Rouco J, Azevedo E, Campilho A. Sensors (Basel). 2016 Mar 9;16(3)
Rouco et al. present a new method that may improve the performance of previous approaches for the automatic detection of the common carotid artery (CCA) lumen centreline on longitudinal B-mode ultrasound images. The authors introduced and evaluated a new software offering an automatic lumen detection using local phase symmetry analysis.
The authors showed that this new software was robust to noise, lumen artefacts, contrast variations and was able to deal with the presence of CCA-like structures, significantly improving the performance of similar, previous approaches in the literature, from 87.5% ± 0.7% of correct detections to 98.3% ± 0.3% in a set of 200 images.
The main take home message of this study is that the authors propose a robust candidate lumen-detection and an advanced candidate selection technique, which takes advantage of relevant carotid artery features and position-based heuristics in order to improve lumen detection.