Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380136716> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4380136716 abstract "Structural magnetic resonance imaging (sMRI) has shown great clinical value and has been widely used in deep learning (DL) based computer-aided brain disease diagnosis. Previous approaches focused on local shapes and textures in sMRI that may be significant only within a particular domain. The learned representations are likely to contain spurious information and have a poor generalization ability in other diseases and datasets. To facilitate capturing meaningful and robust features, it is necessary to first comprehensively understand the intrinsic pattern of the brain that is not restricted within a single data/task domain. Considering that the brain is a complex connectome of interlinked neurons, the connectional properties in the brain have strong biological significance, which is shared across multiple domains and covers most pathological information. In this work, we propose a connectional style contextual representation learning model (CS-CRL) to capture the intrinsic pattern of the brain, used for multiple brain disease diagnosis. Specifically, it has a vision transformer (ViT) encoder and leverages mask reconstruction as the proxy task and Gram matrices to guide the representation of connectional information. It facilitates the capture of global context and the aggregation of features with biological plausibility. The results indicate that CS-CRL achieves superior accuracy in multiple brain disease diagnosis tasks across six datasets and three diseases and outperforms state-of-the-art models. Furthermore, we demonstrate that CS-CRL captures more brain-network-like properties, better aggregates features, is easier to optimize and is more robust to noise, which explains its superiority in theory. Our source code will be released soon." @default.
- W4380136716 created "2023-06-10" @default.
- W4380136716 creator A5005208212 @default.
- W4380136716 creator A5018970859 @default.
- W4380136716 creator A5023779351 @default.
- W4380136716 creator A5025474414 @default.
- W4380136716 creator A5028056556 @default.
- W4380136716 creator A5035772408 @default.
- W4380136716 creator A5039062226 @default.
- W4380136716 creator A5052756710 @default.
- W4380136716 creator A5072316779 @default.
- W4380136716 date "2023-06-08" @default.
- W4380136716 modified "2023-09-26" @default.
- W4380136716 title "Connectional-Style-Guided Contextual Representation Learning for Brain Disease Diagnosis" @default.
- W4380136716 doi "https://doi.org/10.48550/arxiv.2306.05297" @default.
- W4380136716 hasPublicationYear "2023" @default.
- W4380136716 type Work @default.
- W4380136716 citedByCount "0" @default.
- W4380136716 crossrefType "posted-content" @default.
- W4380136716 hasAuthorship W4380136716A5005208212 @default.
- W4380136716 hasAuthorship W4380136716A5018970859 @default.
- W4380136716 hasAuthorship W4380136716A5023779351 @default.
- W4380136716 hasAuthorship W4380136716A5025474414 @default.
- W4380136716 hasAuthorship W4380136716A5028056556 @default.
- W4380136716 hasAuthorship W4380136716A5035772408 @default.
- W4380136716 hasAuthorship W4380136716A5039062226 @default.
- W4380136716 hasAuthorship W4380136716A5052756710 @default.
- W4380136716 hasAuthorship W4380136716A5072316779 @default.
- W4380136716 hasBestOaLocation W43801367161 @default.
- W4380136716 hasConcept C119857082 @default.
- W4380136716 hasConcept C151730666 @default.
- W4380136716 hasConcept C154945302 @default.
- W4380136716 hasConcept C15744967 @default.
- W4380136716 hasConcept C169760540 @default.
- W4380136716 hasConcept C17744445 @default.
- W4380136716 hasConcept C199539241 @default.
- W4380136716 hasConcept C2776359362 @default.
- W4380136716 hasConcept C2779226451 @default.
- W4380136716 hasConcept C2779343474 @default.
- W4380136716 hasConcept C3018011982 @default.
- W4380136716 hasConcept C41008148 @default.
- W4380136716 hasConcept C59404180 @default.
- W4380136716 hasConcept C86803240 @default.
- W4380136716 hasConcept C94625758 @default.
- W4380136716 hasConcept C97256817 @default.
- W4380136716 hasConcept C97820695 @default.
- W4380136716 hasConceptScore W4380136716C119857082 @default.
- W4380136716 hasConceptScore W4380136716C151730666 @default.
- W4380136716 hasConceptScore W4380136716C154945302 @default.
- W4380136716 hasConceptScore W4380136716C15744967 @default.
- W4380136716 hasConceptScore W4380136716C169760540 @default.
- W4380136716 hasConceptScore W4380136716C17744445 @default.
- W4380136716 hasConceptScore W4380136716C199539241 @default.
- W4380136716 hasConceptScore W4380136716C2776359362 @default.
- W4380136716 hasConceptScore W4380136716C2779226451 @default.
- W4380136716 hasConceptScore W4380136716C2779343474 @default.
- W4380136716 hasConceptScore W4380136716C3018011982 @default.
- W4380136716 hasConceptScore W4380136716C41008148 @default.
- W4380136716 hasConceptScore W4380136716C59404180 @default.
- W4380136716 hasConceptScore W4380136716C86803240 @default.
- W4380136716 hasConceptScore W4380136716C94625758 @default.
- W4380136716 hasConceptScore W4380136716C97256817 @default.
- W4380136716 hasConceptScore W4380136716C97820695 @default.
- W4380136716 hasLocation W43801367161 @default.
- W4380136716 hasOpenAccess W4380136716 @default.
- W4380136716 hasPrimaryLocation W43801367161 @default.
- W4380136716 hasRelatedWork W2398406141 @default.
- W4380136716 hasRelatedWork W2908875379 @default.
- W4380136716 hasRelatedWork W2951388170 @default.
- W4380136716 hasRelatedWork W3001496086 @default.
- W4380136716 hasRelatedWork W3014528967 @default.
- W4380136716 hasRelatedWork W3087493185 @default.
- W4380136716 hasRelatedWork W3095983064 @default.
- W4380136716 hasRelatedWork W3196778703 @default.
- W4380136716 hasRelatedWork W4206762304 @default.
- W4380136716 hasRelatedWork W4313219482 @default.
- W4380136716 isParatext "false" @default.
- W4380136716 isRetracted "false" @default.
- W4380136716 workType "article" @default.