Brain Tumor Segmentation

Introduction

Harmful to human life and health, brain tumor needs to be diagnosed by more accurate and efficient methods. The semantic segmentation algorithm based on deep learning has gradually become the mainstream method to tackle this disease. Multi-modality magnetic resonance imaging (MRI) images are applied to segment specific lesion areas of the brain tumor. The segmentation task of brain tumor needs to include multiple different lesion areas and require multi-modality data for voxel classification. Different modalities specialize in different segmentation tasks, single-modality data do not take full advantage of modality correlations.

Result