Title: A promising method for early detection of ischemic stroke area on brain CT images

Authors: Yahiaoui Amina Fatima Zahra; Bessaid Abdelhafid

Addresses: Department of Biomedical Engineering, Technology Faculty, University of Tlemcen, 13000, Algeria ' Department of Biomedical Engineering, Technology Faculty, University of Tlemcen, 13000, Algeria

Abstract: Non-contrast computed tomography (NCCT) has been chosen as the modality of choice for stroke imaging due to its low price and high availability. However, subtle changes of ischemia are hard to visualise and to extract. Alberta Stroke Program Early CT Score (ASPECTS) has been developed to help radiologists to make decisions regarding thrombolytic treatment. Only patients with favourable baseline scans (8-10) benefitted from endovascular revascularisation therapy. The purpose of this study was to develop a novel approach for automated detection of ischemic stroke area on brain CT images within earliest hours after onset symptoms using comparison of brain hemispheres. Our algorithm has five steps: preprocessing, segmentation of Regions of Interest, elimination of old infarcts and cerebrospinal fluid (CSF) space, feature extraction and ASPECTS scoring. The method was applied to 25 patients who presented to LA MEKERRA imaging centre. Its gives an effective results comparing with literature and a high sensitivity 90.8%.

Keywords: stroke detection; computed tomography; ASPECTS score; bilateral comparison.

DOI: 10.1504/IJIM.2018.096298

International Journal of Image Mining, 2018 Vol.3 No.2, pp.139 - 151

Received: 10 Oct 2017
Accepted: 19 Jul 2018

Published online: 22 Nov 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article