Premium
Segmentation of digitized histological sections for quantification of the muscularized vasculature in the mouse hind limb
Author(s) -
XU YIWEN,
PICKERING J. GEOFFREY,
G ZENGXUAN,
WARD AARON D.
Publication year - 2017
Publication title -
journal of microscopy
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.569
H-Index - 111
eISSN - 1365-2818
pISSN - 0022-2720
DOI - 10.1111/jmi.12522
Subject(s) - segmentation , anatomy , stain , staining , hindlimb , deconvolution , biomedical engineering , lumen (anatomy) , immunohistochemistry , blood vessel , immunostaining , computer science , biology , pathology , artificial intelligence , medicine , algorithm , microbiology and biotechnology , endocrinology
Summary Immunohistochemical tissue staining enhances microvasculature characteristics, including the smooth muscle in the medial layer of the vessel walls that is responsible for regulation of blood flow. The vasculature can be imaged in a comprehensive fashion using whole‐slide scanning. However, since each such image potentially contains hundreds of small vessels, manual vessel delineation and quantification is not practically feasible. In this work, we present a fully automatic segmentation and vasculature quantification algorithm for whole‐slide images. We evaluated its performance on tissue samples drawn from the hind limbs of wild‐type mice, stained for smooth muscle using 3,3'‐Diaminobenzidine (DAB) immunostain. The algorithm was designed to be robust to vessel fragmentation due to staining irregularity, and artefactual staining of nonvessel objects. Colour deconvolution was used to isolate the DAB stain for detection of vessel wall fragments. Complete vessels were reconstructed from the fragments by joining endpoints of topological skeletons. Automatic measures of vessel density, perimeter, wall area and local wall thickness were taken. The segmentation algorithm was validated against manual measures, resulting in a Dice similarity coefficient of 89%. The relationships observed between these measures were as expected from a biological standpoint, providing further reinforcement of the accuracy of this system. This system provides a fully automated and accurate means of measuring the arteriolar and venular morphology of vascular smooth muscle.