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

Classification of Leukocytes01:30

Classification of Leukocytes

1.8K
Leukocytes are classified into two groups based on the presence or absence of cytoplasmic granules. Granular leukocytes, which contain granules, belong to the myeloid lineage and are divided into three subtypes: neutrophils, eosinophils, and basophils. These cells are roughly spherical and characterized by the granules in their cytoplasm.
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
1.8K

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

[Patient similarity: When the internist's reasoning meets artificial intelligence].

La Revue de medecine interne·2026
Same author

Benchmarking deep learning architectures for MALDI-TOF mass spectrometry in infectious disease diagnostics and vector-borne disease surveillance.

NPJ digital medicine·2026
Same author

Zoī cohort, a prospective cohort with comprehensive phenotyping for preventive medicine in France, first 1000 participants: cohort profile.

BMJ open·2026
Same author

Machine Learning for Cardiovascular Prevention Prescriptions: Real-World vs. Synthetic Data.

Studies in health technology and informatics·2026
Same author

Development Parameters of the Decision Aid Rule-Based Evaluation and Support Tool (REST) for Optimizing the Resources of an Information Extraction Task.

Studies in health technology and informatics·2026
Same author

Scaling Up Digital Health Education at Sorbonne University: Year Two Evaluation of the SN@SU Training Program.

Studies in health technology and informatics·2026

相关实验视频

Updated: Jun 15, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.4K

通过多式联网改善白细胞分类的解释性

Manon Chossegros1, Xavier Tannier1, Daniel Stockholm2,3

  • 1Sorbonne Universite, Inserm, Universite Sorbonne Paris-Nord, Laboratoire d'Informatique Medicale et d'Ingenierie des Connaissances en e-Sante, LIMICS, France.

Studies in health technology and informatics
|August 23, 2024
PubMed
概括

这项研究引入了用于白细胞分类的多模式神经网络,将图像和形态数据结合起来. 该模型增强了可解释性,同时识别了用于诊断血液病的关键细胞特征.

关键词:
深度学习 (Deep Learning) 是一种深度学习.机器学习 机器学习多式联络分类是多式联络分类.白血细胞 白血细胞

更多相关视频

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors
06:32

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

1.9K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

508

相关实验视频

Last Updated: Jun 15, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.4K
Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors
06:32

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

1.9K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

508

科学领域:

  • 血液学 血液学 血液学
  • 计算生物学 计算生物学
  • 医疗成像医学成像

背景情况:

  • 准确的白细胞分类对于诊断血液疾病至关重要.
  • 目前的方法依赖于基于图像或基于特征的分类,每个都有局限性.
  • 基于图像的分类提供了高性能,而基于功能的分类提供了更好的可解释性.

研究的目的:

  • 开发和评估用于白细胞分类的多模式神经网络.
  • 将多模式方法的性能和可解释性与仅图像和仅特征模型进行比较.
  • 识别有助于细胞表征的关键形态特征.

主要方法:

  • 利用多模式神经网络整合了细胞图像和形态特征.
  • 训练并比较了三个模型:仅图像,仅功能和多模式.
  • 使用SHAP (夏普利增量解释) 值来解释模型的可解释性.

主要成果:

  • 仅以图像训练实现了最高的分类性能.
  • 与仅使用图像的方法相比,多式模式模型显示了增强的解释性.
  • 细胞表征的关键形态特征被多模式模型确定.

结论:

  • 多模式神经网络在白细胞分类中提供了性能和可解释性之间的平衡.
  • 可以有效地使用SHAP值来解释血液学中的复杂模型.
  • 该研究强调了整合不同类型的数据对强大和易于理解的诊断工具的重要性.