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

Renal Corpuscle01:20

Renal Corpuscle

1.7K
The glomerulus and Bowman's capsule are two essential components of the nephron, which is the functional unit of the kidney. These microscopic structures play a critical role in the process of blood filtration to produce urine.
Glomerulus: Structure and Function
The glomerulus is a tiny, intricate network of capillaries located at the beginning of the nephron. It's enveloped by the Bowman's capsule and receives its blood supply from an afferent arteriole, which divides into numerous...
1.7K

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

Intradialytic Renal Rehabilitation and Mortality: Results from the Registry of Active Renal Rehabilitation in Dialysis Patients (REVEAL-D).

Clinical journal of the American Society of Nephrology : CJASN·2026
Same author

Urinary protein vs albumin for assessing kidney failure risk in chronic kidney disease.

Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association·2026
Same author

Evaluation of the Association between Age, Sex and d-Amino Acid-Based Estimation of Glomerular Filtration Rate.

Clinical journal of the American Society of Nephrology : CJASN·2026
Same author

Clinical Evaluation of the Clinical Reasoning Process of Large Language Models in Nephrology: Comparative Evaluation Study.

JMIR formative research·2026
Same author

Loss of Cyclin G-Associated Kinase Leads to Lysosome Dysfunction and Immune Modulation in Podocytes.

Journal of the American Society of Nephrology : JASN·2026
Same author

Immunoglobulin G4-Related Rhinosinusitis Masquerading as Refractory Eosinophilic Chronic Rhinosinusitis: A Case Report.

Internal medicine (Tokyo, Japan)·2026

相关实验视频

Updated: Jun 11, 2025

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

6.8K

自主监督学习用于从淋巴细胞图像中提取特征,并以最小的注释对疾病进行分类.

Masatoshi Abe1, Hirohiko Niioka2, Ayumi Matsumoto1

  • 1Department of Nephrology, Graduate School of Medicine, Osaka University, 2-2 Yamada-oka, Suita, Osaka, 565-0871, Japan.

Journal of the American Society of Nephrology : JASN
|October 9, 2024
PubMed
概括

没有标签的自蒸 (DINO) 可以有效地分析病理图像,而不需要大量的手动标签. 这种深度学习方法可以提高疾病分类的准确性,尤其是在有限的数据的情况下.

更多相关视频

Author Spotlight: Aiding Research in Kidney Biology by Labeling Glomeruli in Cleared Tissues
09:50

Author Spotlight: Aiding Research in Kidney Biology by Labeling Glomeruli in Cleared Tissues

Published on: February 9, 2024

1.2K
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

2.7K

相关实验视频

Last Updated: Jun 11, 2025

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

6.8K
Author Spotlight: Aiding Research in Kidney Biology by Labeling Glomeruli in Cleared Tissues
09:50

Author Spotlight: Aiding Research in Kidney Biology by Labeling Glomeruli in Cleared Tissues

Published on: February 9, 2024

1.2K
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

2.7K

科学领域:

  • 数字病理学数字病理学
  • 医学中的人工智能.
  • 脏病学研究的研究.

背景情况:

  • 病理学中的深度学习 (DL) 需要大型标记数据集,这些数据很难获得.
  • 有限的标记数据阻碍了DL用于活检图像分析的应用.

研究的目的:

  • 为了评估自主监督学习 (SSL) 的有效性,使用DINO分析脏活检图像.
  • 与传统方法相比,评估DINO在分类病和临床参数方面的表现.

主要方法:

  • 应用DINO (没有标签的自蒸) 到10,423个PAS染色的球膜图像.
  • 通过主要成分分析 (PCA) 提取和可视化淋巴细胞特征.
  • 在DINO预训练和ImageNet预训练模型上使用k-最近邻居 (kNN) 或线性头分类器执行分类任务.

主要成果:

  • 经过DINO预训练的模型捕获了明显的球体形态特征.
  • 在疾病分类方面,DINO预训练模型的表现优于ImageNet预训练模型 (ROC-AUC 0.93与0.89).
  • 在有限的标记数据和临床参数分类方面,DINO表现出卓越的性能,并通过外部验证得到证实.

结论:

  • DINO能够有效地从未标记的脏活检图像中提取组织学特征.
  • 使用DINO的SSL显著提高了DL对病分类的实用性.