FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2967079887> ?p ?o ?g. }

• W2967079887 endingPage "395" @default.
• W2967079887 startingPage "387" @default.
• W2967079887 abstract "To develop a deep convolutional neural network (CNN) to automatically segment an axial CT image of the pelvis for body composition measures. We hypothesized that a deep CNN approach would achieve high accuracy when compared to manual segmentations as the reference standard. We manually segmented 200 axial CT images at the supra-acetabular level in 200 subjects, labeling background, subcutaneous adipose tissue (SAT), muscle, inter-muscular adipose tissue (IMAT), bone, and miscellaneous intra-pelvic content. The dataset was randomly divided into training (180/200) and test (20/200) datasets. Data augmentation was utilized to enlarge the training dataset and all images underwent preprocessing with histogram equalization. Our model was trained for 50 epochs using the U-Net architecture with batch size of 8, learning rate of 0.0001, Adadelta optimizer and a dropout of 0.20. The Dice (F1) score was used to assess similarity between the manual segmentations and the CNN predicted segmentations. The CNN model with data augmentation of N = 3000 achieved accurate segmentation of body composition for all classes. The Dice scores were as follows: background (1.00), miscellaneous intra-pelvic content (0.98), SAT (0.97), muscle (0.95), IMAT (0.91), and bone (0.92). Mean time to automatically segment one CT image was 0.07 s (GPU) and 2.51 s (CPU). Our CNN-based model enables accurate automated segmentation of multiple tissues on pelvic CT images, with promising implications for body composition studies." @default.
• W2967079887 created "2019-08-22" @default.
• W2967079887 creator A5008491621 @default.
• W2967079887 creator A5018251444 @default.
• W2967079887 creator A5040562111 @default.
• W2967079887 creator A5044473833 @default.
• W2967079887 creator A5078516450 @default.
• W2967079887 date "2019-08-08" @default.
• W2967079887 modified "2023-10-12" @default.
• W2967079887 title "Deep learning for automated segmentation of pelvic muscles, fat, and bone from CT studies for body composition assessment" @default.
• W2967079887 cites W1901129140 @default.
• W2967079887 cites W1987869189 @default.
• W2967079887 cites W1993419506 @default.
• W2967079887 cites W1996333080 @default.
• W2967079887 cites W2015788522 @default.
• W2967079887 cites W2042812952 @default.
• W2967079887 cites W2049798783 @default.
• W2967079887 cites W2061302102 @default.
• W2967079887 cites W2069819237 @default.
• W2967079887 cites W2081576992 @default.
• W2967079887 cites W2092337164 @default.
• W2967079887 cites W2115150337 @default.
• W2967079887 cites W2123157434 @default.
• W2967079887 cites W2138610968 @default.
• W2967079887 cites W2157496452 @default.
• W2967079887 cites W2162983983 @default.
• W2967079887 cites W2268912046 @default.
• W2967079887 cites W2285509918 @default.
• W2967079887 cites W2312081744 @default.
• W2967079887 cites W2603403091 @default.
• W2967079887 cites W2617003309 @default.
• W2967079887 cites W2643397491 @default.
• W2967079887 cites W2701848515 @default.
• W2967079887 cites W2750845740 @default.
• W2967079887 cites W2752052309 @default.
• W2967079887 cites W2769578055 @default.
• W2967079887 cites W2772853850 @default.
• W2967079887 cites W2883061070 @default.
• W2967079887 cites W2905023912 @default.
• W2967079887 cites W2908632748 @default.
• W2967079887 doi "https://doi.org/10.1007/s00256-019-03289-8" @default.
• W2967079887 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6980503" @default.
• W2967079887 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31396667" @default.
• W2967079887 hasPublicationYear "2019" @default.
• W2967079887 type Work @default.
• W2967079887 sameAs 2967079887 @default.
• W2967079887 citedByCount "55" @default.
• W2967079887 countsByYear W29670798872020 @default.
• W2967079887 countsByYear W29670798872021 @default.
• W2967079887 countsByYear W29670798872022 @default.
• W2967079887 countsByYear W29670798872023 @default.
• W2967079887 crossrefType "journal-article" @default.
• W2967079887 hasAuthorship W2967079887A5008491621 @default.
• W2967079887 hasAuthorship W2967079887A5018251444 @default.
• W2967079887 hasAuthorship W2967079887A5040562111 @default.
• W2967079887 hasAuthorship W2967079887A5044473833 @default.
• W2967079887 hasAuthorship W2967079887A5078516450 @default.
• W2967079887 hasBestOaLocation W29670798872 @default.
• W2967079887 hasConcept C108583219 @default.
• W2967079887 hasConcept C124504099 @default.
• W2967079887 hasConcept C126838900 @default.
• W2967079887 hasConcept C153180895 @default.
• W2967079887 hasConcept C154945302 @default.
• W2967079887 hasConcept C163892561 @default.
• W2967079887 hasConcept C2778357063 @default.
• W2967079887 hasConcept C2989005 @default.
• W2967079887 hasConcept C41008148 @default.
• W2967079887 hasConcept C71924100 @default.
• W2967079887 hasConcept C81363708 @default.
• W2967079887 hasConcept C89600930 @default.
• W2967079887 hasConceptScore W2967079887C108583219 @default.
• W2967079887 hasConceptScore W2967079887C124504099 @default.
• W2967079887 hasConceptScore W2967079887C126838900 @default.
• W2967079887 hasConceptScore W2967079887C153180895 @default.
• W2967079887 hasConceptScore W2967079887C154945302 @default.
• W2967079887 hasConceptScore W2967079887C163892561 @default.
• W2967079887 hasConceptScore W2967079887C2778357063 @default.
• W2967079887 hasConceptScore W2967079887C2989005 @default.
• W2967079887 hasConceptScore W2967079887C41008148 @default.
• W2967079887 hasConceptScore W2967079887C71924100 @default.
• W2967079887 hasConceptScore W2967079887C81363708 @default.
• W2967079887 hasConceptScore W2967079887C89600930 @default.
• W2967079887 hasFunder F4320337357 @default.
• W2967079887 hasIssue "3" @default.
• W2967079887 hasLocation W29670798871 @default.
• W2967079887 hasLocation W29670798872 @default.
• W2967079887 hasOpenAccess W2967079887 @default.
• W2967079887 hasPrimaryLocation W29670798871 @default.
• W2967079887 hasRelatedWork W2157102420 @default.
• W2967079887 hasRelatedWork W2969058086 @default.
• W2967079887 hasRelatedWork W3029198973 @default.
• W2967079887 hasRelatedWork W3133861977 @default.
• W2967079887 hasRelatedWork W3167935049 @default.
• W2967079887 hasRelatedWork W3193565141 @default.
• W2967079887 hasRelatedWork W4226493464 @default.
• W2967079887 hasRelatedWork W4293226380 @default.
• W2967079887 hasRelatedWork W4312417841 @default.
• W2967079887 hasRelatedWork W4375867731 @default.

• next