Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.12188/17775
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Janjic, Predrag | en_US |
dc.contributor.author | Petrovski, Kristijan | en_US |
dc.contributor.author | Dolgoski, Blagoja | en_US |
dc.contributor.author | Smiley, John | en_US |
dc.contributor.author | Zdravkovski, Panche | en_US |
dc.contributor.author | Pavlovski, Goran | en_US |
dc.contributor.author | Jakjovski, Zlatko | en_US |
dc.contributor.author | Davcheva, Natasha | en_US |
dc.contributor.author | Poposka, Verica | en_US |
dc.contributor.author | Stankov, Aleksandar | en_US |
dc.contributor.author | Rosoklija, Gorazd | en_US |
dc.contributor.author | Petrushevska, Gordana | en_US |
dc.contributor.author | Kocarev, Ljupcho | en_US |
dc.contributor.author | Dwork, Andrew J. | en_US |
dc.date.accessioned | 2022-05-30T07:43:06Z | - |
dc.date.available | 2022-05-30T07:43:06Z | - |
dc.date.issued | 2019-10 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.12188/17775 | - |
dc.description.abstract | Background: Standard segmentation of high-contrast electron micrographs (EM) identifies myelin accurately but does not translate easily into measurements of individual axons and their myelin, even in cross-sections of parallel fibers. We describe automated segmentation and measurement of each myelinated axon and its sheath in EMs of arbitrarily oriented human white matter from autopsies. New methods: Preliminary segmentation of myelin, axons and background by machine learning, using selected filters, precedes automated correction of systematic errors. Final segmentation is done by a deep neural network (DNN). Automated measurement of each putative fiber rejects measures encountering pre-defined artifacts and excludes fibers failing to satisfy pre-defined conditions. Results: Improved segmentation of three sets of 30 annotated images each (two sets from human prefrontal white matter and one from human optic nerve) is achieved with a DNN trained only with a subset of the first set from prefrontal white matter. Total number of myelinated axons identified by the DNN differed from expert segmentation by 0.2%, 2.9%, and -5.1%, respectively. G-ratios differed by 2.96%, 0.74% and 2.83%. Intraclass correlation coefficients between DNN and annotated segmentation were mostly>0.9, indicating nearly interchangeable performance. Comparison with existing method(s): Measurement-oriented studies of arbitrarily oriented fibers from central white matter are rare. Published methods are typically applied to cross-sections of fascicles and measure aggregated areas of myelin sheaths and axons, allowing estimation only of average g-ratio. Conclusions: Automated segmentation and measurement of axons and myelin is complex. We report a feasible approach that has so far proven comparable to manual segmentation. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Elsevier BV | en_US |
dc.relation.ispartof | Journal of Neuroscience Methods | en_US |
dc.subject | myelin | en_US |
dc.subject | measurement | en_US |
dc.subject | electron micrographs | en_US |
dc.subject | axon | en_US |
dc.title | Measurement-oriented deep-learning workflow for improved segmentation of myelin and axons in high-resolution images of human cerebral white matter | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1016/j.jneumeth.2019.108373 | - |
dc.identifier.url | https://api.elsevier.com/content/article/PII:S0165027019302304?httpAccept=text/xml | - |
dc.identifier.url | https://api.elsevier.com/content/article/PII:S0165027019302304?httpAccept=text/plain | - |
dc.identifier.volume | 326 | - |
dc.identifier.fpage | 108373 | - |
item.fulltext | With Fulltext | - |
item.grantfulltext | open | - |
crisitem.author.dept | Faculty of Medicine | - |
crisitem.author.dept | Faculty of Medicine | - |
crisitem.author.dept | Faculty of Medicine | - |
crisitem.author.dept | Faculty of Medicine | - |
crisitem.author.dept | Faculty of Medicine | - |
crisitem.author.dept | Faculty of Medicine | - |
crisitem.author.dept | Faculty of Computer Science and Engineering | - |
crisitem.author.dept | Faculty of Medicine | - |
Appears in Collections: | Faculty of Medicine: Journal Articles |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Measurment oriented deep learning - Elsevier.pdf | 3.85 MB | Adobe PDF | View/Open |
Page view(s)
76
checked on Aug 14, 2024
Download(s)
16
checked on Aug 14, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.