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

Janjic, Predrag; Petrovski, Kristijan; Dolgoski, Blagoja; Smiley, John; Zdravkovski, Panche; Pavlovski, Goran; Jakjovski, Zlatko; Davcheva, Natasha; Poposka, Verica; Stankov, Aleksandar; Rosoklija, Gorazd; Petrushevska, Gordana; Kocarev, Ljupco; Dwork, Andrew J

doi:10.1016/j.jneumeth.2019.108373

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

Journal

Journal of Neuroscience Methods

Date Issued

2019-10

Author(s)

Janjic, Predrag

Petrovski, Kristijan

Dolgoski, Blagoja

Smiley, John

Rosoklija, Gorazd

Kocarev, Ljupco

Dwork, Andrew J

DOI

10.1016/j.jneumeth.2019.108373

Abstract

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.