CANet: Context Aware Network for 3D Brain Tumor Segmentation

by   Zhihua Liu, et al.

Automated segmentation of brain tumors in 3D magnetic resonance imaging plays an active role in tumor diagnosis, progression monitoring and surgery planning. Based on convolutional neural networks, especially fully convolutional networks, previous studies have shown some promising technologies for brain tumor segmentation. However, these approaches lack suitable strategies to incorporate contextual information to deal with local ambiguities, leading to unsatisfactory segmentation outcomes in challenging circumstances. In this work, we propose a novel Context-Aware Network (CANet) with a Hybrid Context Aware Feature Extractor (HCA-FE) and a Context Guided Attentive Conditional Random Field (CG-ACRF) for feature fusion. HCA-FE captures high dimensional and discriminative features with the contexts from both the convolutional space and feature interaction graphs. We adopt the powerful inference ability of probabilistic graphical models to learn hidden feature maps, and then use CG-ACRF to fuse the features of different contexts. We evaluate our proposed method on publicly accessible brain tumor segmentation datasets BRATS2017 and BRATS2018 against several state-of-the-art approaches using different segmentation metrics. The experimental results show that the proposed algorithm has better or competitive performance, compared to the standard approaches.


page 1

page 2

page 9

page 14

page 15

page 16

page 20


Dilated Inception U-Net (DIU-Net) for Brain Tumor Segmentation

Magnetic resonance imaging (MRI) is routinely used for brain tumor diagn...

Hierarchical Graphical Models for Context-Aware Hybrid Brain-Machine Interfaces

We present a novel hierarchical graphical model based context-aware hybr...

Adaptive feature recombination and recalibration for semantic segmentation: application to brain tumor segmentation in MRI

Convolutional neural networks (CNNs) have been successfully used for bra...

Context-Aware Refinement Network Incorporating Structural Connectivity Prior for Brain Midline Delineation

Brain midline delineation can facilitate the clinical evaluation of brai...

MRI Brain Tumor Segmentation using Random Forests and Fully Convolutional Networks

In this paper, we propose a novel learning based method for automated se...

Context-aware PolyUNet for Liver and Lesion Segmentation from Abdominal CT Images

Accurate liver and lesion segmentation from computed tomography (CT) ima...

H-DenseUNet: Hybrid Densely Connected UNet for Liver and Liver Tumor Segmentation from CT Volumes

Liver cancer is one of the leading causes of cancer death. To assist doc...

Please sign up or login with your details

Forgot password? Click here to reset