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

AI-Assisted Detection of Supraspinatus Tendon Pathologies Using a Hierarchical Deep Learning Model to Improve Clinical Applicability: Development and Evaluation Study.

JMIR medical informatics·2026
Same author

Pediatric eosinophilic esophagitis in a tertiary center in Taiwan: A cohort study.

Pediatrics and neonatology·2026
Same author

Clinical implementation of 3D deep learning techniques in predicting touch-up lesions for atrial fibrillation patients undergoing cryoablation.

International journal of cardiology. Heart & vasculature·2026
Same author

Gut commensal Parabacteroides goldsteinii protects against Salmonella infection in mice by enhancing innate defense function.

NPJ biofilms and microbiomes·2026
Same author

Digital Twins for Predictive Modelling of Thrombosis and Stroke Risk: Current Approaches and Future Directions.

Thrombosis and haemostasis·2026
Same author

Assessing the Evolution and Influence of Medical Open Databases on Biomedical Research and Health Care Innovation: A 25-Year Perspective With a Focus on Privacy and Privacy-Enhancing Technologies.

Journal of medical Internet research·2026

相关实验视频

Updated: Jul 18, 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

48.1K

用快速数据密度函数转换对脑瘤图像进行特征感知无监督病变细分.

Shin-Jhe Huang1, Chien-Chang Chen1, Yamin Kao1

  • 1Geometric Data Vision Laboratory, Department of Biomedical Sciences and Engineering, National Central University, Taoyuan City, 32001, Taiwan.

Scientific reports
|August 21, 2023
PubMed
概括

我们介绍了一种使用快速数据密度函数转换 (fDDFT) 和几何深度学习进行无监督医疗图像细分的新方法. 这种方法准确地识别了病变形态和边界,提高了临床研究的效率和准确性.

更多相关视频

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

42.7K
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

40.3K

相关实验视频

Last Updated: Jul 18, 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

48.1K
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

42.7K
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

40.3K

科学领域:

  • 医学成像分析 医学成像分析
  • 计算物理 计算物理
  • 人工智能的人工智能

背景情况:

  • 医疗图像的准确细分对于诊断和治疗计划至关重要.
  • 当前的深度学习方法通常需要大型标记数据集和大量的计算资源.
  • 无监督方法为病变识别和细分提供了一个有希望的替代方案.

研究的目的:

  • 开发一种使用医学图像矩阵识别和细分病变形态的无监督方法.
  • 利用快速数据密度功能转换 (fDDFT) 和几何深度学习的框架.
  • 提高医学图像分析的效率和准确性.

主要方法:

  • 在fDDFT能量空间上对灰度医疗图像矩阵的异态映射.
  • 整合几何深度学习和图形神经网络指标.
  • 使用网格密度函数与全球卷积内核用于特征提取和边界识别.
  • 使用自动编码器辅助模块来减少计算复杂性.
  • 在各种开放访问数据集上进行验证.

主要成果:

  • 实现了无监督的病变形态识别和准确的细分.
  • 证明了高效的全球卷积运算,并降低了复杂度.
  • 在大型3D数据集中,每个对象的推断时间平均为1.76秒.
  • 子的中位数超过了0.75,满足了标准的深度学习要求.
  • fDDFT和神经网络的协同作用改善了训练 (58%) 和推断 (51%) 时间,将Dice的得分提高到0.9415.

结论:

  • 拟议的基于fDDFT的方法可以在医学图像中有效地进行无监督的病变细分.
  • 与传统的深度学习模型相比,该方法在计算效率和准确性方面提供了显著的改进.
  • 这种技术为跨学科应用和临床研究提供了快速计算建模的便利.