Glioma Segmentation with Cascaded UNet

MRI analysis takes central position in brain tumor diagnosis and treatment, thus its precise evaluation is crucially important. However, its 3D nature imposes several challenges, so the analysis is often performed on 2D projections that reduces the complexity, but increases bias. On the other hand, time consuming 3D evaluation, like segmentation, is able to provide precise estimation of a number of valuable spatial characteristics, giving us understanding about the course of the disease. Recent studies focusing on the segmentation task, report superior performance of Deep Learning methods compared to classical computer vision algorithms. But still, it remains a challenging problem. In this paper we present deep cascaded approach for automatic brain tumor segmentation. Similar to recent methods for object detection, our implementation is based on neural networks; we propose modifications to the 3D UNet architecture and augmentation strategy to efficiently handle multimodal MRI input, besides this we introduce approach to enhance segmentation quality with context obtained from models of the same topology operating on downscaled data. We evaluate presented approach on BraTS 2018 dataset and achieve promising results on test dataset with 14th place and Dice score of 0.720/0.878/0.785 for enhancing tumor, whole tumor and tumor core segmentation respectively.