相关实验视频

Updated: Jun 14, 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

利用深度学习识别脏活检电子显微镜图像中的电子密度沉积物

Shuangshuang Zhu^1,2, Bei Luo³, Sendong Lai³

¹Department of Laboratory Medicine, Guangdong Provincial Key Laboratory of Precision Medical Diagnostics, Guangdong Engineering and Technology Research Center for Rapid Diagnostic Biosensors, Guangdong Provincial Key Laboratory of Single-Cell and Extracellular Vesicles, Nanfang Hospital, Southern Medical University, Guangzhou, China, zhushuang101@126.com.

American journal of nephrology

|May 19, 2025

概括

一个新的深度学习平台在脏活检图像中自动化电子密度沉积位置. 这个人工智能工具提供了高效可靠的分类,帮助病理学家诊断脏疾病.

科学领域:

腎臟病學 (nephrology) 是一種神經病學.
数字病理学数字病理学
人工智能在医学中的应用

背景情况:

电子显微镜 (EM) 对于识别细胞沉积物在脏活检中至关重要.
这些沉积物的手动分类是耗时的,容易引起观察者之间的变化.
自动化这个过程可以提高诊断效率和一致性.

研究的目的:

开发和评估基于深度学习的平台,用于在EM图像中自动分类电子密度沉积位置.
将深度学习模型的性能与人类病理学家进行比较.

主要方法:

从1,039个脏活检中回顾收集了4,303张EM图像.
由专家病理学家建立的基本真理,将沉积物分为介质层,亚皮层,内膜层和亚内皮层.
开发基于ResNet18的深度学习模型,用于二进制和多类分类.
使用科恩的卡帕和准确度指标对专家病理学家进行验证.

主要成果:

深度学习模型在识别存储存在方面取得了高准确性 (AUC 0.959,准确率为 0.899).
分类子网在特定的沉积点上表现出强的表现 (例如,亚皮质AUC为0.987,内膜AUC为0.986).
该模型的准确性超过了综合性病理学家,但低于EM专家.

结论:

成功开发了一个网络平台,用于在脏活检EM图像中进行自动化电子密度沉积位置评估.
深度学习模型提供了一种高效可靠的工具,性能优于综合性病理学家.
这项技术有可能提高病诊断的准确性和速度.

关键词:

深度学习模型深度学习模型电子显微镜电子显微镜脏活组织检查网络平台网络平台网络平台

更多相关视频

Identification of the Source of Secreted Proteins in the Kidney by Brefeldin A Injection

Identification of the Source of Secreted Proteins in the Kidney by Brefeldin A Injection

Published on: November 10, 2021

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

相关概念视频

Immunogold Electron Microscopy

Immunogold Electron Microscopy

Immunoelectron microscopy utilizes immunogold labeling of endogenous proteins with specific antibodies to detect and localize these proteins in cells and tissues. The procedure provides insights into the distribution and quantification of protein under different stimulation conditions offering clues about their functions. Conjugating highly electron-dense gold particles with primary or secondary antibodies allow antigen detection on and within cells, with high resolution and specificity.

Preparation of Samples for Electron Microscopy

Preparation of Samples for Electron Microscopy

To be visualized by an electron microscope, either transmission or scanning, biological samples need to be fixed (stabilized) so the electron beam does not destroy them and dried thoroughly (desiccated/dehydrated) so the vacuum does not affect them. Fixation needs to be done as quickly as possible because the sample properties will start changing as soon as it is removed from its natural environment. For example, in a tissue sample, the oxygen levels begin decreasing, causing an altered...