Download PDFOpen PDF in browserGlioblastomas Brain Tumor Segmentation Using Optimized Three-Dimensional (3DU-Net) ModelEasyChair Preprint 1011310 pages•Date: May 12, 2023AbstractAutomated segmentation is a computerized technique that helps to find tumor location, size, and shape. Human segmentation is error prone, time consuming, and needs an expert radiologist. In our study, we developed a customized 3D U-Net model that processes 3D volumetric images for multiclass tumor segmentation.This framework is modified in such a way that the gradient flow is better for finding accurate output. The BraTS 2020 dataset is used to train this network with end-to-end learning strategy followed by defining the proper skip connection from encoder to decoder. In model evaluation, binary cross-entropy with Dice loss functions is utilized.Testing samples are predicted and classified into three regions: whole tumor (WT), tumor core (TC), and enhancing tumor (ET). Model performance is evaluated through Dice coefficient metrics for each class. On the basis of this model, experiments were carried out on the BraTS 2020 dataset which could be considered as a validated benchmark. The segmentation’s obtained results have been validated with ground truth references by computing the Dice Metric parameter.Our clinical partners have attested that the proposed tool could achieve great performances. The aim of this research is to make an advanced tool which could help radiologists to make a more accurate diagnosis. It could also assist clinicians in the early detection of brain tumors. Keyphrases: 3D U-net, Brats dataset, Deep Learning (DL), Gliomas, Resonance Imaging (MRI), Segmentation
|