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

The Value of Five Novel Anthropometric Indicators in Evaluating MASLD and Liver Fibrosis in MASLD: A Cross-Sectional Study.

JGH open : an open access journal of gastroenterology and hepatology·2026
Same author

Efficacy and safety of multiple treatments for small hepatocellular carcinoma: an updated systematic review and component network meta analysis.

EClinicalMedicine·2026
Same author

Natural history and clinical characteristics of pulmonary subsolid nodules in pediatric patients: a cohort study.

Quantitative imaging in medicine and surgery·2026
Same author

Glymphatic system dysfunction in obstructive sleep apnea with mild cognitive impairment evidenced by DTI-ALPS.

Sleep medicine·2026
Same author

The micro-structural changes in white matter fibers associated with anxiety and depression in moderate-severe obstructive sleep apnea.

Scientific reports·2026
Same author

Association between lactate-to-albumin ratio and all-cause mortality in critically ill hepatic failure patients with sepsis: A retrospective cohort study.

Medicine·2026

相关实验视频

Updated: Jul 25, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.8K

一个高效的存储和色策略,用于基于矢量量化的3D大脑细分和瘤提取,使用无监督深度学习网络.

Ailing De1, Xiulin Wang1,2, Qing Zhang1

  • 1Department of Radiology, Affiliated Zhongshan Hospital of Dalian University, Dalian, 116000 Liaoning China.

Cognitive neurodynamics
|June 26, 2023
PubMed
概括

这项研究介绍了一种无监督的深度学习方法,用于3D脑瘤细分,克服了手动注释的需要,并提高了计算速度. 这种新的方法实现了临床应用的高精度和效率.

关键词:
3D数据细分的3D数据细分.代码书设计 代码书设计在 DEC 网络中,DEC 网络是 DEC 网络.没有监督的深度学习.矢量量化定量化 矢量量化定量化

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

40.3K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

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

Published on: December 15, 2023

2.5K

相关实验视频

Last Updated: Jul 25, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.8K
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
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

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

Published on: December 15, 2023

2.5K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算神经科学是一种神经科学.

背景情况:

  • 深度学习在3D脑图像细分方面表现出色,这对于瘤诊断和治疗计划至关重要.
  • 当前的方法面临着巨大的手动注释要求和计算效率低下的挑战.
  • 瘤的放射性特征对于临床决策至关重要.

研究的目的:

  • 开发用于脑瘤的无监督3D深度学习细分方法.
  • 解决手动数据注释的局限性,提高计算效率.
  • 提高生物医学图像细分中的深度学习模型的可行性.

主要方法:

  • 提出了一种基于矢量量化 (VQ) 的3D细分,使用一种新的无监督3D深嵌入集群 (3D-DEC) 网络.
  • 实施了一种效率内存保留和色策略,以提高计算速度.
  • 以无监督的方式对基于VQ的3D-DEC网络进行了体积数据的训练.

主要成果:

  • 在公开的MRI数据集 (IBSR,BrainWeb) 和真实临床数据上实现了卓越的准确性 (例如,在真实数据上达到了91%) 和稳定性.
  • 证明了显著的效率与显著的加速比率 (例如,在真实数据上31.00).
  • 在细分准确性和速度方面表现优于最先进的3D卷积神经网络 (CNN) 模型.

结论:

  • 提出的无监督方法有效地解决了在脑瘤细分中缺乏手动注释的问题.
  • 该模型显著增加了计算速度,同时保持了竞争力的细分精度.
  • 这种方法适用于瘤治疗后续检查,为手术和术后护理提供关键的放射性特征.