Abstract

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.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call