Estimating Arterial Wall Deformations from Automatic Key-Point Detection and Matching

Assessing arterial-wall motion and deformations may reveal pathologic alterations in biomechanical properties of the parietal tissues and, thus, contribute to detection vascular disease onset. Ultrasound image sequences allow observation this many methods have been developed estimate temporal changes artery diameter wall thickness track 2-D displacements selected points. Some enable assessment shearing or stretching within wall, but none them can all these simultaneously. The method herein proposed was devised simultaneously translation, compression, arterial ultrasound B-mode representing carotid longitudinal section. Salient blob-like patterns, called key points, are automatically detected each frame matched between successive frames. A robust estimator based on an affine transformation model is then used assess frame-to-frame explaining at best key-point matches reject outliers. Realistic simulated were evaluate accuracy robustness against ground truth. also visually assessed clinical sequences, for which true unknown.