Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387211912> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4387211912 endingPage "777" @default.
- W4387211912 startingPage "768" @default.
- W4387211912 abstract "Magnetic Resonance Imaging (MRI) acceleration techniques using k-space sub-sampling (KS) can greatly improve the efficiency of MRI-based stroke diagnosis. Although Deep Neural Networks (DNN) have shown great potential on stroke lesion recognition tasks when the MR images are reconstructed from the full k-space, they are vulnerable to the lower quality MR images generated by KS. In this paper, we propose a Distributionally Robust Learning (DRL) approach to improve the performance of stroke recognition DNN models when the MR images are reconstructed from the sub-sampled k-space. For Convolutional Neural Network (CNN) and Vision Transformer (ViT)-based models, our methods improve the stroke classification AUROC and AUPRC by up to 11.91% and 9.32% on the KS-perturbed brain MR images, respectively, compared against Empirical Risk Minimization (ERM) and other baseline defensive methods. We further show that DRL models can successfully recognize the stroke cases from highly perturbed MR images where clinicians may fail, which provides a solution for improved diagnosis in an accelerated MRI setting." @default.
- W4387211912 created "2023-10-01" @default.
- W4387211912 creator A5022424473 @default.
- W4387211912 creator A5030183664 @default.
- W4387211912 creator A5062797260 @default.
- W4387211912 creator A5067887830 @default.
- W4387211912 creator A5068903474 @default.
- W4387211912 creator A5075696701 @default.
- W4387211912 creator A5087577640 @default.
- W4387211912 date "2023-01-01" @default.
- W4387211912 modified "2023-10-01" @default.
- W4387211912 title "Distributionally Robust Image Classifiers for Stroke Diagnosis in Accelerated MRI" @default.
- W4387211912 cites W1901129140 @default.
- W4387211912 cites W1982779347 @default.
- W4387211912 cites W1999913571 @default.
- W4387211912 cites W2103166470 @default.
- W4387211912 cites W2127890285 @default.
- W4387211912 cites W2133272152 @default.
- W4387211912 cites W2194775991 @default.
- W4387211912 cites W2790485410 @default.
- W4387211912 cites W2915335211 @default.
- W4387211912 cites W2962700793 @default.
- W4387211912 cites W3105403262 @default.
- W4387211912 cites W3136481591 @default.
- W4387211912 cites W4205281574 @default.
- W4387211912 cites W4313156423 @default.
- W4387211912 cites W4375869352 @default.
- W4387211912 doi "https://doi.org/10.1007/978-3-031-43904-9_74" @default.
- W4387211912 hasPublicationYear "2023" @default.
- W4387211912 type Work @default.
- W4387211912 citedByCount "0" @default.
- W4387211912 crossrefType "book-chapter" @default.
- W4387211912 hasAuthorship W4387211912A5022424473 @default.
- W4387211912 hasAuthorship W4387211912A5030183664 @default.
- W4387211912 hasAuthorship W4387211912A5062797260 @default.
- W4387211912 hasAuthorship W4387211912A5067887830 @default.
- W4387211912 hasAuthorship W4387211912A5068903474 @default.
- W4387211912 hasAuthorship W4387211912A5075696701 @default.
- W4387211912 hasAuthorship W4387211912A5087577640 @default.
- W4387211912 hasConcept C119857082 @default.
- W4387211912 hasConcept C126838900 @default.
- W4387211912 hasConcept C127413603 @default.
- W4387211912 hasConcept C143409427 @default.
- W4387211912 hasConcept C153180895 @default.
- W4387211912 hasConcept C154945302 @default.
- W4387211912 hasConcept C2780645631 @default.
- W4387211912 hasConcept C31972630 @default.
- W4387211912 hasConcept C41008148 @default.
- W4387211912 hasConcept C50644808 @default.
- W4387211912 hasConcept C71924100 @default.
- W4387211912 hasConcept C78519656 @default.
- W4387211912 hasConcept C81363708 @default.
- W4387211912 hasConceptScore W4387211912C119857082 @default.
- W4387211912 hasConceptScore W4387211912C126838900 @default.
- W4387211912 hasConceptScore W4387211912C127413603 @default.
- W4387211912 hasConceptScore W4387211912C143409427 @default.
- W4387211912 hasConceptScore W4387211912C153180895 @default.
- W4387211912 hasConceptScore W4387211912C154945302 @default.
- W4387211912 hasConceptScore W4387211912C2780645631 @default.
- W4387211912 hasConceptScore W4387211912C31972630 @default.
- W4387211912 hasConceptScore W4387211912C41008148 @default.
- W4387211912 hasConceptScore W4387211912C50644808 @default.
- W4387211912 hasConceptScore W4387211912C71924100 @default.
- W4387211912 hasConceptScore W4387211912C78519656 @default.
- W4387211912 hasConceptScore W4387211912C81363708 @default.
- W4387211912 hasLocation W43872119121 @default.
- W4387211912 hasOpenAccess W4387211912 @default.
- W4387211912 hasPrimaryLocation W43872119121 @default.
- W4387211912 hasRelatedWork W1891287906 @default.
- W4387211912 hasRelatedWork W2036807459 @default.
- W4387211912 hasRelatedWork W2767651786 @default.
- W4387211912 hasRelatedWork W2912288872 @default.
- W4387211912 hasRelatedWork W2961085424 @default.
- W4387211912 hasRelatedWork W3021430260 @default.
- W4387211912 hasRelatedWork W3027997911 @default.
- W4387211912 hasRelatedWork W3181746755 @default.
- W4387211912 hasRelatedWork W4287776258 @default.
- W4387211912 hasRelatedWork W4306674287 @default.
- W4387211912 isParatext "false" @default.
- W4387211912 isRetracted "false" @default.
- W4387211912 workType "book-chapter" @default.