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

Bone Marrow Sampling and Transplants01:22

Bone Marrow Sampling and Transplants

2.7K
Bone marrow transplant is a potential cure for several diseases, including cancer and specific genetic disorders. Notably, this procedure is applicable for patients suffering from aplastic anemia, certain types of leukemia, severe combined immunodeficiency disease (SCID), Hodgkin's disease, non-Hodgkin's lymphoma, multiple myeloma, thalassemia, sickle-cell disease, and certain cancers.
The transplant begins with high doses of chemotherapy and radiation treatment, which aim to destroy...
2.7K

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

Clinical outcomes, patterns of relapse and molecular landscape of advanced stage High Grade B-cell Lymphoma.

Blood advances·2026
Same author

Concurrent administration of BCMA and GPRC5D chimeric antigen receptor (CAR) T cells in advanced multiple myeloma.

Blood·2026
Same author

A holistic prognostic model for leukemia-free survival after allogeneic transplantation in acute leukemia.

Bone marrow transplantation·2026
Same author

Zanubrutinib, Obinutuzumab, and Venetoclax in CLL: Long-Term Follow Up, MRD Kinetics, Retreatment, T-Cell Profiling, PKs.

Blood advances·2026
Same author

Genomic features do not account for differences in multiple myeloma risk by ancestry.

Blood cancer discovery·2026
Same author

Fibrotic marrow limiting morphologic classification in MDS/MPN with SF3B1 mutation and thrombocytosis: diagnostic implications under the ICC 2022 framework.

Virchows Archiv : an international journal of pathology·2026

相关实验视频

Updated: Apr 13, 2026

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone
09:31

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone

Published on: April 8, 2015

11.5K

DeepHeme是一款高性能,可通用的深层组合,用于骨髓形态测量和血液诊断.

Shenghuan Sun1, Zhanghan Yin2,3,4, Jacob G Van Cleave2,3

  • 1Bakar Computational Health Sciences Institute, University of California, San Francisco, CA 94143, USA.

Science translational medicine
|June 11, 2025
PubMed
概括

深度学习模型DeepHeme准确地分类骨髓细胞,匹配或超过人类专家的性能. 这种人工智能工具提高了血液学疾病的诊断效率.

更多相关视频

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

11.6K
Preparation of Whole Bone Marrow for Mass Cytometry Analysis of Neutrophil-lineage Cells
08:09

Preparation of Whole Bone Marrow for Mass Cytometry Analysis of Neutrophil-lineage Cells

Published on: June 19, 2019

9.2K

相关实验视频

Last Updated: Apr 13, 2026

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone
09:31

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone

Published on: April 8, 2015

11.5K
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

11.6K
Preparation of Whole Bone Marrow for Mass Cytometry Analysis of Neutrophil-lineage Cells
08:09

Preparation of Whole Bone Marrow for Mass Cytometry Analysis of Neutrophil-lineage Cells

Published on: June 19, 2019

9.2K

科学领域:

  • 计算病理学计算病理学
  • 血液学中的人工智能
  • 医学诊断 医学诊断 医学诊断

背景情况:

  • 骨髓吸附物 (BMA) 细胞形态学对于诊断血液学疾病至关重要,但复杂且容易出错.
  • 目前用于BMA分析的深度学习模型缺乏专家级准确性和通用性.

研究的目的:

  • 开发和验证一个深度学习模型,用于准确和可概括的骨髓细胞分类.
  • 为了在自动化血液病理幻灯片分析中实现专家级别的性能.

主要方法:

  • 开发了DeepHeme,这是一个快照集团深度学习分类器,使用了30394张骨髓图像的精选数据集.
  • 在旧金山加利福尼亚大学的数据上训练和测试DeepHeme,并在纪念斯隆凯特林癌症中心的独立数据集上进行验证.
  • 将DeepHeme的细胞分类性能与三个人类血液病理学专家进行了比较.

主要成果:

  • DeepHeme实现了比以前的模型更高的准确性,并分类了更多的细胞类型.
  • 外部验证表明,在不同的数据集和WSI系统中具有强大的通用性.
  • 在单个细胞分类方面,DeepHeme的诊断性能与人类专家的诊断性能相当或超过.

结论:

  • DeepHeme代表了自动化血液病理幻灯片分析的重大进步.
  • 精确且可泛化的人工智能驱动的细胞分类有助于开发预测标记.
  • 这项技术有可能提高血液学疾病处理中的诊断效率和准确性.