FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199461261> ?p ?o ?g. }

• W3199461261 endingPage "102217" @default.
• W3199461261 startingPage "102217" @default.
• W3199461261 abstract "Parapneumonic effusion (PPE) is a common condition that causes death in patients hospitalized with pneumonia. Rapid distinction of complicated PPE (CPPE) from uncomplicated PPE (UPPE) in Computed Tomography (CT) scans is of great importance for the management and medical treatment of PPE. However, UPPE and CPPE display similar appearances in CT scans, and it is challenging to distinguish CPPE from UPPE via a single 2D CT image, whether attempted by a human expert, or by any of the existing disease classification approaches. 3D convolutional neural networks (CNNs) can utilize the entire 3D volume for classification: however, they typically suffer from the intrinsic defect of over-fitting. Therefore, it is important to develop a method that not only overcomes the heavy memory and computational requirements of 3D CNNs, but also leverages the 3D information. In this paper, we propose an uncertainty-guided graph attention network (UG-GAT) that can automatically extract and integrate information from all CT slices in a 3D volume for classification into UPPE, CPPE, and normal control cases. Specifically, we frame the distinction of different cases as a graph classification problem. Each individual is represented as a directed graph with a topological structure, where vertices represent the image features of slices, and edges encode the spatial relationship between them. To estimate the contribution of each slice, we first extract the slice representations with uncertainty, using a Bayesian CNN: we then make use of the uncertainty information to weight each slice during the graph prediction phase in order to enable more reliable decision-making. We construct a dataset consisting of 302 chest CT volumetric data from different subjects (99 UPPE, 99 CPPE and 104 normal control cases) in this study, and to the best of our knowledge, this is the first attempt to classify UPPE, CPPE and normal cases using a deep learning method. Extensive experiments show that our approach is lightweight in demands, and outperforms accepted state-of-the-art methods by a large margin. Code is available at https://github.com/iMED-Lab/UG-GAT." @default.
• W3199461261 created "2021-09-27" @default.
• W3199461261 creator A5004033797 @default.
• W3199461261 creator A5004658590 @default.
• W3199461261 creator A5006418661 @default.
• W3199461261 creator A5017205444 @default.
• W3199461261 creator A5018590276 @default.
• W3199461261 creator A5053784165 @default.
• W3199461261 creator A5054366112 @default.
• W3199461261 creator A5057905491 @default.
• W3199461261 creator A5073239318 @default.
• W3199461261 creator A5083371477 @default.
• W3199461261 creator A5083823986 @default.
• W3199461261 creator A5091617684 @default.
• W3199461261 date "2022-01-01" @default.
• W3199461261 modified "2023-10-10" @default.
• W3199461261 title "Uncertainty-guided graph attention network for parapneumonic effusion diagnosis" @default.
• W3199461261 cites W1603696362 @default.
• W3199461261 cites W1995185582 @default.
• W3199461261 cites W2098337122 @default.
• W3199461261 cites W2141162625 @default.
• W3199461261 cites W2149432024 @default.
• W3199461261 cites W2253429366 @default.
• W3199461261 cites W2394599079 @default.
• W3199461261 cites W2485510676 @default.
• W3199461261 cites W2507945485 @default.
• W3199461261 cites W2533800772 @default.
• W3199461261 cites W2574952845 @default.
• W3199461261 cites W2602906130 @default.
• W3199461261 cites W2603734281 @default.
• W3199461261 cites W2625947337 @default.
• W3199461261 cites W268451672 @default.
• W3199461261 cites W2743008510 @default.
• W3199461261 cites W2770261599 @default.
• W3199461261 cites W2771590529 @default.
• W3199461261 cites W2779494124 @default.
• W3199461261 cites W2803813327 @default.
• W3199461261 cites W2804383999 @default.
• W3199461261 cites W2806489700 @default.
• W3199461261 cites W2897755679 @default.
• W3199461261 cites W2900489637 @default.
• W3199461261 cites W2912031002 @default.
• W3199461261 cites W2946185430 @default.
• W3199461261 cites W2946539594 @default.
• W3199461261 cites W2951965145 @default.
• W3199461261 cites W2957352479 @default.
• W3199461261 cites W2963058055 @default.
• W3199461261 cites W2980471687 @default.
• W3199461261 cites W3026931681 @default.
• W3199461261 cites W3027763298 @default.
• W3199461261 cites W3027914507 @default.
• W3199461261 cites W3048378651 @default.
• W3199461261 cites W3092314636 @default.
• W3199461261 cites W3092530991 @default.
• W3199461261 cites W3095681026 @default.
• W3199461261 cites W3103663607 @default.
• W3199461261 cites W3118440636 @default.
• W3199461261 cites W3131131418 @default.
• W3199461261 doi "https://doi.org/10.1016/j.media.2021.102217" @default.
• W3199461261 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34775280" @default.
• W3199461261 hasPublicationYear "2022" @default.
• W3199461261 type Work @default.
• W3199461261 sameAs 3199461261 @default.
• W3199461261 citedByCount "9" @default.
• W3199461261 countsByYear W31994612612022 @default.
• W3199461261 countsByYear W31994612612023 @default.
• W3199461261 crossrefType "journal-article" @default.
• W3199461261 hasAuthorship W3199461261A5004033797 @default.
• W3199461261 hasAuthorship W3199461261A5004658590 @default.
• W3199461261 hasAuthorship W3199461261A5006418661 @default.
• W3199461261 hasAuthorship W3199461261A5017205444 @default.
• W3199461261 hasAuthorship W3199461261A5018590276 @default.
• W3199461261 hasAuthorship W3199461261A5053784165 @default.
• W3199461261 hasAuthorship W3199461261A5054366112 @default.
• W3199461261 hasAuthorship W3199461261A5057905491 @default.
• W3199461261 hasAuthorship W3199461261A5073239318 @default.
• W3199461261 hasAuthorship W3199461261A5083371477 @default.
• W3199461261 hasAuthorship W3199461261A5083823986 @default.
• W3199461261 hasAuthorship W3199461261A5091617684 @default.
• W3199461261 hasBestOaLocation W31994612612 @default.
• W3199461261 hasConcept C119857082 @default.
• W3199461261 hasConcept C124101348 @default.
• W3199461261 hasConcept C132525143 @default.
• W3199461261 hasConcept C153180895 @default.
• W3199461261 hasConcept C154945302 @default.
• W3199461261 hasConcept C33724603 @default.
• W3199461261 hasConcept C41008148 @default.
• W3199461261 hasConcept C80444323 @default.
• W3199461261 hasConcept C81363708 @default.
• W3199461261 hasConceptScore W3199461261C119857082 @default.
• W3199461261 hasConceptScore W3199461261C124101348 @default.
• W3199461261 hasConceptScore W3199461261C132525143 @default.
• W3199461261 hasConceptScore W3199461261C153180895 @default.
• W3199461261 hasConceptScore W3199461261C154945302 @default.
• W3199461261 hasConceptScore W3199461261C33724603 @default.
• W3199461261 hasConceptScore W3199461261C41008148 @default.
• W3199461261 hasConceptScore W3199461261C80444323 @default.
• W3199461261 hasConceptScore W3199461261C81363708 @default.

• next