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

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...

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

Secondary neutron emissions and induced activity quantification during 14 MeV proton irradiation of thick natural yttrium target.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2026
Same author

Molecular Characterization and Detection of <i>Brachyspira pilosicoli</i> Associated with Intestinal Dysbiosis of Layer Chickens on the Indian Subcontinent.

Avian diseases·2026
Same author

Phytochemical-Mediated Synthesis of AgNPs Using Caulerpa peltata: Photoluminescent Analysis and Cytotoxic Potential.

Luminescence : the journal of biological and chemical luminescence·2025
Same author

Genomic plasticity and phylogeny of sheeppox and goatpox viruses reveal progressive host and terrestrial adaptation.

Gene·2025
Same author

Phyco-Fabricated Zinc Oxide Nanorods From Dictyota dichotoma Seaweed: A Promising Resource for Environmental and Biomedical Applications.

Luminescence : the journal of biological and chemical luminescence·2025
Same author

Green Synthesis of ZrO<sub>2</sub> Nanoparticles From Gardenia resinifera for Efficient Photocatalytic Methylene Blue Dye Degradation With Antimicrobial and Antioxidant Properties.

Luminescence : the journal of biological and chemical luminescence·2025

相关实验视频

Updated: Jun 27, 2026

Database-guided Flow-cytometry for Evaluation of Bone Marrow Myeloid Cell Maturation
12:05

Database-guided Flow-cytometry for Evaluation of Bone Marrow Myeloid Cell Maturation

Published on: November 3, 2018

11.5K

形态异常 红血细胞的分类 使用不平衡数据集的融合方法.

Prasenjit Dhar1, K Suganya Devi1, Ramanuj Bhattacharjee2

  • 1Medical Imaging Laboratory, Department of Computer Science and Engineering, National Institute of Technology Silchar, Silchar, Assam, India.

Microscopy research and technique
|January 28, 2025
PubMed
概括

使用LSTM神经网络的深度学习方法自动化了异常红细胞 (RBC) 的分类,改善了早期发现血液疾病的方法. 这种方法融合了功能,并使用自定义的损失函数来处理类不平衡,提高诊断准确度.

关键词:
不正常的红细胞.没有异细胞化.阶级不平衡 阶级不平衡核聚变的特点是核聚变的特点.聚基洛细胞酶 (poikilocytosis) 是一种

更多相关视频

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

7.0K
Immunostaining-Based Detection of Dynamic Alterations in Red Blood Cell Proteins
10:07

Immunostaining-Based Detection of Dynamic Alterations in Red Blood Cell Proteins

Published on: March 17, 2023

1.5K

相关实验视频

Last Updated: Jun 27, 2026

Database-guided Flow-cytometry for Evaluation of Bone Marrow Myeloid Cell Maturation
12:05

Database-guided Flow-cytometry for Evaluation of Bone Marrow Myeloid Cell Maturation

Published on: November 3, 2018

11.5K
Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

7.0K
Immunostaining-Based Detection of Dynamic Alterations in Red Blood Cell Proteins
10:07

Immunostaining-Based Detection of Dynamic Alterations in Red Blood Cell Proteins

Published on: March 17, 2023

1.5K

科学领域:

  • 医学诊断 医学诊断 医学诊断
  • 医疗保健中的人工智能
  • 血液学 血液学 血液学

背景情况:

  • 红细胞 (RBC) 对于运输氧气至关重要,但形状 (poikilocytosis) 和大小 (anisocytosis) 的异常可能表明严重的健康问题,如贫血和血症.
  • 血液学家对红细胞进行手动显微镜检查是耗时且容易出错的.
  • 红细胞形态的自动分类对于早期和准确诊断血液相关疾病至关重要.

研究的目的:

  • 开发和评估一种深度学习策略,利用长短期记忆 (LSTM) 神经网络进行异常红细胞的自动分类.
  • 通过融合传统和高级特征并解决阶级不平衡问题,提高分类准确性.
  • 在不同的数据集上验证拟议的方法,并将其性能与现有的基准模型进行比较.

主要方法:

  • 基于长期短期记忆 (LSTM) 的神经网络被用于RBC分类.
  • 传统和高级特征被提取和融合,以改善异常红细胞类别之间的区别.
  • 通过将类权重集成到交叉损失中来设计一个自定义的损失函数,以减轻类失衡的影响.
  • 该模型在Chula-PIC-Lab数据集和Cachar癌症医院和研究中心 (CCHRC) 的私人数据集上进行了训练和评估.

主要成果:

  • 提出的基于LSTM的深度学习方法在Chula-PIC-Lab和CCHRC数据集上实现了高平均F1分数和准确性.
  • 该方法与基准模型相比表现优越,包括Custom CNN,Custom LSTM,Efficient Net-B1,SMOTE,混合NN和HPKNN.
  • 定制损失函数有效地解决了类不平衡问题,从而对代表性不足的异常RBC类型进行了更强大的分类.

结论:

  • 开发的基于LSTM的深度学习策略为分类异常红细胞提供了准确有效的自动化方法.
  • 这种方法有可能在早期诊断和治疗血液相关疾病方面显著帮助血液学家.
  • 功能融合和自定义丢失函数技术有效地提高了医疗图像分类任务的深度学习模型的性能.