A bifurcation identifier for IV-OCT using orthogonal least squares and supervised machine learning

Highlights • The second automated approach to classify hundreds of coronary OCT frames as bifurcation or nonbifurcation. • An important step to improve studies of atherosclerotic plaques in bifurcation regions. • Geometrical features of vessel cross-section are selected by orthogonal least squares m...

Full description

Saved in:
Bibliographic Details
Published in:Computerized medical imaging and graphics 2015-12, Vol.46, p.237-248
Main Authors: Macedo, Maysa M.G, Guimarães, Welingson V.N, Galon, Micheli Z, Takimura, Celso K, Lemos, Pedro A, Gutierrez, Marco Antonio
Format: Article
Language:English
Subjects:
Bifurcation
Classification
Coronary Artery Disease - diagnostic imaging
Data Interpretation, Statistical
Humans
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Internal Medicine
Intravascular
Least-Squares Analysis
Machine learning
Optical coherence tomography
Orthogonal least squares
Other
Pattern Recognition, Automated - methods
Radiography
Reproducibility of Results
Segmentation
Sensitivity and Specificity
Supervised Machine Learning
Tomography, Optical Coherence - methods
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights • The second automated approach to classify hundreds of coronary OCT frames as bifurcation or nonbifurcation. • An important step to improve studies of atherosclerotic plaques in bifurcation regions. • Geometrical features of vessel cross-section are selected by orthogonal least squares method. • The lumen segmentation is comparable to measurements provided by other methods in the literature.
ISSN:0895-6111
1879-0771
DOI:10.1016/j.compmedimag.2015.09.004