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

Multi-scale generative adversarial network: three-dimensional reconstruction of the scoliotic spine from biplanar X-rays.

Quantitative imaging in medicine and surgery·2026
Same author

Accurate and fast monocular endoscopic depth estimation of structure-content integrated diffusion.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2025
Same author

Degree of joint risk factor control and premature mortality in hypertensive participants.

Precision clinical medicine·2025
Same author

In Situ Anchored, Ultrasmall, Oxygen Vacancy-Rich TiO<sub>2-x</sub> on Carbonized Bacterial Cellulose for the Efficient Adsorption and Separation of Organic Pollutants.

Nanomaterials (Basel, Switzerland)·2025
Same author

Life satisfaction as compared with traditional risk factors in relation to incident cardiovascular diseases.

European journal of epidemiology·2025
Same author

Ferroelectric Polarization Effects of Single-Atom Catalysts on Water Oxidation.

Advanced materials (Deerfield Beach, Fla.)·2025

相关实验视频

Updated: Sep 17, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.4K

利用浅层特征和空间背景来对弱监督的脑内出血细分进行细分.

Hao Ma1,2,3, Min Tan2,4, Gaosheng Xie2

  • 1Software College, Northeastern University, Shenyang, China.

Quantitative imaging in medicine and surgery
|July 3, 2025
PubMed
概括

这项研究引入了一种新的弱监督语义细分方法,以使用深度学习来改善脑内出血的诊断. 这种新方法提高了细分的准确性,大大减少了错误,并帮助放射科医生.

关键词:
脑内出血细分 (ICH细分) 脑内出血细分 (ICH细分)医学成像医学成像缺乏监督的学习学习.

更多相关视频

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.4K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K

相关实验视频

Last Updated: Sep 17, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.4K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.4K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 深度学习 (Deep Learning) 是一种深度学习.

背景情况:

  • 弱监督的语义细分 (WSSS) 用于脑内出血 (ICH) 诊断是由于图像级标签缺乏精确的位置信息而受到限制.
  • 开发有效的WSSS方法对于改善自动化ICH细分和诊断至关重要.

研究的目的:

  • 开发一种用于增强脑内出血细分的新方法,使用弱图像级标签.
  • 为了提高ICH细分中的目标定位和轮检测的准确性.

主要方法:

  • 提出了一个浅特征类激活地图 (CAM) 模块,以利用细粒度的浅特征进行准确的定位.
  • 引入了一个空间上下文意识 (SCA) 模块,以结合空间上下文和完整的出血细分.
  • 在大脑出血细分数据集 (BHSD) 和内出血检测和细分数据集 (BCIHM) 的CT图像上验证了该方法.

主要成果:

  • 拟议的方法显著提高了ICH细分的准确性,将整个欧盟的平均交叉点 (mIoU) 从52.5%提高到69.8% (BHSD) 和50.1%提高到68.9% (BCIHM).
  • 与其他WSSS方法相比,实现了优越的性能,达到88%和86%的完全监督的U-Net性能.
  • 在错过和假阳性局部化中显著减少.

结论:

  • 新的WSSS方法通过准确匹配病变位置和轮,有效地改善了脑内出血细分.
  • 该方法减少了错过和错误的阳性定位,从而减少了放射科医生在创建像素级数据集中的工作量.