Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136168210> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W3136168210 abstract "Universal Lesion Detection (ULD) in computed tomography plays an essential role in computer-aided diagnosis. Promising ULD results have been reported by coarse-to-fine two-stage detection approaches, but such two-stage ULD methods still suffer from issues like imbalance of positive v.s. negative anchors during object proposal and insufficient supervision problem during localization regression and classification of the region of interest (RoI) proposals. While leveraging pseudo segmentation masks such as bounding map (BM) can reduce the above issues to some degree, it is still an open problem to effectively handle the diverse lesion shapes and sizes in ULD. In this paper, we propose a BM-based conditional training for two-stage ULD, which can (i) reduce positive vs. negative anchor imbalance via BM-based conditioning (BMC) mechanism for anchor sampling instead of traditional IoU-based rule; and (ii) adaptively compute size-adaptive BM (ABM) from lesion bounding box, which is used for improving lesion localization accuracy via ABMsupervised segmentation. Experiments with four state-of-the-art methods show that the proposed approach can bring an almost free detection accuracy improvement without requiring expensive lesion mask annotations." @default.
- W3136168210 created "2021-03-29" @default.
- W3136168210 creator A5012324763 @default.
- W3136168210 creator A5028465673 @default.
- W3136168210 creator A5084846204 @default.
- W3136168210 creator A5091049278 @default.
- W3136168210 date "2021-03-23" @default.
- W3136168210 modified "2023-09-24" @default.
- W3136168210 title "Conditional Training with Bounding Map for Universal Lesion Detection" @default.
- W3136168210 cites W2963663752 @default.
- W3136168210 cites W3099683629 @default.
- W3136168210 hasPublicationYear "2021" @default.
- W3136168210 type Work @default.
- W3136168210 sameAs 3136168210 @default.
- W3136168210 citedByCount "0" @default.
- W3136168210 crossrefType "posted-content" @default.
- W3136168210 hasAuthorship W3136168210A5012324763 @default.
- W3136168210 hasAuthorship W3136168210A5028465673 @default.
- W3136168210 hasAuthorship W3136168210A5084846204 @default.
- W3136168210 hasAuthorship W3136168210A5091049278 @default.
- W3136168210 hasConcept C115961682 @default.
- W3136168210 hasConcept C118552586 @default.
- W3136168210 hasConcept C147037132 @default.
- W3136168210 hasConcept C153180895 @default.
- W3136168210 hasConcept C154945302 @default.
- W3136168210 hasConcept C2776151529 @default.
- W3136168210 hasConcept C2781156865 @default.
- W3136168210 hasConcept C2781238097 @default.
- W3136168210 hasConcept C31972630 @default.
- W3136168210 hasConcept C41008148 @default.
- W3136168210 hasConcept C63584917 @default.
- W3136168210 hasConcept C71924100 @default.
- W3136168210 hasConcept C89600930 @default.
- W3136168210 hasConceptScore W3136168210C115961682 @default.
- W3136168210 hasConceptScore W3136168210C118552586 @default.
- W3136168210 hasConceptScore W3136168210C147037132 @default.
- W3136168210 hasConceptScore W3136168210C153180895 @default.
- W3136168210 hasConceptScore W3136168210C154945302 @default.
- W3136168210 hasConceptScore W3136168210C2776151529 @default.
- W3136168210 hasConceptScore W3136168210C2781156865 @default.
- W3136168210 hasConceptScore W3136168210C2781238097 @default.
- W3136168210 hasConceptScore W3136168210C31972630 @default.
- W3136168210 hasConceptScore W3136168210C41008148 @default.
- W3136168210 hasConceptScore W3136168210C63584917 @default.
- W3136168210 hasConceptScore W3136168210C71924100 @default.
- W3136168210 hasConceptScore W3136168210C89600930 @default.
- W3136168210 hasLocation W31361682101 @default.
- W3136168210 hasOpenAccess W3136168210 @default.
- W3136168210 hasPrimaryLocation W31361682101 @default.
- W3136168210 hasRelatedWork W2806218207 @default.
- W3136168210 hasRelatedWork W2886686736 @default.
- W3136168210 hasRelatedWork W2897538002 @default.
- W3136168210 hasRelatedWork W2921110433 @default.
- W3136168210 hasRelatedWork W2921331879 @default.
- W3136168210 hasRelatedWork W2974527462 @default.
- W3136168210 hasRelatedWork W2979367232 @default.
- W3136168210 hasRelatedWork W2985903570 @default.
- W3136168210 hasRelatedWork W2995779812 @default.
- W3136168210 hasRelatedWork W3007351280 @default.
- W3136168210 hasRelatedWork W3115370317 @default.
- W3136168210 hasRelatedWork W3124418612 @default.
- W3136168210 hasRelatedWork W3161689197 @default.
- W3136168210 hasRelatedWork W3201749299 @default.
- W3136168210 hasRelatedWork W3203379702 @default.
- W3136168210 hasRelatedWork W3204000660 @default.
- W3136168210 hasRelatedWork W3207213789 @default.
- W3136168210 hasRelatedWork W3208415705 @default.
- W3136168210 hasRelatedWork W3214517710 @default.
- W3136168210 hasRelatedWork W898114428 @default.
- W3136168210 isParatext "false" @default.
- W3136168210 isRetracted "false" @default.
- W3136168210 magId "3136168210" @default.
- W3136168210 workType "article" @default.