Literature DB >> 31377177

Measurement-oriented deep-learning workflow for improved segmentation of myelin and axons in high-resolution images of human cerebral white matter.

Predrag Janjic1, Kristijan Petrovski2, Blagoja Dolgoski3, John Smiley4, Panche Zdravkovski3, Goran Pavlovski5, Zlatko Jakjovski5, Natasa Davceva5, Verica Poposka5, Aleksandar Stankov5, Gorazd Rosoklija6, Gordana Petrushevska3, Ljupco Kocarev7, Andrew J Dwork8.   

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.
Copyright © 2019 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Convolutional networks; Deep learning; Electron microscopy; Myelin; Segmentation; White matter; g-Ratio

Year:  2019        PMID: 31377177      PMCID: PMC6751333          DOI: 10.1016/j.jneumeth.2019.108373

Source DB:  PubMed          Journal:  J Neurosci Methods        ISSN: 0165-0270            Impact factor:   2.390


  27 in total

1.  Marked loss of myelinated nerve fibers in the human brain with age.

Authors:  Lisbeth Marner; Jens R Nyengaard; Yong Tang; Bente Pakkenberg
Journal:  J Comp Neurol       Date:  2003-07-21       Impact factor: 3.215

2.  A fast learning algorithm for deep belief nets.

Authors:  Geoffrey E Hinton; Simon Osindero; Yee-Whye Teh
Journal:  Neural Comput       Date:  2006-07       Impact factor: 2.026

Review 3.  Intraclass correlations: uses in assessing rater reliability.

Authors:  P E Shrout; J L Fleiss
Journal:  Psychol Bull       Date:  1979-03       Impact factor: 17.737

4.  A semi-automated method for identifying and measuring myelinated nerve fibers in scanning electron microscope images.

Authors:  Heather L More; Jingyun Chen; Eli Gibson; J Maxwell Donelan; Mirza Faisal Beg
Journal:  J Neurosci Methods       Date:  2011-08-04       Impact factor: 2.390

5.  CNP is required for maintenance of axon-glia interactions at nodes of Ranvier in the CNS.

Authors:  Matthew N Rasband; Jane Tayler; Yoshimi Kaga; Yang Yang; Corinna Lappe-Siefke; Klaus-Armin Nave; Rashmi Bansal
Journal:  Glia       Date:  2005-04-01       Impact factor: 7.452

6.  Neuregulin-1/ErbB signaling serves distinct functions in myelination of the peripheral and central nervous system.

Authors:  Bastian G Brinkmann; Amit Agarwal; Michael W Sereda; Alistair N Garratt; Thomas Müller; Hagen Wende; Ruth M Stassart; Schanila Nawaz; Christian Humml; Viktorija Velanac; Konstantin Radyushkin; Sandra Goebbels; Tobias M Fischer; Robin J Franklin; Cary Lai; Hannelore Ehrenreich; Carmen Birchmeier; Markus H Schwab; Klaus Armin Nave
Journal:  Neuron       Date:  2008-08-28       Impact factor: 17.173

Review 7.  The effects of normal aging on myelin and nerve fibers: a review.

Authors:  Alan Peters
Journal:  J Neurocytol       Date:  2002 Sep-Nov

8.  Axonal neuregulin-1 regulates myelin sheath thickness.

Authors:  Galin V Michailov; Michael W Sereda; Bastian G Brinkmann; Tobias M Fischer; Bernhard Haug; Carmen Birchmeier; Lorna Role; Cary Lai; Markus H Schwab; Klaus-Armin Nave
Journal:  Science       Date:  2004-03-25       Impact factor: 47.728

Review 9.  Machines that learn to segment images: a crucial technology for connectomics.

Authors:  Viren Jain; H Sebastian Seung; Srinivas C Turaga
Journal:  Curr Opin Neurobiol       Date:  2010-10       Impact factor: 6.627

10.  Distribution of axon diameters in cortical white matter: an electron-microscopic study on three human brains and a macaque.

Authors:  Daniel Liewald; Robert Miller; Nikos Logothetis; Hans-Joachim Wagner; Almut Schüz
Journal:  Biol Cybern       Date:  2014-08-21       Impact factor: 2.086

View more
  5 in total

1.  A Comparative Study of Natural Language Processing Algorithms Based on Cities Changing Diabetes Vulnerability Data.

Authors:  Siting Wang; Fuman Song; Qinqun Qiao; Yuanyuan Liu; Jiageng Chen; Jun Ma
Journal:  Healthcare (Basel)       Date:  2022-06-15

2.  Deep learning methods and applications in neuroimaging.

Authors:  Jing Sui; MingXia Liu; Jong-Hwan Lee; Jun Zhang; Vince Calhoun
Journal:  J Neurosci Methods       Date:  2020-04-06       Impact factor: 2.987

3.  High-throughput segmentation of unmyelinated axons by deep learning.

Authors:  Emanuele Plebani; Natalia P Biscola; Leif A Havton; Bartek Rajwa; Abida Sanjana Shemonti; Deborah Jaffey; Terry Powley; Janet R Keast; Kun-Han Lu; M Murat Dundar
Journal:  Sci Rep       Date:  2022-01-24       Impact factor: 4.379

4.  Rapid, automated nerve histomorphometry through open-source artificial intelligence.

Authors:  Simeon Christian Daeschler; Marie-Hélène Bourget; Dorsa Derakhshan; Vasudev Sharma; Stoyan Ivaylov Asenov; Tessa Gordon; Julien Cohen-Adad; Gregory Howard Borschel
Journal:  Sci Rep       Date:  2022-04-08       Impact factor: 4.996

5.  MyelTracer: A Semi-Automated Software for Myelin g-Ratio Quantification.

Authors:  Tobias Kaiser; Harrison Mitchell Allen; Ohyoon Kwon; Boaz Barak; Jing Wang; Zhigang He; Minqing Jiang; Guoping Feng
Journal:  eNeuro       Date:  2021-07-21
  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.