Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Beyond sudden cardiac death: the left atrium as a window into disease progression in hypertrophic cardiomyopathy.

European heart journal. Cardiovascular Imaging·2026
Same author

Cardiac Magnetic Resonance in Adults: An Updated Review of the Diagnostic Approach to Major Heart Diseases.

Journal of clinical medicine·2025
Same author

A fast method for extracting essential and synthetic lethality genes in GEM models.

Bioinformatics advances·2025
Same author

Survival risk prediction in hematopoietic stem cell transplantation for multiple myeloma.

Journal of integrative bioinformatics·2025
Same author

Cardiogenic shock in systemic sclerosis: a retrospective study of acute ventricular dysfunction.

Rheumatology international·2025
Same author

Left ventricular ejection fraction decline and cardiovascular events in suspected cardiomyopathy with excessive trabeculation: toward precision medicine.

Revista espanola de cardiologia (English ed.)·2025

相关实验视频

Updated: Jul 7, 2025

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography
06:34

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography

Published on: October 28, 2020

4.0K

改进深度学习模型以准确诊断LVNC

Jaime Rafael Barón1, Gregorio Bernabé1, Pilar González-Férez1

  • 1Computer Engineering Department, University of Murcia, 30100 Murcia, Spain.

Journal of clinical medicine
|December 23, 2023
PubMed
概括

使用心脏MRI图像上的先进AI细分技术,改善了左心室非紧缩性心肌病 (LVNC) 的准确诊断. 这些方法提高了检测准确度,有助于制定更好的患者治疗策略.

关键词:
核磁共振成像细分 图像细分心肌病心脏病变的发生.卷积神经网络是一种卷积神经网络.左心室非紧缩诊断 诊断 左心室非紧缩

更多相关视频

Biventricular Assessment of Cardiac Function and Pressure-Volume Loops by Closed-Chest Catheterization in Mice
08:21

Biventricular Assessment of Cardiac Function and Pressure-Volume Loops by Closed-Chest Catheterization in Mice

Published on: June 15, 2020

4.2K
Morphological and Functional Assessment of the Right Ventricle Using 3D Echocardiography
07:11

Morphological and Functional Assessment of the Right Ventricle Using 3D Echocardiography

Published on: October 28, 2020

2.9K

相关实验视频

Last Updated: Jul 7, 2025

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography
06:34

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography

Published on: October 28, 2020

4.0K
Biventricular Assessment of Cardiac Function and Pressure-Volume Loops by Closed-Chest Catheterization in Mice
08:21

Biventricular Assessment of Cardiac Function and Pressure-Volume Loops by Closed-Chest Catheterization in Mice

Published on: June 15, 2020

4.2K
Morphological and Functional Assessment of the Right Ventricle Using 3D Echocardiography
07:11

Morphological and Functional Assessment of the Right Ventricle Using 3D Echocardiography

Published on: October 28, 2020

2.9K

科学领域:

  • 心脏病学 心脏病学
  • 医疗成像医学成像
  • 人工智能的人工智能

背景情况:

  • 准确诊断左心室非紧缩性心肌病 (LVNC) 对于患者的管理至关重要,但仍然是一个诊断挑战.
  • 在心脏MRI图像中,左心室细分很困难,阻碍了精确的LVNC检测.
  • 现有的自动化方法往往与LVNC的复杂形图案作斗争.

研究的目的:

  • 为了提高左心室非紧缩性心肌病 (LVNC) 诊断的准确性.
  • 通过使用先进的深度学习技术,改善心脏MRI图像中的左心室细分.
  • 评估改进的细分对LVNC的诊断性能的影响.

主要方法:

  • 与标准 (512x512) 相比,使用了更高分辨率 (800x800) 的心脏MRI图像.
  • 实施了一个集群算法,以减轻神经网络细分错误 (幻觉).
  • 采用了先进的卷积神经网络架构:注意U-Net,MSA-UNet和U-Net++.

主要成果:

  • 具有800x800图像的U-Net++显示出优异的细分性能,比基线U-Net.net平均Dice得分提高了0.02.
  • 聚类算法在受影响的图像中增加了0.06的平均子得分.
  • 在LVNC检测方面,U-Net++实现了0.896的诊断准确度,0.907的精度和0.912的F1得分,超过了U-Net.

结论:

  • 提出的技术,包括更高分辨率的成像,集群和先进的U-Net架构,显著提高LVNC检测的准确性.
  • 在对左心室进行细分和诊断LVNC时,U-Net++表现出强的性能.
  • 医院间的数据变化突出了实现一致概括的挑战,表明了未来研究的领域.