3D Deep Learning for Automatic Brain MR Tumor Segmentation with T-Spline Intensity Inhomogeneity Correction

Abstract

Automatic segmentation of brain tumor data is a herculean task for medical applications, particularly in cancer diagnosis. This paper emulates some challenging issues such as noise sensitivity, partial volume averaging, intensity inhomogeneity, inter-slice intensity variations, and intensity non-standardization. This paper intends a novel N3T-spline intensity inhomogeneity correction for bias field correction and the three dimension convolutional neural network (3DCNN) for automatic segmentation. The proposed work consists of four stages (i) pre-processing, (ii) feature extraction (iii) automatic segmentation and (iv) post-processing. In the pre-processing step, novel nonparametric non-uniformity normalization (N3) based T-spline approach is proposed to correct the bias field distortion, which recedes the noises and intensity variations. The extended gray level co-occurrence matrix (EGLCM) is a feature extraction technique, from which the texture patches more suitable for brain tumor segmentation can be extracted. The proposed 3DCNN automatically segments the brain tumor and divides the discrete abnormal tissues from the raw data and EGLCM features. Finally, a simple threshold scheme is adapted on the segmented result to correct the false labels and eliminate the 3D connected small regions. The simulation results in the proposed segmentation procedure could acquire competitive performance as compared with the existing procedure for the BRATS 2015 dataset.