University of Aberdeen logo

AURA - Aberdeen University Research Archive

 

Weakly supervised pre-training for brain tumor segmentation using principal axis measurements of tumor burden

dc.contributor.authorMckone, Joshua E.
dc.contributor.authorLambrou, Tryphon
dc.contributor.authorYe, Xujiong
dc.contributor.authorBrown, James M.
dc.contributor.institutionUniversity of Aberdeen.Computing Scienceen
dc.contributor.institutionUniversity of Aberdeen.Machine Learningen
dc.date.accessioned2024-08-16T11:30:01Z
dc.date.available2024-08-16T11:30:01Z
dc.date.issued2024-06-20
dc.description.statusPeer revieweden
dc.format.extent11
dc.format.extent1794779
dc.identifier291629164
dc.identifiera32b932f-58b5-4d0d-b5d7-6c5c30d5137a
dc.identifier85197392326
dc.identifier.citationMckone, J E, Lambrou, T, Ye, X & Brown, J M 2024, 'Weakly supervised pre-training for brain tumor segmentation using principal axis measurements of tumor burden', Frontiers in Computer Science, vol. 6, 1386514. https://doi.org/10.3389/fcomp.2024.1386514en
dc.identifier.doi10.3389/fcomp.2024.1386514
dc.identifier.issn2624-9898
dc.identifier.otherORCID: /0000-0003-2899-5815/work/165792417
dc.identifier.urihttps://hdl.handle.net/2164/24046
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85197392326&partnerID=8YFLogxKen
dc.identifier.vol6en
dc.language.isoeng
dc.relation.ispartofFrontiers in Computer Scienceen
dc.subjectbrain tumoren
dc.subjectdeep learningen
dc.subjectimage segmentationen
dc.subjectRANOen
dc.subjectweak supervisionen
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subjectComputer Science (miscellaneous)en
dc.subjectComputer Vision and Pattern Recognitionen
dc.subjectComputer Science Applicationsen
dc.subject.lccQA75en
dc.titleWeakly supervised pre-training for brain tumor segmentation using principal axis measurements of tumor burdenen
dc.typeJournal articleen

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Mckone_etal_FiCS_Weakly_Supervised_Pre-training_VOR.pdf
Size:
1.71 MB
Format:
Adobe Portable Document Format

Collections