Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225142522> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4225142522 endingPage "2787" @default.
- W4225142522 startingPage "2777" @default.
- W4225142522 abstract "The gold standard for diagnosing lymph node metastasis of papillary thyroid carcinoma is to analyze the whole slide histopathological images (WSIs). Due to the large size of WSIs, recent computer-aided diagnosis approaches adopt the multi-instance learning (MIL) strategy and the key part is how to effectively aggregate the information of different instances (patches). In this paper, a novel transformer-guided framework is proposed to predict lymph node metastasis from WSIs, where we incorporate the transformer mechanism to improve the accuracy from three different aspects. First, we propose an effective transformer-based module for discriminative patch feature extraction, including a lightweight feature extractor with a pruned transformer (Tiny-ViT) and a clustering-based instance selection scheme. Next, we propose a new Transformer-MIL module to capture the relationship of different discriminative patches with sparse distribution on WSIs and better nonlinearly aggregate patch-level features into the slide-level prediction. Considering that the slide-level annotation is relatively limited to training a robust Transformer-MIL, we utilize the pathological relationship between the primary tumor and its lymph node metastasis and develop an effective attention-based mutual knowledge distillation (AMKD) paradigm. Experimental results on our collected WSI dataset demonstrate the efficiency of the proposed Transformer-MIL and attention-based knowledge distillation. Our method outperforms the state-of-the-art methods by over 2.72% in AUC (area under the curve)." @default.
- W4225142522 created "2022-05-01" @default.
- W4225142522 creator A5006938103 @default.
- W4225142522 creator A5012581106 @default.
- W4225142522 creator A5025656383 @default.
- W4225142522 creator A5048773848 @default.
- W4225142522 creator A5084601239 @default.
- W4225142522 date "2022-10-01" @default.
- W4225142522 modified "2023-10-13" @default.
- W4225142522 title "Lymph Node Metastasis Prediction From Whole Slide Images With Transformer-Guided Multiinstance Learning and Knowledge Transfer" @default.
- W4225142522 cites W1871050032 @default.
- W4225142522 cites W1966450612 @default.
- W4225142522 cites W2011430131 @default.
- W4225142522 cites W2040414046 @default.
- W4225142522 cites W2080743883 @default.
- W4225142522 cites W2110261828 @default.
- W4225142522 cites W2194775991 @default.
- W4225142522 cites W2507319753 @default.
- W4225142522 cites W2531897166 @default.
- W4225142522 cites W2571156573 @default.
- W4225142522 cites W2772723798 @default.
- W4225142522 cites W2806857275 @default.
- W4225142522 cites W2890655214 @default.
- W4225142522 cites W2909778238 @default.
- W4225142522 cites W2956228567 @default.
- W4225142522 cites W2964275459 @default.
- W4225142522 cites W2979584421 @default.
- W4225142522 cites W2998544007 @default.
- W4225142522 cites W3026683112 @default.
- W4225142522 cites W3034534840 @default.
- W4225142522 cites W3043535018 @default.
- W4225142522 cites W3089090082 @default.
- W4225142522 cites W3158601984 @default.
- W4225142522 cites W3176719058 @default.
- W4225142522 cites W3198940209 @default.
- W4225142522 cites W3201856807 @default.
- W4225142522 cites W3203480968 @default.
- W4225142522 cites W3204614423 @default.
- W4225142522 doi "https://doi.org/10.1109/tmi.2022.3171418" @default.
- W4225142522 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35486559" @default.
- W4225142522 hasPublicationYear "2022" @default.
- W4225142522 type Work @default.
- W4225142522 citedByCount "8" @default.
- W4225142522 countsByYear W42251425222022 @default.
- W4225142522 countsByYear W42251425222023 @default.
- W4225142522 crossrefType "journal-article" @default.
- W4225142522 hasAuthorship W4225142522A5006938103 @default.
- W4225142522 hasAuthorship W4225142522A5012581106 @default.
- W4225142522 hasAuthorship W4225142522A5025656383 @default.
- W4225142522 hasAuthorship W4225142522A5048773848 @default.
- W4225142522 hasAuthorship W4225142522A5084601239 @default.
- W4225142522 hasConcept C119857082 @default.
- W4225142522 hasConcept C121332964 @default.
- W4225142522 hasConcept C153180895 @default.
- W4225142522 hasConcept C154945302 @default.
- W4225142522 hasConcept C165801399 @default.
- W4225142522 hasConcept C41008148 @default.
- W4225142522 hasConcept C52622490 @default.
- W4225142522 hasConcept C62520636 @default.
- W4225142522 hasConcept C66322947 @default.
- W4225142522 hasConcept C97931131 @default.
- W4225142522 hasConceptScore W4225142522C119857082 @default.
- W4225142522 hasConceptScore W4225142522C121332964 @default.
- W4225142522 hasConceptScore W4225142522C153180895 @default.
- W4225142522 hasConceptScore W4225142522C154945302 @default.
- W4225142522 hasConceptScore W4225142522C165801399 @default.
- W4225142522 hasConceptScore W4225142522C41008148 @default.
- W4225142522 hasConceptScore W4225142522C52622490 @default.
- W4225142522 hasConceptScore W4225142522C62520636 @default.
- W4225142522 hasConceptScore W4225142522C66322947 @default.
- W4225142522 hasConceptScore W4225142522C97931131 @default.
- W4225142522 hasFunder F4320335787 @default.
- W4225142522 hasIssue "10" @default.
- W4225142522 hasLocation W42251425221 @default.
- W4225142522 hasLocation W42251425222 @default.
- W4225142522 hasOpenAccess W4225142522 @default.
- W4225142522 hasPrimaryLocation W42251425221 @default.
- W4225142522 hasRelatedWork W1972656095 @default.
- W4225142522 hasRelatedWork W2024160000 @default.
- W4225142522 hasRelatedWork W2061273563 @default.
- W4225142522 hasRelatedWork W2285052147 @default.
- W4225142522 hasRelatedWork W2729514902 @default.
- W4225142522 hasRelatedWork W2743258233 @default.
- W4225142522 hasRelatedWork W2773500201 @default.
- W4225142522 hasRelatedWork W2806866760 @default.
- W4225142522 hasRelatedWork W2998168123 @default.
- W4225142522 hasRelatedWork W4287995534 @default.
- W4225142522 hasVolume "41" @default.
- W4225142522 isParatext "false" @default.
- W4225142522 isRetracted "false" @default.
- W4225142522 workType "article" @default.