TY - GEN
T1 - Hybrid Feature Network Driven by Attention and Graph Features for Multiple Sclerosis Lesion Segmentation from MR Images
AU - Chen, Zhanlan
AU - Wang, Xiuying
AU - Zheng, Jiangbin
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/12/13
Y1 - 2020/12/13
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85100084552&partnerID=8YFLogxK
U2 - 10.1109/ICARCV50220.2020.9305404
DO - 10.1109/ICARCV50220.2020.9305404
M3 - 会议稿件
AN - SCOPUS:85100084552
T3 - 16th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV 2020
SP - 678
EP - 683
BT - 16th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 16th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV 2020
Y2 - 13 December 2020 through 15 December 2020
ER -