Home // ICCGI 2013, The Eighth International Multi-Conference on Computing in the Global Information Technology // View article

Automated Analysis of CT Slices for Detection of Ideal Midline from Brain CT Scans

Authors:
Xuguang Qi
Sharad Shandilya
Ashwin Belle
Rosalyn Hargraves
Charles Cockrell
Yang Tang
Kevin Ward
Kayvan Najarian

Keywords: ideal midline;IML; midline shift; MLS; CT slice; SSA; mid-sagittal plane

Abstract:
Midline shift detection with high accuracy is crucial in quantitatively analyzing the severity of a brain injury in clinical environments. Accuracy of the estimated ideal midline (IML) significantly affects the accuracy of the computed midline shift. In this work, a two-step process, which consists of computed tomography (CT) Slice Selection Algorithm (SSA) and IML detection, is proposed to automatically estimate the IML in brain CT images. SSA is designed for automatic slice selection. Skull fracture level and intracranial area are used as vital features in the selection. Using skull symmetry and anatomical features, IML detection accurately estimates the position and rotation angle of the IML before calibrating. Experimental results of the multi-stage algorithm were assessed on 1762 CT slices of 40 patients. The accuracy of the proposed system is 91.6%, which makes it viable for use under clinical settings.

Pages: 117 to 121

Copyright: Copyright (c) IARIA, 2013

Publication date: July 21, 2013

Published in: conference

ISSN: 2308-4529

ISBN: 978-1-61208-283-7

Location: Nice, France

Dates: from July 21, 2013 to July 26, 2013