Multi-step Cascaded Networks for Brain Tumor Segmentation

TL;DR

This paper introduces a multi-step cascaded neural network that leverages hierarchical tumor structure and auxiliary supervision to improve brain tumor segmentation accuracy, addressing class imbalance and overfitting issues.

Contribution

It proposes a novel multi-step cascaded network with deep supervision and data augmentation for more accurate brain tumor segmentation.

Findings

Mean dice coefficients: 0.886 for whole tumor

Mean dice coefficients: 0.813 for tumor core

Mean dice coefficients: 0.771 for enhancing tumor

Abstract

Automatic brain tumor segmentation method plays an extremely important role in the whole process of brain tumor diagnosis and treatment. In this paper, we propose a multi-step cascaded network which takes the hierarchical topology of the brain tumor substructures into consideration and segments the substructures from coarse to fine .During segmentation, the result of the former step is utilized as the prior information for the next step to guide the finer segmentation process. The whole network is trained in an end-to-end fashion. Besides, to alleviate the gradient vanishing issue and reduce overfitting, we added several auxiliary outputs as a kind of deep supervision for each step and introduced several data augmentation strategies, respectively, which proved to be quite efficient for brain tumor segmentation. Lastly, focal loss is utilized to solve the problem of remarkably imbalance of the tumor regions and background. Our model is tested on the BraTS 2019 validation dataset, the preliminary results of mean dice coefficients are 0.886, 0.813, 0.771 for the whole tumor, tumor core and enhancing tumor respectively. Code is available at https://github.com/JohnleeHIT/Brats2019