FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3143376278> ?p ?o ?g. }

• W3143376278 abstract "Deep learning (DL) has drawn tremendous attention in object localization and recognition for both natural and medical images. U-Net segmentation models have demonstrated superior performance compared to conventional handcrafted feature-based methods. Medical image modality-specific DL models are better at transferring domain knowledge to a relevant target task than those that are pretrained on stock photography images. This helps improve model adaptation, generalization, and class-specific region of interest (ROI) localization. In this study, we train chest X-ray (CXR) modality-specific U-Nets and other state-of-the-art U-Net models for semantic segmentation of tuberculosis (TB)-consistent findings. Automated segmentation of such manifestations could help radiologists reduce errors and supplement decision-making while improving patient care and productivity. Our approach uses the publicly available TBX11K CXR dataset with weak TB annotations, typically provided as bounding boxes, to train a set of U-Net models. Next, we improve the results by augmenting the training data with weak localizations, post-processed into an ROI mask, from a DL classifier that is trained to classify CXRs as showing normal lungs or suspected TB manifestations. Test data are individually derived from the TBX11K CXR training distribution and other cross-institutional collections including the Shenzhen TB and Montgomery TB CXR datasets. We observe that our augmented training strategy helped the CXR modality-specific U-Net models achieve superior performance with test data derived from the TBX11K CXR training distribution as well as from cross-institutional collections (p < 0.05)." @default.
• W3143376278 created "2021-04-13" @default.
• W3143376278 creator A5001587638 @default.
• W3143376278 creator A5005506423 @default.
• W3143376278 creator A5007773014 @default.
• W3143376278 creator A5017208524 @default.
• W3143376278 creator A5065629281 @default.
• W3143376278 date "2021-02-21" @default.
• W3143376278 modified "2023-09-23" @default.
• W3143376278 title "Improved Semantic Segmentation of Tuberculosis-consistent findings in Chest X-rays Using Augmented Training of Modality-specific U-Net Models with Weak Localizations" @default.
• W3143376278 cites W1686810756 @default.
• W3143376278 cites W1901129140 @default.
• W3143376278 cites W1904878066 @default.
• W3143376278 cites W1976863970 @default.
• W3143376278 cites W1994062553 @default.
• W3143376278 cites W2056568601 @default.
• W3143376278 cites W2148347694 @default.
• W3143376278 cites W2152772232 @default.
• W3143376278 cites W2158215861 @default.
• W3143376278 cites W2163605009 @default.
• W3143376278 cites W2183341477 @default.
• W3143376278 cites W2194775991 @default.
• W3143376278 cites W2310042802 @default.
• W3143376278 cites W2608231518 @default.
• W3143376278 cites W2731899572 @default.
• W3143376278 cites W2885134687 @default.
• W3143376278 cites W2888397986 @default.
• W3143376278 cites W2893299523 @default.
• W3143376278 cites W2912529512 @default.
• W3143376278 cites W2913081511 @default.
• W3143376278 cites W2914203365 @default.
• W3143376278 cites W2934946272 @default.
• W3143376278 cites W2939788146 @default.
• W3143376278 cites W2955425717 @default.
• W3143376278 cites W2962746461 @default.
• W3143376278 cites W2962767316 @default.
• W3143376278 cites W2962914239 @default.
• W3143376278 cites W2963163009 @default.
• W3143376278 cites W2963446712 @default.
• W3143376278 cites W2967694144 @default.
• W3143376278 cites W2977613223 @default.
• W3143376278 cites W2979322170 @default.
• W3143376278 cites W3004666248 @default.
• W3143376278 cites W3011825565 @default.
• W3143376278 cites W3034922525 @default.
• W3143376278 cites W3046199400 @default.
• W3143376278 cites W3048802707 @default.
• W3143376278 cites W3091052392 @default.
• W3143376278 cites W3104612611 @default.
• W3143376278 cites W3122023273 @default.
• W3143376278 hasPublicationYear "2021" @default.
• W3143376278 type Work @default.
• W3143376278 sameAs 3143376278 @default.
• W3143376278 citedByCount "0" @default.
• W3143376278 crossrefType "posted-content" @default.
• W3143376278 hasAuthorship W3143376278A5001587638 @default.
• W3143376278 hasAuthorship W3143376278A5005506423 @default.
• W3143376278 hasAuthorship W3143376278A5007773014 @default.
• W3143376278 hasAuthorship W3143376278A5017208524 @default.
• W3143376278 hasAuthorship W3143376278A5065629281 @default.
• W3143376278 hasConcept C153180895 @default.
• W3143376278 hasConcept C154945302 @default.
• W3143376278 hasConcept C169903167 @default.
• W3143376278 hasConcept C2780226545 @default.
• W3143376278 hasConcept C41008148 @default.
• W3143376278 hasConcept C89600930 @default.
• W3143376278 hasConcept C95623464 @default.
• W3143376278 hasConceptScore W3143376278C153180895 @default.
• W3143376278 hasConceptScore W3143376278C154945302 @default.
• W3143376278 hasConceptScore W3143376278C169903167 @default.
• W3143376278 hasConceptScore W3143376278C2780226545 @default.
• W3143376278 hasConceptScore W3143376278C41008148 @default.
• W3143376278 hasConceptScore W3143376278C89600930 @default.
• W3143376278 hasConceptScore W3143376278C95623464 @default.
• W3143376278 hasOpenAccess W3143376278 @default.
• W3143376278 hasRelatedWork W2947856670 @default.
• W3143376278 hasRelatedWork W2998243718 @default.
• W3143376278 hasRelatedWork W3004666248 @default.
• W3143376278 hasRelatedWork W3016142775 @default.
• W3143376278 hasRelatedWork W3017823544 @default.
• W3143376278 hasRelatedWork W3028196528 @default.
• W3143376278 hasRelatedWork W3032911858 @default.
• W3143376278 hasRelatedWork W3033586327 @default.
• W3143376278 hasRelatedWork W3105907673 @default.
• W3143376278 hasRelatedWork W3129249380 @default.
• W3143376278 hasRelatedWork W3131982608 @default.
• W3143376278 hasRelatedWork W3136709974 @default.
• W3143376278 hasRelatedWork W3147783603 @default.
• W3143376278 hasRelatedWork W3149975914 @default.
• W3143376278 hasRelatedWork W3161549308 @default.
• W3143376278 hasRelatedWork W3168680802 @default.
• W3143376278 hasRelatedWork W3196259816 @default.
• W3143376278 hasRelatedWork W3197059146 @default.
• W3143376278 hasRelatedWork W3200565390 @default.
• W3143376278 hasRelatedWork W3204275303 @default.
• W3143376278 isParatext "false" @default.
• W3143376278 isRetracted "false" @default.
• W3143376278 magId "3143376278" @default.
• W3143376278 workType "article" @default.