Sequential 3D U-Nets for Biologically-Informed Brain Tumor Segmentation

by   Andrew Beers, et al.

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.


page 5

page 6


Multimodal CNN Networks for Brain Tumor Segmentation in MRI: A BraTS 2022 Challenge Solution

Automatic segmentation is essential for the brain tumor diagnosis, disea...

Robustness of Brain Tumor Segmentation

We address the generalization behavior of deep neural networks in the co...

DR-Unet104 for Multimodal MRI brain tumor segmentation

In this paper we propose a 2D deep residual Unet with 104 convolutional ...

A Computation-Efficient CNN System for High-Quality Brain Tumor Segmentation

In this paper, a Convolutional Neural Network (CNN) system is proposed f...

Please sign up or login with your details

Forgot password? Click here to reset