The Atheromatic CAD system using a Support Vector Machine classifier achieved 83.7% accuracy in classifying carotid plaques as symptomatic or asymptomatic in B-mode ultrasound images.
Does the Atheromatic CAD system accurately classify carotid plaques as symptomatic or asymptomatic in B-mode ultrasound images?
A novel Computer Aided Diagnosis system using Support Vector Machine classification can differentiate symptomatic from asymptomatic carotid plaques on ultrasound with 83.7% accuracy.
In this paper, we present a Computer Aided Diagnosis (CAD) based technique (Atheromatic system) for classification of carotid plaques in B-mode ultrasound images into symptomatic or asymptomatic classes. This system, called Atheromatic, has two steps: (i) feature extraction using a combination of Discrete Wavelet Transform (DWT) and averaging algorithms and (ii) classification using Support Vector Machine (SVM) classifier for automated decision making. The CAD system was built and tested using a database consisting of 150 asymptomatic and 196 symptomatic plaque regions of interests which were manually segmented. The ground truth of each plaque was determined based on the presence or absence of symptoms. Three-fold cross-validation protocol was adapted for developing and testing the classifiers. The SVM classifier with a polynomial kernel of order 2 recorded the highest classification accuracy of 83.7%. In the clinical scenario, such a technique, after much more validation, can be used as an adjunct tool to aid physicians by giving a second opinion on the nature of the plaque (symptomatic/asymptomatic) which would help in the more confident determination of the subsequent treatment regime for the patient.
Acharya et al. (2012) studied Carotid plaques (n=346). Atheromatic system (Computer Aided Diagnosis technique) vs. Clinical ground truth was evaluated on Classification accuracy. The Atheromatic CAD system using a Support Vector Machine classifier achieved 83.7% accuracy in classifying carotid plaques as symptomatic or asymptomatic in B-mode ultrasound images.