Matches in SemOpenAlex for { <https://semopenalex.org/work/W4300641390> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4300641390 abstract "Accurate segmentation of organs-at-risks (OARs) is a precursor for optimizing radiation therapy planning. Existing deep learning-based multi-scale fusion architectures have demonstrated a tremendous capacity for 2D medical image segmentation. The key to their success is aggregating global context and maintaining high resolution representations. However, when translated into 3D segmentation problems, existing multi-scale fusion architectures might underperform due to their heavy computation overhead and substantial data diet. To address this issue, we propose a new OAR segmentation framework, called OARFocalFuseNet, which fuses multi-scale features and employs focal modulation for capturing global-local context across multiple scales. Each resolution stream is enriched with features from different resolution scales, and multi-scale information is aggregated to model diverse contextual ranges. As a result, feature representations are further boosted. The comprehensive comparisons in our experimental setup with OAR segmentation as well as multi-organ segmentation show that our proposed OARFocalFuseNet outperforms the recent state-of-the-art methods on publicly available OpenKBP datasets and Synapse multi-organ segmentation. Both of the proposed methods (3D-MSF and OARFocalFuseNet) showed promising performance in terms of standard evaluation metrics. Our best performing method (OARFocalFuseNet) obtained a dice coefficient of 0.7995 and hausdorff distance of 5.1435 on OpenKBP datasets and dice coefficient of 0.8137 on Synapse multi-organ segmentation dataset." @default.
- W4300641390 created "2022-10-03" @default.
- W4300641390 creator A5008543269 @default.
- W4300641390 creator A5030188696 @default.
- W4300641390 creator A5044673103 @default.
- W4300641390 creator A5067667984 @default.
- W4300641390 creator A5072616384 @default.
- W4300641390 creator A5085120914 @default.
- W4300641390 date "2022-08-15" @default.
- W4300641390 modified "2023-09-30" @default.
- W4300641390 title "An Efficient Multi-Scale Fusion Network for 3D Organ at Risk (OAR) Segmentation" @default.
- W4300641390 doi "https://doi.org/10.48550/arxiv.2208.07417" @default.
- W4300641390 hasPublicationYear "2022" @default.
- W4300641390 type Work @default.
- W4300641390 citedByCount "0" @default.
- W4300641390 crossrefType "posted-content" @default.
- W4300641390 hasAuthorship W4300641390A5008543269 @default.
- W4300641390 hasAuthorship W4300641390A5030188696 @default.
- W4300641390 hasAuthorship W4300641390A5044673103 @default.
- W4300641390 hasAuthorship W4300641390A5067667984 @default.
- W4300641390 hasAuthorship W4300641390A5072616384 @default.
- W4300641390 hasAuthorship W4300641390A5085120914 @default.
- W4300641390 hasBestOaLocation W43006413901 @default.
- W4300641390 hasConcept C105795698 @default.
- W4300641390 hasConcept C111919701 @default.
- W4300641390 hasConcept C121332964 @default.
- W4300641390 hasConcept C124101348 @default.
- W4300641390 hasConcept C124504099 @default.
- W4300641390 hasConcept C151730666 @default.
- W4300641390 hasConcept C153180895 @default.
- W4300641390 hasConcept C154945302 @default.
- W4300641390 hasConcept C163892561 @default.
- W4300641390 hasConcept C22029948 @default.
- W4300641390 hasConcept C25694479 @default.
- W4300641390 hasConcept C26517878 @default.
- W4300641390 hasConcept C2778755073 @default.
- W4300641390 hasConcept C2779343474 @default.
- W4300641390 hasConcept C2779960059 @default.
- W4300641390 hasConcept C33923547 @default.
- W4300641390 hasConcept C38652104 @default.
- W4300641390 hasConcept C41008148 @default.
- W4300641390 hasConcept C62520636 @default.
- W4300641390 hasConcept C65885262 @default.
- W4300641390 hasConcept C86803240 @default.
- W4300641390 hasConcept C89600930 @default.
- W4300641390 hasConceptScore W4300641390C105795698 @default.
- W4300641390 hasConceptScore W4300641390C111919701 @default.
- W4300641390 hasConceptScore W4300641390C121332964 @default.
- W4300641390 hasConceptScore W4300641390C124101348 @default.
- W4300641390 hasConceptScore W4300641390C124504099 @default.
- W4300641390 hasConceptScore W4300641390C151730666 @default.
- W4300641390 hasConceptScore W4300641390C153180895 @default.
- W4300641390 hasConceptScore W4300641390C154945302 @default.
- W4300641390 hasConceptScore W4300641390C163892561 @default.
- W4300641390 hasConceptScore W4300641390C22029948 @default.
- W4300641390 hasConceptScore W4300641390C25694479 @default.
- W4300641390 hasConceptScore W4300641390C26517878 @default.
- W4300641390 hasConceptScore W4300641390C2778755073 @default.
- W4300641390 hasConceptScore W4300641390C2779343474 @default.
- W4300641390 hasConceptScore W4300641390C2779960059 @default.
- W4300641390 hasConceptScore W4300641390C33923547 @default.
- W4300641390 hasConceptScore W4300641390C38652104 @default.
- W4300641390 hasConceptScore W4300641390C41008148 @default.
- W4300641390 hasConceptScore W4300641390C62520636 @default.
- W4300641390 hasConceptScore W4300641390C65885262 @default.
- W4300641390 hasConceptScore W4300641390C86803240 @default.
- W4300641390 hasConceptScore W4300641390C89600930 @default.
- W4300641390 hasLocation W43006413901 @default.
- W4300641390 hasOpenAccess W4300641390 @default.
- W4300641390 hasPrimaryLocation W43006413901 @default.
- W4300641390 hasRelatedWork W2005476934 @default.
- W4300641390 hasRelatedWork W2344532017 @default.
- W4300641390 hasRelatedWork W2345964005 @default.
- W4300641390 hasRelatedWork W2630229246 @default.
- W4300641390 hasRelatedWork W2897195263 @default.
- W4300641390 hasRelatedWork W2972805928 @default.
- W4300641390 hasRelatedWork W2979336375 @default.
- W4300641390 hasRelatedWork W3097503654 @default.
- W4300641390 hasRelatedWork W3128451644 @default.
- W4300641390 hasRelatedWork W3152950745 @default.
- W4300641390 isParatext "false" @default.
- W4300641390 isRetracted "false" @default.
- W4300641390 workType "article" @default.