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

Tuberculous tenosynovitis and bursitis: imaging findings in 21 cases.

Radiology·1996
Same author

Recombinant mitotoxin basic fibroblast growth factor-saporin reduces venous anastomotic intimal hyperplasia in the arteriovenous graft.

Circulation·1996
Same author

Measurement of urinary estrogen metabolites using a monoclonal enzyme-linked immunoassay kit: assay performance and feasibility for epidemiological studies.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·1996
Same author

Differences in cholinergic responses from outer hair cells of rat and guinea pig.

Hearing research·1996
Same author

Pharmacokinetics of retinoids in women after meal consumption or vitamin A supplementation.

Journal of clinical pharmacology·1996
Same author

Determination of the amino acid residue involved in [3H]beta-funaltrexamine covalent binding in the cloned rat mu-opioid receptor.

The Journal of biological chemistry·1996

相关实验视频

Updated: Jun 30, 2025

A Methodological Approach to Non-invasive Assessments of Vascular Function and Morphology
09:33

A Methodological Approach to Non-invasive Assessments of Vascular Function and Morphology

Published on: February 7, 2015

16.3K

[基于两阶段分析的多尺度动脉斑块检测方法]

H Xiao1, W Fang1, M Lin1

  • 1School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China.

Nan fang yi ke da xue xue bao = Journal of Southern Medical University
|March 19, 2024
PubMed
概括
此摘要是机器生成的。

一种新的深度学习方法,SM-YOLO,在超声波图像中准确识别多尺度的动脉斑. 这种两阶段的方法可以提高实时临床应用的检测速度和性能.

关键词:
这是一个YOLOX.冠状动脉斑块 冠状动脉斑块是什么深度学习是一种深度学习.功能融合 功能融合 功能融合支持矢量机器的支持矢量机器.

更多相关视频

A Method to Study the Correlation Between Local Collagen Structure and Mechanical Properties of Atherosclerotic Plaque Fibrous Tissue
13:45

A Method to Study the Correlation Between Local Collagen Structure and Mechanical Properties of Atherosclerotic Plaque Fibrous Tissue

Published on: November 11, 2022

2.1K
Microwave-driven Synthesis of Iron Oxide Nanoparticles for Fast Detection of Atherosclerosis
08:13

Microwave-driven Synthesis of Iron Oxide Nanoparticles for Fast Detection of Atherosclerosis

Published on: March 22, 2016

10.5K

相关实验视频

Last Updated: Jun 30, 2025

A Methodological Approach to Non-invasive Assessments of Vascular Function and Morphology
09:33

A Methodological Approach to Non-invasive Assessments of Vascular Function and Morphology

Published on: February 7, 2015

16.3K
A Method to Study the Correlation Between Local Collagen Structure and Mechanical Properties of Atherosclerotic Plaque Fibrous Tissue
13:45

A Method to Study the Correlation Between Local Collagen Structure and Mechanical Properties of Atherosclerotic Plaque Fibrous Tissue

Published on: November 11, 2022

2.1K
Microwave-driven Synthesis of Iron Oxide Nanoparticles for Fast Detection of Atherosclerosis
08:13

Microwave-driven Synthesis of Iron Oxide Nanoparticles for Fast Detection of Atherosclerosis

Published on: March 22, 2016

10.5K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 心血管诊断心血管诊断服务

背景情况:

  • 动脉斑块是心血管疾病风险的关键指标.
  • 在超声波图像中精确检测多尺度斑块仍然是一个挑战.

研究的目的:

  • 在超声波图像中开发一种准确和高效的方法来识别多尺度 carotid 斑块.
  • 为了提高动脉疾病评估的诊断性能.

主要方法:

  • 一个两阶段的深度学习模型,SM-YOLO,是使用卷积神经网络开发的.
  • 应用了图像预处理技术 (中位过,直方图平衡,马转换).
  • 第一个阶段使用YOLOX_l进行候选斑块检测,采用多尺度策略.
  • 第二阶段使用了面向梯度 (HOG) 和局部二进制模式 (LBP) 组图的特征,并使用了支向量机 (SVM) 分类器.

主要成果:

  • SM-YOLO实现了高性能指标:89.44%的回忆,90.96%的准确性,90.19%的F1-Score和92.70%的AP.
  • 该模型在所有性能指标和视觉评估中表现优于其他经过测试的检测模型.
  • 与更快的R-CNN相比,SM-YOLO的检测时间明显更快,满足了实时检测要求.

结论:

  • 拟议的SM-YOLO方法可以在超声波图像中准确识别动脉斑块.
  • 这种深度学习方法为增强动脉疾病诊断提供了一个有前途的工具.