相关实验视频

Updated: May 16, 2026

Quantification of Mouse Heart Left Ventricular Function, Myocardial Strain, and Hemodynamic Forces by Cardiovascular Magnetic Resonance Imaging

Quantification of Mouse Heart Left Ventricular Function, Myocardial Strain, and Hemodynamic Forces by Cardiovascular Magnetic Resonance Imaging

Published on: May 24, 2021

弱半监督的心脏MRI细分与频域伪标签动态混合监督和部分子约束

Wenzong Li¹, Hui Liu¹, Jingcui Qin²

¹School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China.

Neural networks : the official journal of the International Neural Network Society

|November 27, 2025

概括

对于心脏MRI细分的新弱半监督框架PDFMSeg,减少了对广泛注释的依赖. 它使用频域伪标签动态混合监控 (FPLMS) 和部分子损失 (LpDice) 来提高更少标签数据的准确性.

科学领域:

医疗成像医学成像
人工智能的人工智能
心血管疾病心血管疾病

背景情况:

心脏MRI为诊断心血管疾病提供了精确的可视化.
深度学习细分方法需要大量的注释数据集,这些数据集是劳动密集型和耗时的.
弱半监督学习提供了一个解决方案,以减少注释依赖.

研究的目的:

介绍PDFMSeg,一种用于心脏MRI细分的新型弱半监督框架.
在深度学习模型中减少对细致注释数据集的需求.
提高自动心脏细分的准确性和效率.

主要方法:

开发了PDFMSeg,这是一个使用频域伪标签动态混合监控 (FPLMS) 和部分子损失 (LpDice) 的框架.
FPLMS从伪标签中动态混合频率组件,以增强边界约束.
LpDice 集成了 Dice 损失与忽略面具和日志-cosh 功能,以改善监督.

主要成果:

与最先进的弱半监督方法相比,PDFMSeg在10%的注释比率下,在ACDC和MSCMR数据集上实现了更高的性能.
获得的子分数 (DSC) 为83.57%和74.29%,雅卡尔系数 (JC) 为71.81%和59.09%,豪斯多夫距离95% (HD95) 为13.29和31.66.
该模型在计算上是高效的,只需要1.82M参数和2.32G FLOP.

结论:

PDFMSeg有效地减少了对心脏MRI细分的注释要求.
拟议的框架显示了心血管疾病诊断中的临床应用的巨大潜力.
该方法在性能和计算效率之间提供了一个有前途的平衡.

关键词:

心脏MRI细分心脏MRI细分一部分子损失.这是一个伪标签.软弱的半监督学习学习.

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

相关概念视频

Magnetic Resonance Imaging

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...

Imaging Studies for Cardiovascular System IV: CMRI

Imaging Studies for Cardiovascular System IV: CMRI

Cardiovascular magnetic resonance imaging, or CMRI, is a non-invasive diagnostic test that employs a magnetic field and radiofrequency waves to create precise images of the heart and arteries. It provides comprehensive information about cardiac anatomy, function, perfusion, and tissue characterization without ionizing radiation.IndicationsCMRI diagnoses various heart conditions, including tissue damage from heart attacks, ischemic heart disease, myocarditis, aortic issues (tears, aneurysms,...