Hybrid Feature Network Driven by Attention and Graph Features for Multiple Sclerosis Lesion Segmentation from MR Images

Zhanlan Chen, Xiuying Wang, Jiangbin Zheng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Accurate segmentation of multiple sclerosis from MR images, faces the challenges imposed by the high variability in lesion appearance, and distant and disjoint lesion regions. Previous methods using multi-scale feature fusion or cascade networks, mostly rely on local feature representation learned from limited receptive field, which fail to leverage global context and model relations between multiple regions. To address these issues, we propose a hybrid feature network (HF-Net) driven by attention and graph convolution features, to improve the MS lesion segmentation from MR images. The attention features help to enhance discriminative feature representation. Specifically, the pyramid augmented attention module encodes spatial features into local features, while the channel augmented attention module models channel-wise interdependencies between features. Meanwhile, the graph feature module exploits the global relations between features over local receptive field. The proposed HF-Net was evaluated on the datasets from the MSSEG Challenge and the ongoing ISBI Challenge, which outperforms several state-of-the-art methods.

Original languageEnglish
Title of host publication16th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages678-683
Number of pages6
ISBN (Electronic)9781728177090
DOIs
StatePublished - 13 Dec 2020
Event16th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV 2020 - Virtual, Shenzhen, China
Duration: 13 Dec 202015 Dec 2020

Publication series

Name16th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV 2020

Conference

Conference16th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV 2020
Country/TerritoryChina
CityVirtual, Shenzhen
Period13/12/2015/12/20

Fingerprint

Dive into the research topics of 'Hybrid Feature Network Driven by Attention and Graph Features for Multiple Sclerosis Lesion Segmentation from MR Images'. Together they form a unique fingerprint.

Cite this