Kalman-Based Carotid-Artery Longitudinal-Kinetics Estimation and Pattern Recognition

Objectives. The context of the study is the early detection of atherosclerosis. The specific aim of the article is to estimate the longitudinal displacements of the carotid artery wall and assess the discriminative power of the estimated motion patterns to distinguish at-risk individuals from health...

Full description

Saved in:
Bibliographic Details
Published in:IRBM Vol. 38; no. 4; pp. 219 - 223
Main Authors: Qorchi, S., Zahnd, G., Galbrun, D., Sérusclat, A., Moulin, P., Vray, D., Orkisz, M.
Format: Journal Article
Language:English
Published: Elsevier Masson SAS 01.08.2017
Elsevier BV
Elsevier Masson
Subjects:
[SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging
[SPI.ACOU]Engineering Sciences [physics]/Acoustics [physics.class-ph]
[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Acoustics
Bioengineering
Cardiovascular risk
Carotid artery
Engineering Sciences
Imaging
Kalman filter
Life Sciences
Motion tracking
Signal and Image processing
Supervised classification
Ultrasound imaging
Carotid artery
Motion tracking
Ultrasound imaging
Kalman filter
Supervised classification
Cardiovascular risk
ISSN:1959-0318
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Objectives. The context of the study is the early detection of atherosclerosis. The specific aim of the article is to estimate the longitudinal displacements of the carotid artery wall and assess the discriminative power of the estimated motion patterns to distinguish at-risk individuals from healthy subjects. Methods. Motion estimation builds on block matching with a Kalman filter updating the reference-block gray levels, and incorporates a Kalman filter controlling the trajectory via a model using cosine decomposition. The estimated motion patterns were normalized and provided as input features to a machine-learning-based classifier that automatically assigned healthy or at-risk labels. Results. Evaluated on 113 subjects, the method successfully estimated all but one trajectory, and classification achieved 70% sensitivity and 72% specificity. Conclusions. The proposed method is well suited to estimate 2D (longitudinal and radial) quasi-periodic displacements of the arterial wall in ultrasound image sequences. The estimated motion patterns can contribute to discriminate at-risk from healthy subjects. •Carotid artery tissue motion is tracked in ultrasound image sequences.•A Kalman filter based on the Discrete Cosine Transform controls the trajectory.•Subjects are classified in healthy and at-risk groups using a machine learning scheme.•The method was evaluated on 56 healthy volunteers and 57 at-risk patients.•The method demonstrates improved motion tracking and classification results.
ISSN:1959-0318
DOI:10.1016/j.irbm.2017.06.001