Tubular Structure Segmentation Using Spatial Fully Connected Network with Radial Distance Loss for 3D Medical Images

分割 计算机科学 体素 距离变换 人工智能 中轴 图像分割 计算机视觉 模式识别(心理学) 图像(数学)
作者
Chenglong Wang,Yuichiro Hayashi,Masahiro Oda,Hayato Itoh,Takayuki Kitasaka,Alejandro F. Frangi,Kensaku Mori
出处
期刊:Lecture Notes in Computer Science 卷期号:: 348-356 被引量:25
标识
DOI:10.1007/978-3-030-32226-7_39
摘要

This paper presents a new spatial fully connected tubular network for 3D tubular-structure segmentation. Automatic and complete segmentation of intricate tubular structures remains an unsolved challenge in the medical image analysis. Airways and vasculature pose high demands on medical image analysis as they are elongated fine structures with calibers ranging from several tens of voxels to voxel-level resolution, branching in deeply multi-scale fashion, and with complex topological and spatial relationships. Most machine/deep learning approaches are based on intensity features and ignore spatial consistency across the network that are otherwise distinct in tubular structures. In this work, we introduce 3D slice-by-slice convolutional layers in a U-Net architecture to capture the spatial information of elongated structures. Furthermore, we present a novel loss function, coined radial distance loss, specifically designed for tubular structures. The commonly used methods of cross-entropy loss and generalized Dice loss are sensitive to volumetric variation. However, in tiny tubular structure segmentation, topological errors are as important as volumetric errors. The proposed radial distance loss places higher weight to the centerline, and this weight decreases along the radial direction. Radial distance loss can help networks focus more attention on tiny structures than on thicker tubular structures. We perform experiments on bronchus segmentation on 3D CT images. The experimental results show that compared to the baseline U-Net, our proposed network achieved improvement about 24% and 30% in Dice index and centerline over ratio.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
IMkily完成签到,获得积分10
1秒前
他克莫司完成签到,获得积分10
1秒前
Ayers发布了新的文献求助10
1秒前
1秒前
打工肥仔应助失眠夏山采纳,获得20
2秒前
英姑应助TIGun采纳,获得10
2秒前
SilvanYang完成签到,获得积分10
2秒前
哈哈完成签到,获得积分10
2秒前
霸气以菱发布了新的文献求助10
3秒前
奶茶完成签到,获得积分10
3秒前
海棠花未眠完成签到,获得积分10
3秒前
困了就睡发布了新的文献求助10
3秒前
3秒前
4秒前
4秒前
wpz完成签到,获得积分10
5秒前
无名发布了新的文献求助10
5秒前
㎏w发布了新的文献求助10
5秒前
5秒前
深情安青应助sigla采纳,获得10
6秒前
7秒前
swnucquwd完成签到 ,获得积分10
8秒前
ye发布了新的文献求助10
9秒前
nannan发布了新的文献求助10
10秒前
你看看完成签到,获得积分10
10秒前
12秒前
科研通AI2S应助qq采纳,获得10
12秒前
12秒前
哈h驳回了DijiaXu应助
12秒前
Emma完成签到,获得积分10
13秒前
IvanMcRae发布了新的文献求助10
13秒前
14秒前
zebra8848完成签到,获得积分10
14秒前
Ava应助Gnahz采纳,获得10
14秒前
SG完成签到,获得积分10
14秒前
妙松发布了新的文献求助10
15秒前
刘娇娇发布了新的文献求助10
16秒前
zz完成签到,获得积分10
16秒前
17秒前
gcc发布了新的文献求助10
18秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Toward a Combinatorial Approach for the Prediction of IgG Half-Life and Clearance 500
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3970120
求助须知:如何正确求助?哪些是违规求助? 3514810
关于积分的说明 11176124
捐赠科研通 3250136
什么是DOI,文献DOI怎么找? 1795198
邀请新用户注册赠送积分活动 875647
科研通“疑难数据库(出版商)”最低求助积分说明 804964