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
虚心的不二完成签到 ,获得积分10
1秒前
xuzj应助科研通管家采纳,获得10
2秒前
小马甲应助科研通管家采纳,获得10
2秒前
2秒前
思源应助科研通管家采纳,获得10
2秒前
2秒前
研友_VZG7GZ应助科研通管家采纳,获得10
2秒前
fang应助科研通管家采纳,获得10
2秒前
隐形曼青应助科研通管家采纳,获得10
2秒前
科研通AI5应助科研通管家采纳,获得10
2秒前
FashionBoy应助科研通管家采纳,获得10
2秒前
shiizii应助科研通管家采纳,获得10
2秒前
4秒前
火星上的雨莲完成签到,获得积分10
8秒前
开朗的绮山发布了新的文献求助150
8秒前
平淡远山发布了新的文献求助10
9秒前
热心市民小红花应助Roman采纳,获得10
10秒前
艺术家完成签到 ,获得积分10
11秒前
研友_ngqjz8完成签到,获得积分10
12秒前
LT完成签到 ,获得积分0
13秒前
优秀的dd完成签到 ,获得积分10
14秒前
JamesPei应助八月宁静采纳,获得10
14秒前
www完成签到 ,获得积分10
16秒前
自由如天完成签到,获得积分10
16秒前
轻松白桃给轻松白桃的求助进行了留言
17秒前
热心市民小红花应助Roman采纳,获得10
18秒前
简单的元珊完成签到,获得积分10
19秒前
wanci应助饮汽水采纳,获得10
20秒前
量子星尘发布了新的文献求助10
20秒前
成就映秋完成签到,获得积分10
20秒前
cherrychou完成签到,获得积分10
22秒前
不要引力完成签到,获得积分10
23秒前
24秒前
邵初蓝完成签到,获得积分10
24秒前
沙耶发布了新的文献求助200
25秒前
JOKER完成签到 ,获得积分10
27秒前
泥過完成签到 ,获得积分10
28秒前
张姣姣完成签到,获得积分10
28秒前
OLDBLOW发布了新的文献求助10
28秒前
29秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
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 4038235
求助须知:如何正确求助?哪些是违规求助? 3575992
关于积分的说明 11374009
捐赠科研通 3305760
什么是DOI,文献DOI怎么找? 1819276
邀请新用户注册赠送积分活动 892662
科研通“疑难数据库(出版商)”最低求助积分说明 815022