Multi-Atlas Brain Parcellation Using Squeeze-and-Excitation Fully Convolutional Networks

Zhenyu Tang, Xianli Liu, Yang Li, Pew Thian Yap, Dinggang Shen

Research output: Contribution to journalArticle

Abstract

Multi-atlas parcellation (MAP) is carried out on a brain image by propagating and fusing labelled regions from brain atlases. Typical nonlinear registration-based label propagation is time-consuming and sensitive to inter-subject differences. Recently, deep learning parcellation (DLP) has been proposed to avoid nonlinear registration for better efficiency and robustness than MAP. However, most existing DLP methods neglect using brain atlases, which contain high-level information (e.g., manually labelled brain regions), to provide auxiliary features for improving the parcellation accuracy. In this paper, we propose a novel multi-atlas DLP method for brain parcellation. Our method is based on fully convolutional networks (FCN) and squeeze-and-excitation (SE) modules. It can automatically and adaptively select features from the most relevant brain atlases to guide parcellation. Moreover, our method is trained via a generative adversarial network (GAN), where a convolutional neural network (CNN) with multi-scale $l_{1}$ loss is used as the discriminator. Benefiting from brain atlases, our method outperforms MAP and state-of-the-art DLP methods on two public image datasets (LPBA40 and NIREP-NA0).

Original languageEnglish
Article number9096532
Pages (from-to)6864-6872
Number of pages9
JournalIEEE Transactions on Image Processing
Volume29
DOIs
Publication statusPublished - 2020

Keywords

  • brain atlas selection
  • Brain parcellation
  • fully convolutional networks
  • squeeze-and-excitation module

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'Multi-Atlas Brain Parcellation Using Squeeze-and-Excitation Fully Convolutional Networks'. Together they form a unique fingerprint.

Cite this