Extending 2d Deep Learning Architectures To 3d Image Segmentation Problems

Several deep learning architectures are combined for brain tumor segmentation. All the architectures are inspired on recent 2D models where 2D convolution have been replaced by 3D convolutions. The key differences between the architectures are the size of the receptive field and the number of feature maps on the final layers. The obtained results are comparable to the top methods of previous Brats Challenges when median is use to average the results. Further investigation is still needed to analyze the outlier patients.