TY - GEN
T1 - A multi-view deep convolutional neural networks for lung nodule segmentation
AU - Wang, Shuo
AU - Zhou, Mu
AU - Gevaert, Olivier
AU - Tang, Zhenchao
AU - Dong, Di
AU - Liu, Zhenyu
AU - Tian, Jie
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/9/13
Y1 - 2017/9/13
N2 - We present a multi-view convolutional neural networks (MV-CNN) for lung nodule segmentation. The MV-CNN specialized in capturing a diverse set of nodule-sensitive features from axial, coronal and sagittal views in CT images simultaneously. The proposed network architecture consists of three CNN branches, where each branch includes seven stacked layers and takes multi-scale nodule patches as input. The three CNN branches are then integrated with a fully connected layer to predict whether the patch center voxel belongs to the nodule. The proposed method has been evaluated on 893 nodules from the public LIDC-IDRI dataset, where ground-truth annotations and CT imaging data were provided. We showed that MV-CNN demonstrated encouraging performance for segmenting various type of nodules including juxta-pleural, cavitary, and non-solid nodules, achieving an average dice similarity coefficient (DSC) of 77.67% and average surface distance (ASD) of 0.24, outperforming conventional image segmentation approaches.
AB - We present a multi-view convolutional neural networks (MV-CNN) for lung nodule segmentation. The MV-CNN specialized in capturing a diverse set of nodule-sensitive features from axial, coronal and sagittal views in CT images simultaneously. The proposed network architecture consists of three CNN branches, where each branch includes seven stacked layers and takes multi-scale nodule patches as input. The three CNN branches are then integrated with a fully connected layer to predict whether the patch center voxel belongs to the nodule. The proposed method has been evaluated on 893 nodules from the public LIDC-IDRI dataset, where ground-truth annotations and CT imaging data were provided. We showed that MV-CNN demonstrated encouraging performance for segmenting various type of nodules including juxta-pleural, cavitary, and non-solid nodules, achieving an average dice similarity coefficient (DSC) of 77.67% and average surface distance (ASD) of 0.24, outperforming conventional image segmentation approaches.
UR - https://www.scopus.com/pages/publications/85032215167
U2 - 10.1109/EMBC.2017.8037182
DO - 10.1109/EMBC.2017.8037182
M3 - 会议稿件
C2 - 29060226
AN - SCOPUS:85032215167
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 1752
EP - 1755
BT - 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017
Y2 - 11 July 2017 through 15 July 2017
ER -