University of Leicester
Browse
Final_Round__CANet__Context_Aware_Network_for_3D_Brain_Glioma_Segmentation.pdf (17.57 MB)

CANet: Context Aware Network for Brain Glioma Segmentation

Download (17.57 MB)
journal contribution
posted on 2021-03-09, 11:17 authored by Z Liu, L Tong, Z Zhou, Z Jiang, Q Zhang, Y Wang, C Shan, L Li, Huiyu Zhou
Automated segmentation of brain glioma plays an active role in diagnosis decision, progression monitoring and surgery planning. Based on deep neural networks, previous studies have shown promising technologies for brain glioma segmentation. However, these approaches lack powerful strategies to incorporate contextual information of tumor cells and their surrounding, which has been proven as a fundamental cue to deal with local ambiguity. In this work, we propose a novel approach named Context-Aware Network (CANet) for brain glioma segmentation. CANet captures high dimensional and discriminative features with contexts from both the convolutional space and feature interaction graphs. We further propose context guided attentive conditional random fields which can selectively aggregate features. We evaluate our method using publicly accessible brain glioma segmentation datasets BRATS2017,BRATS2018 and BRATS2019. The experimental results show that the proposed algorithm has better or competitive performance against several State-of-The-Art approaches under different segmentation metrics on the training and validation sets.

History

Citation

IEEE Transactions on Medical Imaging ( Volume: 40, Issue: 7, July 2021)

Author affiliation

School of Informatics

Version

  • AM (Accepted Manuscript)

Published in

IEEE Transactions on Medical Imaging

Volume

40

Issue

7

Pagination

1763-1777

Publisher

Institute of Electrical and Electronics Engineers

issn

0278-0062

Acceptance date

2021-03-06

Copyright date

2021

Available date

2021-03-09

Language

en

Usage metrics

    University of Leicester Publications

    Categories

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC