Brain Tumor Segmentation on Multimodal 3D-MRI using Deep Learning Method
Peicheng Wu, Qing Chang
Abstract
Gliomas are the most common primary brain malignancies. Accurate and robust tumor segmentation is important for diagnosis, treatment planning and risk factor identification. In this paper, we present a deep learning-based framework for brain tumor segmentation, using multimodal MRI scans. A 3D U-net based deep learning model has been trained for the brain tumor segmentation task. Our architecture is essentially a deeply-supervised encoder-decoder network, where the encoder and decoder sub-networks are connected through a series of nested, dense skip paths. We train our model on the BraTS 2019 dataset. Dice coefficients for enhancing tumor, tumor core, and the whole tumor are 0.757, 0.817 and 0.891 respectively on the validation dataset.