Abstract

In this study, an optimal feature vector has been extracted from brain computed tomography (CT) images of patients with traumatic brain injury to classify the images into two groups of mild/severe cases. A fully anisotropic Morlet wavelet transform is performed on brain CT images, and the energy of coefficients is extracted as our proposed textural features. Next, genetic algorithms with two fitness functions of (1) K-nearest neighbour and (2) support vector machine classification errors are employed to choose the optimal feature vector. The proposed features and classification algorithm are shown to have reliable performance achieving a good classification accuracy rate of 86.5%.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call