3D vessel-like structure segmentation in medical images by an edge-reinforced network

The vessel-like structure in biomedical images, such as within cerebrovascular and nervous pathologies, is an essential biomarker in understanding diseases’ mechanisms and in diagnosing and treating diseases. However, existing vessel-like structure segmentation methods often produce unsatisfactory r...

Full description

Saved in:
Bibliographic Details
Published in:Medical image analysis Vol. 82; p. 102581
Main Authors: Xia, Likun, Zhang, Hao, Wu, Yufei, Song, Ran, Ma, Yuhui, Mou, Lei, Liu, Jiang, Xie, Yixuan, Ma, Ming, Zhao, Yitian
Format: Journal Article
Language:English
Published: Elsevier B.V 01.11.2022
Subjects:
3D segmentation
Attention
Deep network
Loss function
Vessel-like structure
Deep network
Loss function
Vessel-like structure
3D segmentation
Attention
ISSN:1361-8415, 1361-8423, 1361-8423
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The vessel-like structure in biomedical images, such as within cerebrovascular and nervous pathologies, is an essential biomarker in understanding diseases’ mechanisms and in diagnosing and treating diseases. However, existing vessel-like structure segmentation methods often produce unsatisfactory results due to challenging segmentations for crisp edges. The edge and nonedge voxels of the vessel-like structure in three-dimensional (3D) medical images usually have a highly imbalanced distribution as most voxels are non-edge, making it challenging to find crisp edges. In this work, we propose a generic neural network for the segmentation of the vessel-like structures in different 3D medical imaging modalities. The new edge-reinforced neural network (ER-Net) is based on an encoder–decoder architecture. Moreover, a reverse edge attention module and an edge-reinforced optimization loss are proposed to increase the weight of the voxels on the edge of the given 3D volume to discover and better preserve the spatial edge information. A feature selection module is further introduced to select discriminative features adaptively from an encoder and decoder simultaneously, which aims to increase the weight of edge voxels, thus significantly improving the segmentation performance. The proposed method is thoroughly validated using four publicly accessible datasets, and the experimental results demonstrate that the proposed method generally outperforms other state-of-the-art algorithms for various metrics. [Display omitted] •We propose a novel method for 3D vessel-like structure segmentation, which is validated quantitatively and qualitatively using two cerebrovascular and two nerve datasets.•We propose a novel edge-reinforced neural network to detect edges better, capture the microstructure and improve structure connectivity of the given 3D volumetric data.•We propose reverse edge attention and edge-reinforced optimization loss to constrain both the edge and non-edge voxels of vessel-like structures and improve segmentation performance.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1361-8415
1361-8423
1361-8423
DOI:10.1016/j.media.2022.102581