Glioma Segmentation with Cascaded Unet
This work addresses the challenge of precise glioma segmentation for medical diagnosis and treatment, but it appears incremental as it builds on existing UNet-based methods with modifications.
The paper tackles the problem of automatic brain tumor segmentation from 3D MRI data by proposing a deep cascaded approach based on modified 3D UNet architectures and augmentation strategies, and it evaluates the method on the BraTS 2018 dataset.
MRI analysis takes central position in brain tumor diagnosis and treatment, thus it's precise evaluation is crucially important. However, it's 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.\newline 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 discuss results.