LSTM Multi-modal UNet for Brain Tumor Segmentation

Deep learning models such as convolutional neural network has been widely used in 3D biomedical image segmentation. However, most of them neither consider the correlations between different modalities, nor fully exploit depth information. To better leverage the multi-modalities and depth information, we proposed an architecture for brain tumor segmentation in multi- modal magnetic resonance images (MRI), named LSTM multi- modal UNet. Experiments results on BRATS-2015 show that our method outperforms the state-of-the-art biomedical segmentation approaches.