Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381198685> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4381198685 endingPage "1" @default.
- W4381198685 startingPage "1" @default.
- W4381198685 abstract "The fusion of multi-modal medical data is essential to assist medical experts to make treatment decisions for precision medicine. For example, combining the whole slide histopathological images (WSIs) and tabular clinical data can more accurately predict the lymph node metastasis (LNM) of papillary thyroid carcinoma before surgery to avoid unnecessary lymph node resection. However, the huge-sized WSI provides much more high-dimensional information than low-dimensional tabular clinical data, making the information alignment challenging in the multi-modal WSI analysis tasks. This paper presents a novel transformer-guided multi-modal multi-instance learning framework to predict lymph node metastasis from both WSIs and tabular clinical data. We first propose an effective multi-instance grouping scheme, named siamese attention-based feature grouping (SAG), to group high-dimensional WSIs into representative low-dimensional feature embeddings for fusion. We then design a novel bottleneck shared-specific feature transfer module (BSFT) to explore the shared and specific features between different modalities, where a few learnable bottleneck tokens are utilized for knowledge transfer between modalities. Moreover, a modal adaptation and orthogonal projection scheme were incorporated to further encourage BSFT to learn shared and specific features from multi-modal data. Finally, the shared and specific features are dynamically aggregated via an attention mechanism for slide-level prediction. Experimental results on our collected lymph node metastasis dataset demonstrate the efficiency of our proposed components and our framework achieves the best performance with AUC (area under the curve) of 97.34%, outperforming the state-of-the-art methods by over 1.27%." @default.
- W4381198685 created "2023-06-20" @default.
- W4381198685 creator A5012581106 @default.
- W4381198685 creator A5024076883 @default.
- W4381198685 creator A5048773848 @default.
- W4381198685 creator A5084601239 @default.
- W4381198685 creator A5086428742 @default.
- W4381198685 date "2023-01-01" @default.
- W4381198685 modified "2023-10-05" @default.
- W4381198685 title "Shared-specific Feature Learning with Bottleneck Fusion Transformer for Multi-modal Whole Slide Image Analysis" @default.
- W4381198685 doi "https://doi.org/10.1109/tmi.2023.3287256" @default.
- W4381198685 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37335798" @default.
- W4381198685 hasPublicationYear "2023" @default.
- W4381198685 type Work @default.
- W4381198685 citedByCount "1" @default.
- W4381198685 countsByYear W43811986852023 @default.
- W4381198685 crossrefType "journal-article" @default.
- W4381198685 hasAuthorship W4381198685A5012581106 @default.
- W4381198685 hasAuthorship W4381198685A5024076883 @default.
- W4381198685 hasAuthorship W4381198685A5048773848 @default.
- W4381198685 hasAuthorship W4381198685A5084601239 @default.
- W4381198685 hasAuthorship W4381198685A5086428742 @default.
- W4381198685 hasConcept C119857082 @default.
- W4381198685 hasConcept C124101348 @default.
- W4381198685 hasConcept C127413603 @default.
- W4381198685 hasConcept C138885662 @default.
- W4381198685 hasConcept C149635348 @default.
- W4381198685 hasConcept C152139883 @default.
- W4381198685 hasConcept C153180895 @default.
- W4381198685 hasConcept C154945302 @default.
- W4381198685 hasConcept C185592680 @default.
- W4381198685 hasConcept C188027245 @default.
- W4381198685 hasConcept C2776401178 @default.
- W4381198685 hasConcept C2780513914 @default.
- W4381198685 hasConcept C41008148 @default.
- W4381198685 hasConcept C41895202 @default.
- W4381198685 hasConcept C59404180 @default.
- W4381198685 hasConcept C60008888 @default.
- W4381198685 hasConcept C62611344 @default.
- W4381198685 hasConcept C66938386 @default.
- W4381198685 hasConcept C71139939 @default.
- W4381198685 hasConceptScore W4381198685C119857082 @default.
- W4381198685 hasConceptScore W4381198685C124101348 @default.
- W4381198685 hasConceptScore W4381198685C127413603 @default.
- W4381198685 hasConceptScore W4381198685C138885662 @default.
- W4381198685 hasConceptScore W4381198685C149635348 @default.
- W4381198685 hasConceptScore W4381198685C152139883 @default.
- W4381198685 hasConceptScore W4381198685C153180895 @default.
- W4381198685 hasConceptScore W4381198685C154945302 @default.
- W4381198685 hasConceptScore W4381198685C185592680 @default.
- W4381198685 hasConceptScore W4381198685C188027245 @default.
- W4381198685 hasConceptScore W4381198685C2776401178 @default.
- W4381198685 hasConceptScore W4381198685C2780513914 @default.
- W4381198685 hasConceptScore W4381198685C41008148 @default.
- W4381198685 hasConceptScore W4381198685C41895202 @default.
- W4381198685 hasConceptScore W4381198685C59404180 @default.
- W4381198685 hasConceptScore W4381198685C60008888 @default.
- W4381198685 hasConceptScore W4381198685C62611344 @default.
- W4381198685 hasConceptScore W4381198685C66938386 @default.
- W4381198685 hasConceptScore W4381198685C71139939 @default.
- W4381198685 hasFunder F4320335787 @default.
- W4381198685 hasLocation W43811986851 @default.
- W4381198685 hasLocation W43811986852 @default.
- W4381198685 hasOpenAccess W4381198685 @default.
- W4381198685 hasPrimaryLocation W43811986851 @default.
- W4381198685 hasRelatedWork W2382607599 @default.
- W4381198685 hasRelatedWork W2546942002 @default.
- W4381198685 hasRelatedWork W2573334707 @default.
- W4381198685 hasRelatedWork W2592385986 @default.
- W4381198685 hasRelatedWork W2944661354 @default.
- W4381198685 hasRelatedWork W2970216048 @default.
- W4381198685 hasRelatedWork W2998168123 @default.
- W4381198685 hasRelatedWork W4285529594 @default.
- W4381198685 hasRelatedWork W4287995534 @default.
- W4381198685 hasRelatedWork W62276109 @default.
- W4381198685 isParatext "false" @default.
- W4381198685 isRetracted "false" @default.
- W4381198685 workType "article" @default.