Ideal Midline Detection Using Automated Processing of Brain CT Image

Abstract

Brain ideal midline estimation is vital in medical image processing,\respecially in analyzing the severity of a brain injury in clinical\renvironments. We propose an automated computer-aided ideal midline estimation\rsystem with a two-step process. First, a CT Slice Selection Algorithm (SSA) can\rautomatically select an appropriate subset of slices from a large number of raw\rCT images using the skull’s anatomical features. Next, an ideal midline\rdetection is implemented on the selected subset of slices. An exhaustive\rsymmetric position search is performed based on the anatomical features in the\rdetection. In order to enhance the accuracy of the detection, a global rotation\rassumption is applied to determine the ideal midline by fully considering the\rconnection between slices. Experimental results of the multi-stage algorithm\rwere assessed on 3313 CT slices of 70 patients. The accuracy of the proposed\rsystem is 96.9%, which makes it viable for use under clinical settings.