Brain strokes classification by extracting quantum information from CT scans

Anjali Gautam, Balasubramanian Raman

Abstract: Brain strokes are considered a worldwide medical emergency. In this paper, we present a new feature extractor that can classify brain computed tomography (CT) scan images into normal, ischemic stroke or hemorrhagic stroke. The proposed feature extractor is based on comparing neighbours with the center pixel where diagonal neighbours are thresholded with the average intensity of whole image. The remaining horizontal and vertical pixels are obtained by thresholding them with their adjacent neighbour. Thereafter, binary values of the obtained images are used to generate the pattern code for the center pixel. Further, in such a way patter code is computed for whole image which is then used to generate 1-D feature vector known as a local neighbourhood pattern (LNP) descriptor by extracting quantum information from the image. The effectiveness of our feature extracted is proved by conducting experiments on real CT scan images of patients’ brain. For experiments, we have taken nine different classifiers to identify efficacy obtained by extracting LNP features. We have also compared the results obtained by LNP with the results of local binary patterns (LBP) variants, local ternary patterns (LTP), local wavelet patterns (LWP) and local diagonal extrema patterns (LDEP) descriptors. All the experimental results demonstrate that the proposed feature descriptor gives high classification accuracy as compared to other state-of-the-art feature descriptors.