A fast and accurate brain extraction method for CT head images

Abstract

Background Brain extraction is an essential prerequisite for the automated diagnosis of intracranial lesions and determines, to a certain extent, the accuracy of subsequent lesion recognition, location, and segmentation. Segmentation using a fully convolutional neural network (FCN) yields high accuracy but a relatively slow extraction speed. Methods To address the above issues, this paper proposes an integrated algorithm, FABEM. This method first uses threshold segmentation, closed operation, and image filling to generate a specific mask and then detects the number of connected regions of the mask. If the number of connected regions equals 1, the extraction is done by directly multiplying with the original image. Otherwise, the original image is classified by using a convolutional neural network. The mask is further segmented using the region growth method for the original image with a single-region brain distribution. Otherwise, the mask is adjusted using Deeplabv3+, and then the extraction is completed by multiplying the mask with the original image. Results The algorithm and 5 FCN models were tested on 22 datasets containing different lesions, and the algorithm's performance showed MPA = 0.9958, MIoU = 0.9916, and MBF = 0.9957, comparable to the Deeplabv3+. Still, its extraction speed is much faster than the Deeplabv3+. It can complete the brain extraction of a head CT image in about 0.49 seconds, about 3.5 times that of the Deeplabv3+. Conclusion Thus, this method can achieve accurate brain extraction from head CT images faster, creating a good basis for subsequent brain volume measurement and feature extraction of intracranial lesions.