ME-Net: Multi-encoder net framework for brain tumor segmentation

MRI plays a vital role to evaluate brain tumor diagnosis and treatment planning. However, the manual segmentation of the MRI image is strenuous. With the development of deep learning, a large number of automatic segmentation methods have been developed, but most of them stay in 2D images, which leads to subpar performance. Aiming at segmenting 3D MRI, we propose a model for brain tumor segmentation with multiple encoders. Our model reduces the difficulty of feature extraction and greatly improves model performance. We also introduced a new loss function named Categorical Dice, and set different weights for different segmented regions at the same time, which solved the problem of voxel imbalance. We evaluated our approach using the online BraTS 2020 Challenge verification. Our proposed method can achieve promising results compared to the state-of-the-art approaches with Dice scores of 0.70249, 0.88267, and 0.73864 for the intact tumor, tumor core, and enhancing tumor.

Automated summary

Our proposed model for brain tumor segmentation with multiple encoders and a new loss function, Categorical Dice, significantly improved performance in segmenting 3D MRI images, effectively addressing voxel imbalance and achieving excellent results in the BraTS 2020 challenge.