Sequential 3D U-Nets for Biologically-Informed Brain Tumor Segmentation
This addresses the problem of accurate glioma segmentation for medical imaging applications, but it is incremental as it builds on existing U-Net architectures with a structured approach.
The paper tackled brain tumor segmentation by incorporating biological context into deep learning, using sequential 3D U-Nets to segment glioma tissues, achieving Dice scores of 0.882 for whole tumor, 0.732 for enhancing tumor, and 0.730 for tumor core.
Deep learning has quickly become the weapon of choice for brain lesion segmentation. However, few existing algorithms pre-configure any biological context of their chosen segmentation tissues, and instead rely on the neural network's optimizer to develop such associations de novo. We present a novel method for applying deep neural networks to the problem of glioma tissue segmentation that takes into account the structured nature of gliomas - edematous tissue surrounding mutually-exclusive regions of enhancing and non-enhancing tumor. We trained multiple deep neural networks with a 3D U-Net architecture in a tree structure to create segmentations for edema, non-enhancing tumor, and enhancing tumor regions. Specifically, training was configured such that the whole tumor region including edema was predicted first, and its output segmentation was fed as input into separate models to predict enhancing and non-enhancing tumor. Our method was trained and evaluated on the publicly available BraTS dataset, achieving Dice scores of 0.882, 0.732, and 0.730 for whole tumor, enhancing tumor and tumor core respectively.