Show simple item record

dc.contributor.authorDamseh, Rafaten_US
dc.contributor.authorPouliot, Philippeen_US
dc.contributor.authorGagnon, Louisen_US
dc.contributor.authorSakadzic, Savaen_US
dc.contributor.authorBoas, Daviden_US
dc.contributor.authorCheriet, Faridaen_US
dc.contributor.authorLesage, Fredericen_US
dc.coverage.spatialUnited Statesen_US
dc.date.accessioned2020-11-03T14:43:20Z
dc.date.available2020-11-03T14:43:20Z
dc.date.issued2019-11
dc.identifierhttps://www.ncbi.nlm.nih.gov/pubmed/30507542
dc.identifier.citationRafat Damseh, Philippe Pouliot, Louis Gagnon, Sava Sakadzic, David Boas, Farida Cheriet, Frederic Lesage. 2019. "Automatic Graph-Based Modeling of Brain Microvessels Captured With Two-Photon Microscopy.." IEEE J Biomed Health Inform, Volume 23, Issue 6, pp. 2551 - 2562. https://doi.org/10.1109/JBHI.2018.2884678
dc.identifier.issn2168-2208
dc.identifier.urihttps://hdl.handle.net/2144/41575
dc.descriptionPublished in final edited form as: IEEE J Biomed Health Inform. 2019 November ; 23(6): 2551–2562.en_US
dc.description.abstractGraph models of cerebral vasculature derived from two-photon microscopy have shown to be relevant to study brain microphysiology. Automatic graphing of these microvessels remain problematic due to the vascular network complexity and two-photon sensitivity limitations with depth. In this paper, we propose a fully automatic processing pipeline to address this issue. The modeling scheme consists of a fully-convolution neural network to segment microvessels, a three-dimensional surface model generator, and a geometry contraction algorithm to produce graphical models with a single connected component. Based on a quantitative assessment using NetMets metrics, at a tolerance of 60 μm, false negative and false positive geometric error 19 rates are 3.8% and 4.2%, respectively, whereas false nega- 20 tive and false positive topological error rates are 6.1% and 4.5%, respectively. Our qualitative evaluation confirms the efficiency of our scheme in generating useful and accurate graphical models.en_US
dc.description.sponsorship299166 - CIHR; R01 NS108472 - NINDS NIH HHS; R24 NS092986 - NINDS NIH HHS; R01 NS091230 - NINDS NIH HHS; U01 HL133362 - NHLBI NIH HHS; R01 EB021018 - NIBIB NIH HHS; P01 NS055104 - NINDS NIH HHS; R01 MH111359 - NIMH NIH HHSen_US
dc.description.urihttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8555544
dc.format.extentp. 2551 - 2562en_US
dc.languageeng
dc.language.isoen_US
dc.relation.ispartofIEEE J Biomed Health Inform
dc.subjectAlgorithmsen_US
dc.subjectAnimalsen_US
dc.subjectBrainen_US
dc.subjectDeep learningen_US
dc.subjectImage processing, computer-assisteden_US
dc.subjectMiceen_US
dc.subjectMicroscopy, fluorescence, multiphotonen_US
dc.subjectMicrovesselsen_US
dc.subjectCerebral microvasculatureen_US
dc.subjectConvolution neural networksen_US
dc.subjectSegmentationen_US
dc.subjectGraphen_US
dc.subjectTwo-photon microscopyen_US
dc.titleAutomatic graph-based modeling of brain microvessels captured with two-photon microscopyen_US
dc.typeArticleen_US
dc.identifier.doi10.1109/JBHI.2018.2884678
pubs.elements-sourcepubmeden_US
pubs.notesEmbargo: Not knownen_US
pubs.organisational-groupBoston Universityen_US
pubs.organisational-groupBoston University, College of Engineeringen_US
pubs.organisational-groupBoston University, College of Engineering, Department of Biomedical Engineeringen_US
pubs.publication-statusPublisheden_US
dc.identifier.orcid0000-0002-6709-7711 (Boas, David)
dc.description.oaversionPublished version
dc.identifier.mycv467960


This item appears in the following Collection(s)

Show simple item record