Key result
An automatic lumen detection method using local phase symmetry analysis improved correct detections of the common carotid artery lumen centerline from 87.5% to 98.3% compared to a previous approach.
The proposed phase symmetry-based method provides highly robust and accurate automatic detection of the common carotid artery lumen centerline on ultrasound images.
Answers are grounded in this paper and cite their sources.
May support automated carotid ultrasound analysis; hypothesis-generating pending prospective validation.
This article describes a method that improves the performance of previous approaches for the automatic detection of the common carotid artery (CCA) lumen centerline on longitudinal B-mode ultrasound images. We propose to detect several lumen centerline candidates using local symmetry analysis based on local phase information of dark structures at an appropriate scale. These candidates are analyzed with selection mechanisms that use symmetry, contrast or intensity features in combination with position-based heuristics. Several experimental results are provided to evaluate the robustness and performance of the proposed method in comparison with previous approaches. These results lead to the conclusion that our proposal is robust to noise, lumen artifacts, contrast variations and that is able to deal with the presence of CCA-like structures, significantly improving the performance of our previous approach, from 87.5% ± 0.7% of correct detections to 98.3% ± 0.3% in a set of 200 images.
No takes yet. Share an insight, caveat, or question.
Rouco et al. (2016) studied Common carotid artery (CCA) lumen centerline detection (n=200). Automatic lumen detection using local phase symmetry analysis vs. Previous approach was evaluated on Correct detections of the CCA lumen centerline. An automatic lumen detection method using local phase symmetry analysis improved correct detections of the common carotid artery lumen centerline from 87.5% to 98.3% compared to a previous approach.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: