Matches in SemOpenAlex for { <https://semopenalex.org/work/W3170806405> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3170806405 abstract "Predicting outcomes, such as survival or metastasis for individual cancer patients is a crucial component of precision oncology. Machine learning (ML) offers a promising way to exploit rich multi-modal data, including clinical information and imaging to learn predictors of disease trajectory and help inform clinical decision making. In this paper, we present a novel graph-based approach to incorporate imaging characteristics of existing cancer spread to local lymph nodes (LNs) as well as their connectivity patterns in a prognostic ML model. We trained an edge-gated Graph Convolutional Network (Gated-GCN) to accurately predict the risk of distant metastasis (DM) by propagating information across the LN graph with the aid of soft edge attention mechanism. In a cohort of 1570 head and neck cancer patients, the Gated-GCN achieves AUROC of 0.757 for 2-year DM classification and $C$-index of 0.725 for lifetime DM risk prediction, outperforming current prognostic factors as well as previous approaches based on aggregated LN features. We also explored the importance of graph structure and individual lymph nodes through ablation experiments and interpretability studies, highlighting the importance of considering individual LN characteristics as well as the relationships between regions of cancer spread." @default.
- W3170806405 created "2021-06-22" @default.
- W3170806405 creator A5010487226 @default.
- W3170806405 creator A5057938768 @default.
- W3170806405 date "2021-06-03" @default.
- W3170806405 modified "2023-09-27" @default.
- W3170806405 title "Lymph Node Graph Neural Networks for Cancer Metastasis Prediction." @default.
- W3170806405 cites W1522301498 @default.
- W3170806405 cites W1536690700 @default.
- W3170806405 cites W2034132629 @default.
- W3170806405 cites W2124891284 @default.
- W3170806405 cites W2129925362 @default.
- W3170806405 cites W2148754315 @default.
- W3170806405 cites W2167205245 @default.
- W3170806405 cites W2600642189 @default.
- W3170806405 cites W2767128594 @default.
- W3170806405 cites W2768242641 @default.
- W3170806405 cites W2783134495 @default.
- W3170806405 cites W2888600909 @default.
- W3170806405 cites W2918342466 @default.
- W3170806405 cites W2935059896 @default.
- W3170806405 cites W2944218525 @default.
- W3170806405 cites W2944401074 @default.
- W3170806405 cites W2949117887 @default.
- W3170806405 cites W2949197630 @default.
- W3170806405 cites W2970971581 @default.
- W3170806405 cites W2981557009 @default.
- W3170806405 cites W3007332492 @default.
- W3170806405 cites W3082330280 @default.
- W3170806405 cites W3107533236 @default.
- W3170806405 cites W3123565549 @default.
- W3170806405 hasPublicationYear "2021" @default.
- W3170806405 type Work @default.
- W3170806405 sameAs 3170806405 @default.
- W3170806405 citedByCount "0" @default.
- W3170806405 crossrefType "posted-content" @default.
- W3170806405 hasAuthorship W3170806405A5010487226 @default.
- W3170806405 hasAuthorship W3170806405A5057938768 @default.
- W3170806405 hasConcept C108583219 @default.
- W3170806405 hasConcept C119857082 @default.
- W3170806405 hasConcept C132525143 @default.
- W3170806405 hasConcept C154945302 @default.
- W3170806405 hasConcept C2781067378 @default.
- W3170806405 hasConcept C41008148 @default.
- W3170806405 hasConcept C71924100 @default.
- W3170806405 hasConcept C80444323 @default.
- W3170806405 hasConcept C81363708 @default.
- W3170806405 hasConceptScore W3170806405C108583219 @default.
- W3170806405 hasConceptScore W3170806405C119857082 @default.
- W3170806405 hasConceptScore W3170806405C132525143 @default.
- W3170806405 hasConceptScore W3170806405C154945302 @default.
- W3170806405 hasConceptScore W3170806405C2781067378 @default.
- W3170806405 hasConceptScore W3170806405C41008148 @default.
- W3170806405 hasConceptScore W3170806405C71924100 @default.
- W3170806405 hasConceptScore W3170806405C80444323 @default.
- W3170806405 hasConceptScore W3170806405C81363708 @default.
- W3170806405 hasLocation W31708064051 @default.
- W3170806405 hasOpenAccess W3170806405 @default.
- W3170806405 hasPrimaryLocation W31708064051 @default.
- W3170806405 hasRelatedWork W1992377244 @default.
- W3170806405 hasRelatedWork W2099009891 @default.
- W3170806405 hasRelatedWork W2104873924 @default.
- W3170806405 hasRelatedWork W2129326993 @default.
- W3170806405 hasRelatedWork W2397988766 @default.
- W3170806405 hasRelatedWork W2558320085 @default.
- W3170806405 hasRelatedWork W2890143692 @default.
- W3170806405 hasRelatedWork W2890705060 @default.
- W3170806405 hasRelatedWork W2962819936 @default.
- W3170806405 hasRelatedWork W2964279023 @default.
- W3170806405 hasRelatedWork W3005422048 @default.
- W3170806405 hasRelatedWork W3034288498 @default.
- W3170806405 hasRelatedWork W3171807193 @default.
- W3170806405 hasRelatedWork W3191784942 @default.
- W3170806405 hasRelatedWork W3201274471 @default.
- W3170806405 hasRelatedWork W3201741481 @default.
- W3170806405 hasRelatedWork W3202179572 @default.
- W3170806405 hasRelatedWork W637916531 @default.
- W3170806405 hasRelatedWork W3131268382 @default.
- W3170806405 isParatext "false" @default.
- W3170806405 isRetracted "false" @default.
- W3170806405 magId "3170806405" @default.
- W3170806405 workType "article" @default.