Automated vessel segmentation in lung CT and CTA images via deep neural networks

分割 卷积神经网络 Sørensen–骰子系数 计算机科学 人工智能 深度学习 人工神经网络 基本事实 模式识别(心理学) 计算机断层血管造影 图像分割 计算机断层摄影术 放射科 医学
作者
Wenjun Tan,Luqian Zhou,Xiaoshuo Li,Xiaoyu Yang,Yufei Chen,Jinzhu Yang
出处
期刊:Journal of X-ray Science and Technology [IOS Press]
卷期号:29 (6): 1123-1137 被引量:16
标识
DOI:10.3233/xst-210955
摘要

The distribution of pulmonary vessels in computed tomography (CT) and computed tomography angiography (CTA) images of lung is important for diagnosing disease, formulating surgical plans and pulmonary research.Based on the pulmonary vascular segmentation task of International Symposium on Image Computing and Digital Medicine 2020 challenge, this paper reviews 12 different pulmonary vascular segmentation algorithms of lung CT and CTA images and then objectively evaluates and compares their performances.First, we present the annotated reference dataset of lung CT and CTA images. A subset of the dataset consisting 7,307 slices for training and 3,888 slices for testing was made available for participants. Second, by analyzing the performance comparison of different convolutional neural networks from 12 different institutions for pulmonary vascular segmentation, the reasons for some defects and improvements are summarized. The models are mainly based on U-Net, Attention, GAN, and multi-scale fusion network. The performance is measured in terms of Dice coefficient, over segmentation rate and under segmentation rate. Finally, we discuss several proposed methods to improve the pulmonary vessel segmentation results using deep neural networks.By comparing with the annotated ground truth from both lung CT and CTA images, most of 12 deep neural network algorithms do an admirable job in pulmonary vascular extraction and segmentation with the dice coefficients ranging from 0.70 to 0.85. The dice coefficients for the top three algorithms are about 0.80.Study results show that integrating methods that consider spatial information, fuse multi-scale feature map, or have an excellent post-processing to deep neural network training and optimization process are significant for further improving the accuracy of pulmonary vascular segmentation.
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
星辰大海应助do0采纳,获得10
1秒前
tt完成签到 ,获得积分10
2秒前
浅辰完成签到,获得积分10
3秒前
大气萤完成签到,获得积分20
4秒前
4秒前
我ppp完成签到 ,获得积分10
4秒前
5秒前
易燃物品完成签到,获得积分10
5秒前
Hello应助Ther采纳,获得10
7秒前
CherylZhao完成签到,获得积分10
8秒前
Galato发布了新的文献求助10
9秒前
颜愫完成签到,获得积分10
9秒前
安详向日葵完成签到 ,获得积分10
10秒前
拼搏的白云完成签到,获得积分10
10秒前
852应助hhh采纳,获得10
10秒前
李白白白完成签到,获得积分10
10秒前
王手完成签到,获得积分10
10秒前
11秒前
一人完成签到,获得积分10
12秒前
do0完成签到,获得积分10
13秒前
yar应助xlz110采纳,获得10
13秒前
NexusExplorer应助落寞凌波采纳,获得10
15秒前
量子星尘发布了新的文献求助10
18秒前
123完成签到 ,获得积分10
18秒前
哈哈呵完成签到,获得积分10
18秒前
18秒前
Rylee完成签到,获得积分10
18秒前
Jiro完成签到,获得积分10
20秒前
我ppp发布了新的文献求助60
21秒前
22秒前
纳米酶催化完成签到,获得积分10
23秒前
23秒前
John完成签到,获得积分10
23秒前
李小强完成签到,获得积分10
24秒前
25秒前
28秒前
落寞凌波发布了新的文献求助10
28秒前
28秒前
29秒前
健壮的尔烟完成签到,获得积分10
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 4038368
求助须知:如何正确求助?哪些是违规求助? 3576068
关于积分的说明 11374313
捐赠科研通 3305780
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029