Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Single-Chain Anti-IL-1β Antibody Carried by Outer Membrane Vesicles of Bacteroides fragilis Alleviates Tubular Inflammation in Chronic Kidney Disease.

Journal of extracellular vesicles·2026

Same author

Deficiency of Growth Arrest and DNA Damage-Inducible 45 α -R-Loop Pathway and Kidney Injury in Diabetic Nephropathy.

Journal of the American Society of Nephrology : JASN·2025

Same author

Deficiency of thiosulfate sulfurtransferase mediates the dysfunction of renal tubular mitochondrial fatty acid oxidation in diabetic kidney disease.

Cell death and differentiation·2024

Same author

Roxadustat Versus Erythropoietin: The Comparison of Efficacy in Reversing Ventricular Remodeling in Dialysis Patients with Anaemia.

International journal of medical sciences·2024

Same author

ITGAM-mediated macrophages contribute to basement membrane damage in diabetic nephropathy and atherosclerosis.

BMC nephrology·2024

Same author

The ratio of neutrophils to lymphocytes effectively predicts clinical outcomes in idiopathic membranous nephropathy.

Clinical nephrology·2023

Search research articles

相关实验视频

Updated: Jul 7, 2025

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

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

Published on: June 18, 2020

基于云服务器的机器学习的应用,以协助在IgA脏病的病理结构识别.

Yu-Lin Huang¹, Xiao Qi Liu², Yang Huang¹

¹Institute of Nephrology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China.

Journal of clinical pathology

|December 20, 2023

概括

机器学习模型在整个幻灯片图像中准确地识别病区域. 一个基于互联网的平台促进了广泛采用,以改善IgA病诊断的临床决策支持.

关键词:

诊断的方法诊断的方法脏脏是指脏的部分.机器学习机器学习电路病理学电路病理学

更多相关视频

Detection of MicroRNA Expression in the Kidneys of Immunoglobulin A Nephropathic Mice

Detection of MicroRNA Expression in the Kidneys of Immunoglobulin A Nephropathic Mice

Published on: July 8, 2020

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

相关实验视频

Last Updated: Jul 7, 2025

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

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

Published on: June 18, 2020

Detection of MicroRNA Expression in the Kidneys of Immunoglobulin A Nephropathic Mice

Detection of MicroRNA Expression in the Kidneys of Immunoglobulin A Nephropathic Mice

Published on: July 8, 2020

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

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:

机器学习 (ML) 模型通过分析整个幻灯片图像 (WSIs) 来帮助诊断疾病.
有效的ML模型需要强大,用户友好和普遍适用的数据集来支持临床决策.
目前的ML应用需要在真实世界的临床数据上进行验证.

研究的目的:

开发和评估一种机器学习算法,用于在IgA瘤病 (IgAN) WSIs中定位和分类感兴趣区域 (ROI).
评估基于互联网的ML模型在病理学中的临床决策支持的性能.
为了证明ML在细分脏组织图像中的病理特征方面的有效性.

主要方法:

收集和注释了原发性IgA病 (IgAN) 的整体幻灯片图像 (WSI).
H-AI-L算法是在云平台上开发的,用于WSI查看和ROI检测.
用F1得分,精度,回忆和马修的相关系数 (MCC) 来评估模型性能.

主要成果:

预先训练的模型获得高F1得分,用于球位 (0.89) 和全球性硬化症的差异化 (0.91).
全球球球膜病变多重分类的F1总得分为0.81,回忆率为0.96.
间歇性纤维化/管状缩病变的相似性达到了0.75,表明预测准确度很好.

结论:

机器学习集成算法有效地在Igan WSIs中对ROI进行细分.
基于互联网的ML模型的部署促进了在多个中心的广泛采用和利用.
这种方法支持增加WSIs的分析,以提高诊断能力.