Image Segmentation" @default.
- W4386352783 cites W2153431772 @default.
- W4386352783 cites W2963163009 @default.
- W4386352783 cites W2988306446 @default.
- W4386352783 cites W2992308087 @default.
- W4386352783 cites W3002569343 @default.
- W4386352783 cites W3091595271 @default.
- W4386352783 cites W3099319035 @default.
- W4386352783 cites W3106753828 @default.
- W4386352783 cites W3176659256 @default.
- W4386352783 cites W3177330184 @default.
- W4386352783 cites W3204971388 @default.
- W4386352783 doi "https://doi.org/10.1109/isbi53787.2023.10230495" @default.
- W4386352783 hasPublicationYear "2023" @default.
- W4386352783 type Work @default.
- W4386352783 citedByCount "0" @default.
- W4386352783 crossrefType "proceedings-article" @default.
- W4386352783 hasAuthorship W4386352783A5002096737 @default.
- W4386352783 hasAuthorship W4386352783A5042566789 @default.
- W4386352783 hasAuthorship W4386352783A5064312777 @default.
- W4386352783 hasConcept C108583219 @default.
- W4386352783 hasConcept C111368507 @default.
- W4386352783 hasConcept C115961682 @default.
- W4386352783 hasConcept C119857082 @default.
- W4386352783 hasConcept C124504099 @default.
- W4386352783 hasConcept C12725497 @default.
- W4386352783 hasConcept C127313418 @default.
- W4386352783 hasConcept C142724271 @default.
- W4386352783 hasConcept C153180895 @default.
- W4386352783 hasConcept C154945302 @default.
- W4386352783 hasConcept C22019652 @default.
- W4386352783 hasConcept C31972630 @default.
- W4386352783 hasConcept C41008148 @default.
- W4386352783 hasConcept C50644808 @default.
- W4386352783 hasConcept C534262118 @default.
- W4386352783 hasConcept C71924100 @default.
- W4386352783 hasConcept C89600930 @default.
- W4386352783 hasConceptScore W4386352783C108583219 @default.
- W4386352783 hasConceptScore W4386352783C111368507 @default.
- W4386352783 hasConceptScore W4386352783C115961682 @default.
- W4386352783 hasConceptScore W4386352783C119857082 @default.
- W4386352783 hasConceptScore W4386352783C124504099 @default.
- W4386352783 hasConceptScore W4386352783C12725497 @default.
- W4386352783 hasConceptScore W4386352783C127313418 @default.
- W4386352783 hasConceptScore W4386352783C142724271 @default.
- W4386352783 hasConceptScore W4386352783C153180895 @default.
- W4386352783 hasConceptScore W4386352783C154945302 @default.
- W4386352783 hasConceptScore W4386352783C22019652 @default.
- W4386352783 hasConceptScore W4386352783C31972630 @default.
- W4386352783 hasConceptScore W4386352783C41008148 @default.
- W4386352783 hasConceptScore W4386352783C50644808 @default.
- W4386352783 hasConceptScore W4386352783C534262118 @default.
- W4386352783 hasConceptScore W4386352783C71924100 @default.
- W4386352783 hasConceptScore W4386352783C89600930 @default.
- W4386352783 hasLocation W43863527831 @default.
- W4386352783 hasOpenAccess W4386352783 @default.
- W4386352783 hasPrimaryLocation W43863527831 @default.
- W4386352783 hasRelatedWork W2005437358 @default.
- W4386352783 hasRelatedWork W2517104666 @default.
- W4386352783 hasRelatedWork W2790662084 @default.
- W4386352783 hasRelatedWork W2989932438 @default.
- W4386352783 hasRelatedWork W3099765033 @default.
- W4386352783 hasRelatedWork W4285802257 @default.
- W4386352783 hasRelatedWork W4285827401 @default.
- W4386352783 hasRelatedWork W4309637067 @default.
- W4386352783 hasRelatedWork W4361732492 @default.
- W4386352783 hasRelatedWork W4380075502 @default.
- W4386352783 isParatext "false" @default.
- W4386352783 isRetracted "false" @default.
- W4386352783 workType "article" @default.