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

Glomerular Filtration01:15

Glomerular Filtration

The filtration membrane in the renal system is a highly specialized structure essential for filtering blood. It consists of glomerular capillaries and podocytes, forming a selective barrier that permits the passage of water and small solutes while restricting most plasma proteins and blood cells.
Components of the Filtration Membrane
The filtration process involves three key layers: the glomerular endothelial cells, the basement membrane, and the podocyte-formed filtration slits.
Glomerular Filtration: Net Filtration Pressure01:26

Glomerular Filtration: Net Filtration Pressure

Glomerular filtration, a key process in the kidneys, is regulated by three main pressures: Glomerular blood hydrostatic pressure (GBHP), Capsular hydrostatic pressure (CHP), and Blood colloid osmotic pressure (BCOP).
GBHP, with an average value of 55 mmHg, promotes filtration by pushing water and solutes through the filtration membrane. This is balanced by two opposing forces: CHP, a "back pressure" exerted against the filtration membrane by fluid already in the capsular space and renal tubule,...

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

Safety, Pharmacokinetics, and Pharmacodynamics of SHR6508, a Calcium-Sensing Receptor Agonist, in Maintenance Hemodialysis Patients With Secondary Hyperparathyroidism: A Multicenter, Randomized, Double-Blind, Placebo-Controlled Phase 1 Study.

Kidney medicine·2026
Same author

scMarkerGene: an interpretable neural network framework for cell-type-specific marker gene discovery.

Briefings in bioinformatics·2026
Same author

Predicting the impact of climate change on the suitable habitat of Populus qiongdaoensis in Hainan Island using MaxEnt modeling.

Scientific reports·2026
Same author

Geranyl pyrophosphate in sediments: a potentially limiting precursor associated with 2-MIB production by benthic filamentous cyanobacteria in shallow lakes.

Harmful algae·2026
Same author

Enhancing the emulsifying properties of Tenebrio molitor protein: Effects of oxidation degree on its physicochemical properties and structural characteristics.

International journal of biological macromolecules·2026
Same author

The Efficacy and Safety of Enarodustat for the Treatment of Anemia in Hemodialysis-Dependent Chronic Kidney Disease Patients: A Phase 3, Multicenter, Randomized, Active-Comparator (Recombinant Human Erythropoietin), Open-Label Study - The ENARODIAL Study.

American journal of nephrology·2026

相关实验视频

Updated: May 26, 2026

A Multi-compartment CNS Neuron-glia Co-culture Microfluidic Platform
13:24

A Multi-compartment CNS Neuron-glia Co-culture Microfluidic Platform

Published on: September 10, 2009

11.3K

全球网:一个基于双重任务分支的神经网络,用于多类质细胞细分.

Xiangxue Wang1, Jingkai Zhang1, Yuemei Xu2

  • 1Jiangsu Key Laboratory of Intelligent Medical Image Computing, School of Future Technology, Nanjing University of Information Science and Technology, Nanjing, 210044, China.

Computers in biology and medicine
|January 12, 2025
PubMed
概括

Glo-Net是一种新的深度学习方法,在病理幻灯片中准确地细分和分类质细胞. 它提高了5%的分类和6%的细分 IoU,特别是对于罕见的类型.

关键词:
数据不平衡的数据不平衡深度学习是一种深度学习.淋巴细胞的鉴定多任务学习是多任务学习.

更多相关视频

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

11.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

996

相关实验视频

Last Updated: May 26, 2026

A Multi-compartment CNS Neuron-glia Co-culture Microfluidic Platform
13:24

A Multi-compartment CNS Neuron-glia Co-culture Microfluidic Platform

Published on: September 10, 2009

11.3K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

11.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

996

科学领域:

  • 数字病理学数字病理学
  • 计算图像分析 计算图像分析
  • 脏病理学 脏病理学

背景情况:

  • 精确的淋巴细胞细分和分类对于从组织病理学幻灯片中表征脏疾病至关重要.
  • 传统方法与球分析固有的上下文理解和阶级不平衡作斗争.

研究的目的:

  • 开发一种深度学习方法,Glo-Net,用于在数字化病理幻灯片中准确细分和分类淋巴细胞.
  • 为了应对有限的上下文理解和球体图像分析中的阶级不平衡的挑战.

主要方法:

  • 提出了Glo-Net,这是一个双分支深度学习网络,用于同时对质细胞进行细分和分类.
  • 分段分支划分了淋巴细胞的边界,而分类分支则区分了淋巴细胞类型.
  • 实施了一种创新的损失功能,以减轻类不平衡,并改善小球类型的识别.

主要成果:

  • 在多机构数据集上获得了0.858的平均分类准确度和0.704的F-score.
  • 获得了0.866的平均交叉与联合 (IoU) 对于淋巴细胞细分.
  • 与以前的方法相比,在分类准确度上有5%的改进 (在次要类中高达14%) 和在细分上有6%的IOU增加.

结论:

  • Glo-Net显著提高了块细分和病理学分类的准确性和稳定性.
  • 该网络在多机构数据集中显示出更好的概括性,优于现有的方法.
  • 这种深度学习模型提供了一个强大的工具,可以通过自动化基因病理学分析精确地表征病.