• 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

使用稳健非负矩阵分解的二尖瓣分割

Mitral Valve Segmentation Using Robust Nonnegative Matrix Factorization.

作者信息

Dröge Hannah, Yuan Baichuan, Llerena Rafael, Yen Jesse T, Moeller Michael, Bertozzi Andrea L

机构信息

Department of Electrical Engineering and Computer Science, University of Siegen, 57076 Siegen, Germany.

Department of Mathematics, University of California, Los Angeles, CA 90095, USA.

出版信息

J Imaging. 2021 Oct 16;7(10):213. doi: 10.3390/jimaging7100213.

DOI:10.3390/jimaging7100213
PMID:34677299
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8541511/
Abstract

Analyzing and understanding the movement of the mitral valve is of vital importance in cardiology, as the treatment and prevention of several serious heart diseases depend on it. Unfortunately, large amounts of noise as well as a highly varying image quality make the automatic tracking and segmentation of the mitral valve in two-dimensional echocardiographic videos challenging. In this paper, we present a fully automatic and unsupervised method for segmentation of the mitral valve in two-dimensional echocardiographic videos, independently of the echocardiographic view. We propose a bias-free variant of the robust non-negative matrix factorization (RNMF) along with a window-based localization approach, that is able to identify the mitral valve in several challenging situations. We improve the average f1-score on our dataset of 10 echocardiographic videos by 0.18 to a f1-score of 0.56.

摘要

分析和理解二尖瓣的运动在心脏病学中至关重要，因为几种严重心脏病的治疗和预防都依赖于此。不幸的是，大量噪声以及高度变化的图像质量使得在二维超声心动图视频中对二尖瓣进行自动跟踪和分割具有挑战性。在本文中，我们提出了一种全自动且无监督的方法，用于在二维超声心动图视频中分割二尖瓣，且与超声心动图视图无关。我们提出了一种稳健非负矩阵分解（RNMF）的无偏差变体以及基于窗口的定位方法，该方法能够在多种具有挑战性的情况下识别二尖瓣。我们将我们10个超声心动图视频数据集上的平均F1分数提高了0.18，达到了0.56的F1分数。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/8ddcb0d808dd/jimaging-07-00213-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/324d08f8faa6/jimaging-07-00213-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/c0909f7e7f7c/jimaging-07-00213-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/4a595ff067cb/jimaging-07-00213-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/01bae62fe078/jimaging-07-00213-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/b674f87343f5/jimaging-07-00213-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/f26adf88b6aa/jimaging-07-00213-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/e364064117ac/jimaging-07-00213-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/951578556e42/jimaging-07-00213-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/ab326257ccca/jimaging-07-00213-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/b4fd037617a0/jimaging-07-00213-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/405afe44d373/jimaging-07-00213-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/59d226d154ab/jimaging-07-00213-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/3d05c3e371c0/jimaging-07-00213-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/f6d68a4f3c62/jimaging-07-00213-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/2b1c0e70f404/jimaging-07-00213-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/76372fbd9e0b/jimaging-07-00213-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/8ddcb0d808dd/jimaging-07-00213-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/324d08f8faa6/jimaging-07-00213-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/c0909f7e7f7c/jimaging-07-00213-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/4a595ff067cb/jimaging-07-00213-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/01bae62fe078/jimaging-07-00213-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/b674f87343f5/jimaging-07-00213-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/f26adf88b6aa/jimaging-07-00213-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/e364064117ac/jimaging-07-00213-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/951578556e42/jimaging-07-00213-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/ab326257ccca/jimaging-07-00213-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/b4fd037617a0/jimaging-07-00213-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/405afe44d373/jimaging-07-00213-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/59d226d154ab/jimaging-07-00213-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/3d05c3e371c0/jimaging-07-00213-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/f6d68a4f3c62/jimaging-07-00213-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/2b1c0e70f404/jimaging-07-00213-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/76372fbd9e0b/jimaging-07-00213-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b59e/8541511/8ddcb0d808dd/jimaging-07-00213-g018.jpg

相似文献

1
Mitral Valve Segmentation Using Robust Nonnegative Matrix Factorization.使用稳健非负矩阵分解的二尖瓣分割
J Imaging. 2021 Oct 16;7(10):213. doi: 10.3390/jimaging7100213.
2
Neural collaborative filtering for unsupervised mitral valve segmentation in echocardiography.基于神经网络的协作滤波在心超中二尖瓣的无监督分割。
Artif Intell Med. 2020 Nov;110:101975. doi: 10.1016/j.artmed.2020.101975. Epub 2020 Oct 21.
3
Unsupervised Mitral Valve Tracking for Disease Detection in Echocardiogram Videos.用于超声心动图视频疾病检测的无监督二尖瓣跟踪
J Imaging. 2020 Sep 9;6(9):93. doi: 10.3390/jimaging6090093.
4
A deep learning approach for the automatic recognition of prosthetic mitral valve in echocardiographic images.一种用于在超声心动图像中自动识别人工二尖瓣的深度学习方法。
Comput Biol Med. 2021 Jun;133:104388. doi: 10.1016/j.compbiomed.2021.104388. Epub 2021 Apr 14.
5
Using Anatomic Intelligence to Localize Mitral Valve Prolapse on Three-Dimensional Echocardiography.利用解剖学智能在三维超声心动图上定位二尖瓣脱垂
J Am Soc Echocardiogr. 2016 Oct;29(10):938-945. doi: 10.1016/j.echo.2016.07.002. Epub 2016 Aug 18.
6
Automatic segmentation of odor maps in the mouse olfactory bulb using regularized non-negative matrix factorization.使用正则化非负矩阵分解自动分割小鼠嗅球中的气味图谱。
Neuroimage. 2014 Sep;98:279-88. doi: 10.1016/j.neuroimage.2014.04.041. Epub 2014 Apr 24.
7
Automated tracking of the mitral valve annulus motion in apical echocardiographic images using multidimensional dynamic programming.使用多维动态规划自动跟踪心尖超声心动图图像中的二尖瓣环运动。
Ultrasound Med Biol. 2007 Sep;33(9):1389-99. doi: 10.1016/j.ultrasmedbio.2007.03.007. Epub 2007 May 21.
8
Time continuous detection of the left ventricular long axis and the mitral valve plane in 3-D echocardiography.三维超声心动图中左心室长轴和二尖瓣平面的时间连续检测。
Ultrasound Med Biol. 2008 Feb;34(2):196-207. doi: 10.1016/j.ultrasmedbio.2007.07.016. Epub 2007 Oct 23.
9
Virtual M-Mode for Echocardiography: A New Approach for the Segmentation of the Anterior Mitral Leaflet.虚拟 M 型超声心动图：一种二尖瓣前叶分段的新方法。
IEEE J Biomed Health Inform. 2019 Jan;23(1):305-313. doi: 10.1109/JBHI.2018.2799738. Epub 2018 Jan 30.
10
Tracking large Anterior Mitral Leaflet displacements by incorporating optical flow in an active contours framework.
Annu Int Conf IEEE Eng Med Biol Soc. 2017 Jul;2017:3244-3247. doi: 10.1109/EMBC.2017.8037548.

本文引用的文献

1
Neural collaborative filtering for unsupervised mitral valve segmentation in echocardiography.基于神经网络的协作滤波在心超中二尖瓣的无监督分割。
Artif Intell Med. 2020 Nov;110:101975. doi: 10.1016/j.artmed.2020.101975. Epub 2020 Oct 21.
2
Tracking large Anterior Mitral Leaflet displacements by incorporating optical flow in an active contours framework.
Annu Int Conf IEEE Eng Med Biol Soc. 2017 Jul;2017:3244-3247. doi: 10.1109/EMBC.2017.8037548.
3
Fast and Fully Automatic Left Ventricular Segmentation and Tracking in Echocardiography Using Shape-Based B-Spline Explicit Active Surfaces.基于形状的 B 样条显式主动表面的超声心动图快速全自动左心室分割和跟踪。
IEEE Trans Med Imaging. 2017 Nov;36(11):2287-2296. doi: 10.1109/TMI.2017.2734959. Epub 2017 Aug 2.
4
Tracking of the anterior mitral leaflet in echocardiographic sequences using active contours.使用主动轮廓法在超声心动图序列中追踪二尖瓣前叶。
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:1074-1077. doi: 10.1109/EMBC.2016.7590889.
5
Standardized Evaluation System for Left Ventricular Segmentation Algorithms in 3D Echocardiography.三维超声心动图左心室分段算法的标准化评估系统。
IEEE Trans Med Imaging. 2016 Apr;35(4):967-77. doi: 10.1109/TMI.2015.2503890. Epub 2015 Nov 25.
6
NMFBFS: A NMF-Based Feature Selection Method in Identifying Pivotal Clinical Symptoms of Hepatocellular Carcinoma.NMFBFS：一种基于非负矩阵分解的肝细胞癌关键临床症状识别特征选择方法。
Comput Math Methods Med. 2015;2015:846942. doi: 10.1155/2015/846942. Epub 2015 Oct 12.
7
The basics of echocardiography.超声心动图基础。
J Saudi Heart Assoc. 2010 Apr;22(2):71-6. doi: 10.1016/j.jsha.2010.02.011. Epub 2010 Mar 1.
8
The segmentation of the left ventricle of the heart from ultrasound data using deep learning architectures and derivative-based search methods.使用深度学习架构和基于导数的搜索方法对超声数据进行左心室分割。
IEEE Trans Image Process. 2012 Mar;21(3):968-82. doi: 10.1109/TIP.2011.2169273. Epub 2011 Sep 23.
9
Ultrasound basics.超声基础。
Handb Exp Pharmacol. 2008(185 Pt 1):91-107. doi: 10.1007/978-3-540-72718-7_5.
10
Active contours without edges.无边缘活动轮廓。
IEEE Trans Image Process. 2001;10(2):266-77. doi: 10.1109/83.902291.