AUTOMATIC 2D AND 3D SEGMENTATION OF GLIOBLASTOMA BRAIN TUMOR

Abstract

The brain tumor is the most common destructive and deadly disease. In general, various imaging modalities such as CT, MRI and PET are used to evaluate the brain tumor. Magnetic resonance imaging (MRI) is a prominent diagnostic method for evaluating these tumors. Gliomas, due to their malignant nature and rapid development, are the most common and aggressive form of brain tumors. In the clinical routine, the method of identifying tumor borders from healthy cells is still a difficult task. Manual segmentation takes time, so we use a deep convolutional neural network to improve efficiency. We present a combined DNN architecture using U-net and MobilenetV2. It exploits both local characteristics and more global contextual characteristics from the 2D MRI FLAIR images. The proposed network has encoder and decoder architecture. The performance metrices such as dice loss, dice coefficient, accuracy and IOU have been calculated. Automated segmentation of 3D MRI is essential for the identification, assessment, and treatment of brain tumors although there is significant interest in machine-learning algorithms for computerized segmentation of brain tumors. The goal of this work is to perform 3D volumetric segmentation using BraTumIA. It is a widely available software application used to separate tumor characteristics on 3D brain MR volumes. BraTumIA has lately been used in a number of clinical trials. In this work, we have segmented 2D slices and 3D volumes of MRI brain tumor images.