FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367011797> ?p ?o ?g. }

• W4367011797 endingPage "688" @default.
• W4367011797 startingPage "679" @default.
• W4367011797 abstract "Cervical cancer is a significant disease affecting women worldwide. Regular cervical examination with gynecologists is important for early detection and treatment planning for women with precancers. Precancer is the direct precursor to cervical cancer. However, there is a scarcity of experts and the experts’ assessments are subject to variations in interpretation. In this scenario, the development of a robust automated cervical image classification system is important to augment the experts’ limitations. Ideally, for such a system the class label prediction will vary according to the cervical inspection objectives. Hence, the labeling criteria may not be the same in the cervical image datasets. Moreover, due to the lack of confirmatory test results and inter-rater labeling variation, many images are left unlabeled. Motivated by these challenges, we propose to develop a pretrained cervix model from heterogeneous and partially labeled cervical image datasets. Self-supervised learning (SSL) is employed to build the cervical model. Further, considering data-sharing restrictions, we show how federated self-supervised learning (FSSL) can be employed to develop a cervix model without sharing the cervical images. The task-specific classification models are developed by fine-tuning the cervix model. Two partially labeled cervical image datasets labeled with different classification criteria are used in this study. According to our experimental study, the cervix model prepared with dataset-specific SSL boosts classification accuracy by 2.5% than ImageNet pretrained model. The classification accuracy is further boosted by 1.5% $$uparrow $$ when images from both datasets are combined for SSL. We see that in comparison with the dataset-specific cervix model developed with SSL, the FSSL is performing better." @default.
• W4367011797 created "2023-04-27" @default.
• W4367011797 creator A5018828944 @default.
• W4367011797 creator A5040641104 @default.
• W4367011797 creator A5073995883 @default.
• W4367011797 date "2023-01-01" @default.
• W4367011797 modified "2023-09-28" @default.
• W4367011797 title "Deep Cervix Model Development from Heterogeneous and Partially Labeled Image Datasets" @default.
• W4367011797 cites W1812361043 @default.
• W4367011797 cites W2097989722 @default.
• W4367011797 cites W2167598647 @default.
• W4367011797 cites W2592929672 @default.
• W4367011797 cites W2618245351 @default.
• W4367011797 cites W2803275818 @default.
• W4367011797 cites W2908716024 @default.
• W4367011797 cites W2951934944 @default.
• W4367011797 cites W3016836174 @default.
• W4367011797 cites W3148004426 @default.
• W4367011797 cites W316269977 @default.
• W4367011797 cites W3216923063 @default.
• W4367011797 cites W35451206 @default.
• W4367011797 cites W4206731046 @default.
• W4367011797 cites W4210972068 @default.
• W4367011797 cites W4285722492 @default.
• W4367011797 doi "https://doi.org/10.1007/978-981-19-5191-6_55" @default.
• W4367011797 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37396668" @default.
• W4367011797 hasPublicationYear "2023" @default.
• W4367011797 type Work @default.
• W4367011797 citedByCount "1" @default.
• W4367011797 countsByYear W43670117972023 @default.
• W4367011797 crossrefType "book-chapter" @default.
• W4367011797 hasAuthorship W4367011797A5018828944 @default.
• W4367011797 hasAuthorship W4367011797A5040641104 @default.
• W4367011797 hasAuthorship W4367011797A5073995883 @default.
• W4367011797 hasBestOaLocation W43670117972 @default.
• W4367011797 hasConcept C115961682 @default.
• W4367011797 hasConcept C119857082 @default.
• W4367011797 hasConcept C121608353 @default.
• W4367011797 hasConcept C126322002 @default.
• W4367011797 hasConcept C153180895 @default.
• W4367011797 hasConcept C154945302 @default.
• W4367011797 hasConcept C2777740455 @default.
• W4367011797 hasConcept C2778220009 @default.
• W4367011797 hasConcept C41008148 @default.
• W4367011797 hasConcept C71924100 @default.
• W4367011797 hasConceptScore W4367011797C115961682 @default.
• W4367011797 hasConceptScore W4367011797C119857082 @default.
• W4367011797 hasConceptScore W4367011797C121608353 @default.
• W4367011797 hasConceptScore W4367011797C126322002 @default.
• W4367011797 hasConceptScore W4367011797C153180895 @default.
• W4367011797 hasConceptScore W4367011797C154945302 @default.
• W4367011797 hasConceptScore W4367011797C2777740455 @default.
• W4367011797 hasConceptScore W4367011797C2778220009 @default.
• W4367011797 hasConceptScore W4367011797C41008148 @default.
• W4367011797 hasConceptScore W4367011797C71924100 @default.
• W4367011797 hasLocation W43670117971 @default.
• W4367011797 hasLocation W43670117972 @default.
• W4367011797 hasLocation W43670117973 @default.
• W4367011797 hasLocation W43670117974 @default.
• W4367011797 hasOpenAccess W4367011797 @default.
• W4367011797 hasPrimaryLocation W43670117971 @default.
• W4367011797 hasRelatedWork W2961085424 @default.
• W4367011797 hasRelatedWork W3046775127 @default.
• W4367011797 hasRelatedWork W3170094116 @default.
• W4367011797 hasRelatedWork W4205958290 @default.
• W4367011797 hasRelatedWork W4285260836 @default.
• W4367011797 hasRelatedWork W4286629047 @default.
• W4367011797 hasRelatedWork W4306321456 @default.
• W4367011797 hasRelatedWork W4306674287 @default.
• W4367011797 hasRelatedWork W4386462264 @default.
• W4367011797 hasRelatedWork W4224009465 @default.
• W4367011797 isParatext "false" @default.
• W4367011797 isRetracted "false" @default.
• W4367011797 workType "book-chapter" @default.