• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

基于动态超声的心脏分割算法。

A Heart Segmentation Algorithm Based on Dynamic Ultrasound.

机构信息

Department of Ultrasound, Xijing Hospital, Fourth Military Medical University, Xi'an 710032, China.

出版信息

Biomed Res Int. 2022 Jun 17;2022:1485584. doi: 10.1155/2022/1485584. eCollection 2022.

DOI:10.1155/2022/1485584
PMID:35757484
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9232347/
Abstract

The heart is one of the most important organs of the human body. The role of the heart is to promote blood flow and provide sufficient blood flow to organs and tissues. The research on the heart has important theoretical and clinical significance. Because of the noninvasive and intuitive display of ultrasound image, it can dynamically obtain the heart state and has become the main means to detect the heart dynamics. We analyze the characteristics of cardiac ultrasound image from the medical point of view and signal processing. The heart movement is periodic and rhythmic. The image signal can be decomposed. Firstly, the image is decomposed into high- and low-frequency signals to highlight different dimensional information. Then, the attention model was introduced, focusing on the heart region. Finally, the multidimensional network carrying model was established to achieve cardiac segmentation. The experimental results show that the AOM of the algorithm proposed in this paper reaches 92%, which has a certain degree of advancement and can assist doctors to make accurate diagnosis.

摘要

心脏是人体最重要的器官之一。心脏的作用是促进血液流动,并为器官和组织提供足够的血液流量。心脏的研究具有重要的理论和临床意义。由于超声图像具有非侵入性和直观的显示,可以动态获取心脏状态,因此已成为检测心脏动态的主要手段。我们从医学和信号处理的角度分析了心脏超声图像的特征。心脏运动是周期性和有节奏的。图像信号可以分解。首先,将图像分解为高、低频信号,以突出不同的维度信息。然后,引入注意模型,关注心脏区域。最后,建立多维网络携带模型,实现心脏分割。实验结果表明,本文提出的算法的 AOM 达到 92%,具有一定的先进性,可以辅助医生做出准确的诊断。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/5494e1a5338d/BMRI2022-1485584.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/884c9364a66a/BMRI2022-1485584.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/2f5ad881430e/BMRI2022-1485584.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/7ec0b00d30d4/BMRI2022-1485584.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/3aa00e94083b/BMRI2022-1485584.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/53be002fe9a5/BMRI2022-1485584.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/1b04ccd7573d/BMRI2022-1485584.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/73220fa40c8e/BMRI2022-1485584.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/5494e1a5338d/BMRI2022-1485584.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/884c9364a66a/BMRI2022-1485584.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/2f5ad881430e/BMRI2022-1485584.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/7ec0b00d30d4/BMRI2022-1485584.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/3aa00e94083b/BMRI2022-1485584.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/53be002fe9a5/BMRI2022-1485584.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/1b04ccd7573d/BMRI2022-1485584.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/73220fa40c8e/BMRI2022-1485584.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fef9/9232347/5494e1a5338d/BMRI2022-1485584.008.jpg

相似文献

1
A Heart Segmentation Algorithm Based on Dynamic Ultrasound.基于动态超声的心脏分割算法。
Biomed Res Int. 2022 Jun 17;2022:1485584. doi: 10.1155/2022/1485584. eCollection 2022.
2
Deep learning-based automatic segmentation of images in cardiac radiography: A promising challenge.基于深度学习的心脏放射成像图像自动分割:一项颇具前景的挑战。
Comput Methods Programs Biomed. 2022 Jun;220:106821. doi: 10.1016/j.cmpb.2022.106821. Epub 2022 Apr 19.
3
Efficient workflow for automatic segmentation of the right heart based on 2D echocardiography.基于二维超声心动图的右心自动分割高效工作流程。
Int J Cardiovasc Imaging. 2018 Jul;34(7):1041-1055. doi: 10.1007/s10554-018-1314-4. Epub 2018 Feb 10.
4
Cardiac magnetic resonance image segmentation based on convolutional neural network.基于卷积神经网络的心脏磁共振图像分割。
Comput Methods Programs Biomed. 2020 Dec;197:105755. doi: 10.1016/j.cmpb.2020.105755. Epub 2020 Sep 11.
5
Feature Extraction of Kidney Tissue Image Based on Ultrasound Image Segmentation.基于超声图像分割的肾脏组织图像特征提取。
J Healthc Eng. 2021 Apr 26;2021:9915697. doi: 10.1155/2021/9915697. eCollection 2021.
6
A category attention instance segmentation network for four cardiac chambers segmentation in fetal echocardiography.用于胎儿超声心动图中四心腔分割的类别注意实例分割网络。
Comput Med Imaging Graph. 2021 Oct;93:101983. doi: 10.1016/j.compmedimag.2021.101983. Epub 2021 Sep 16.
7
[Self-organization neural network based ultrasonic heart image segmentation].基于自组织神经网络的超声心动图图像分割
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 1998 Dec;15(4):397-9, 405.
8
Fast and accurate segmentation method of active shape model with Rayleigh mixture model clustering for prostate ultrasound images.基于瑞利混合模型聚类的主动形状模型的快速准确前列腺超声图像分割方法。
Comput Methods Programs Biomed. 2020 Feb;184:105097. doi: 10.1016/j.cmpb.2019.105097. Epub 2019 Sep 26.
9
Anatomical structure segmentation from early fetal ultrasound sequences using global pollination CAT swarm optimizer-based Chan-Vese model.利用基于全局授粉 CAT 蜂群优化器的 Chan-Vese 模型对早期胎儿超声序列进行解剖结构分割。
Med Biol Eng Comput. 2019 Aug;57(8):1763-1782. doi: 10.1007/s11517-019-01991-2. Epub 2019 Jun 12.
10
Robust Optical Flow Estimation in Cardiac Ultrasound Images Using a Sparse Representation.基于稀疏表示的心脏超声图像稳健光流估计。
IEEE Trans Med Imaging. 2019 Mar;38(3):741-752. doi: 10.1109/TMI.2018.2870947. Epub 2018 Sep 18.

本文引用的文献

1
Deep learning-based automatic segmentation of images in cardiac radiography: A promising challenge.基于深度学习的心脏放射成像图像自动分割:一项颇具前景的挑战。
Comput Methods Programs Biomed. 2022 Jun;220:106821. doi: 10.1016/j.cmpb.2022.106821. Epub 2022 Apr 19.
2
Sex Differences and Similarities in Valvular Heart Disease.瓣膜性心脏病的性别差异和相似性。
Circ Res. 2022 Feb 18;130(4):455-473. doi: 10.1161/CIRCRESAHA.121.319914. Epub 2022 Feb 17.
3
Detection of myocardial fibrosis by speckle-tracking echocardiography: from prediction to clinical applications.
斑点追踪超声心动图检测心肌纤维化:从预测到临床应用。
Heart Fail Rev. 2022 Sep;27(5):1857-1867. doi: 10.1007/s10741-022-10214-0. Epub 2022 Jan 19.
4
A completely automated pipeline for 3D reconstruction of human heart from 2D cine magnetic resonance slices.一个完全自动化的从 2D 电影磁共振片重建人体心脏 3D 结构的流水线。
Philos Trans A Math Phys Eng Sci. 2021 Dec 13;379(2212):20200257. doi: 10.1098/rsta.2020.0257. Epub 2021 Oct 25.
5
Clinical Applications of 4D Flow MR Imaging in Aortic Valvular and Congenital Heart Disease.4D 流磁共振成像在主动脉瓣和先天性心脏病中的临床应用。
Magn Reson Med Sci. 2022 Mar 1;21(2):319-326. doi: 10.2463/mrms.rev.2021-0030. Epub 2021 Jun 25.
6
3-D Gabor-based anisotropic diffusion for speckle noise suppression in dynamic ultrasound images.基于 3-D Gabor 滤波器的各向异性扩散法用于动态超声图像的散斑噪声抑制。
Phys Eng Sci Med. 2021 Mar;44(1):207-219. doi: 10.1007/s13246-020-00969-x. Epub 2021 Jan 26.
7
Identification of COVID-19 samples from chest X-Ray images using deep learning: A comparison of transfer learning approaches.基于深度学习的胸部 X 光图像中 COVID-19 样本的识别:迁移学习方法的比较。
J Xray Sci Technol. 2020;28(5):821-839. doi: 10.3233/XST-200715.
8
Fast fully automatic heart fat segmentation in computed tomography datasets.快速全自动心脏脂肪分割在计算机断层扫描数据集。
Comput Med Imaging Graph. 2020 Mar;80:101674. doi: 10.1016/j.compmedimag.2019.101674. Epub 2019 Dec 6.
9
Computer aided decision making for heart disease detection using hybrid neural network-Genetic algorithm.使用混合神经网络-遗传算法进行心脏病检测的计算机辅助决策。
Comput Methods Programs Biomed. 2017 Apr;141:19-26. doi: 10.1016/j.cmpb.2017.01.004. Epub 2017 Jan 18.
10
Interactive Whole-Heart Segmentation in Congenital Heart Disease.先天性心脏病的交互式全心分割
Med Image Comput Comput Assist Interv. 2015 Oct;9351:80-88. doi: 10.1007/978-3-319-24574-4_10. Epub 2015 Nov 18.