Key result
A computer-aided diagnosis system for carotid plaque detection achieved an area under the ROC curve of 0.89, demonstrating feasibility and good agreement with expert neurologists.
Why the study?
Does a computer-aided diagnosis system accurately detect carotid plaques in ultrasound images of subjects with and without carotid artery stenosis?
Cross-Sectional (n=44)
Does a computer-aided diagnosis system accurately detect carotid plaques in ultrasound images of subjects with and without carotid artery stenosis?
Effect estimate: AUC 0.89
An automated computer-aided diagnosis system using ultrasound images demonstrated high accuracy (AUC 0.89) for detecting carotid plaques, showing potential as a useful second-opinion tool.
Supports CAD as a potential second-opinion tool in carotid ultrasound; leaves open prospective validation before clinical adoption.
The degree of carotid stenosis is up to now considered one of the most important features for determining the risk of stroke. Ultrasound (US) is a non-invasive technique, relatively inexpensive, portable, which has an excellent temporal resolution. Computer-Aided Diagnosis (CAD) has became one of the major research field in medical imaging and diagnostic radiology. This work presents a CAD system, an automatic prototype software used for carotid plaque detection. We studied US images of 44 subjects, 22 with and 22 subjects without carotid artery stenosis. The CAD system automatically performed the following processing steps: registration of images, detection of lesions by a segmentation method using Watershed algorithm, extraction of dynamic and morphologic features, and classification of plaques through Cluster Analysis. Investigations has been carried out on 287 suspect regions including 61 plaques and 226 non-plaques cases. The area under the ROC curve was 0.89. The experimental results also show that the proposed methods is feasible, and have a good agreement with the expert neurologist. Without the need of any user-interaction, the proposed method generates a detection out-put that may be useful in second opinion.
No takes yet. Share an insight, caveat, or question.
Sottile et al. (2013) conducted a cross-sectional in Carotid atherosclerosis (n=44). Computer-Aided Diagnosis (CAD) system vs. Expert neurologist was evaluated on Carotid plaque detection (AUC 0.89). A computer-aided diagnosis system for carotid plaque detection achieved an area under the ROC curve of 0.89, demonstrating feasibility and good agreement with expert neurologists.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: