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

Lineage Commitment

Lineage Commitment

Commitment is the process whereby stem cells:

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 and Radiographic Outcomes at a Mean of 7 Years Following Primary Transfibular Total Ankle Arthroplasty in Younger and Older Patients.

The Journal of bone and joint surgery. American volume·2026

Same author

IVCM-Insight: automated interactive interpretation of in vivo confocal microscopy.

NPJ digital medicine·2026

Same author

Corrigendum to "Dual-functional hydrogel platform suppresses M1 activation and stabilizes M2 macrophages in intervertebral disc degeneration" [Mater. Today Bio, 38 (2026), 103087].

Materials today. Bio·2026

Same author

Five views on the foundations of data science.

Patterns (New York, N.Y.)·2026

Same author

2 Parallel Heart: Parallel Experiments of a Highly Accurate Dual Independent Neural Network for Predicting Myocardial Infarction in Service of Clinical Practice.

IEEE transactions on bio-medical engineering·2026

Same author

Research Progress on Nano-TiO<sub>2</sub> Photocatalytic Degradation of Automobile Exhaust.

Molecules (Basel, Switzerland)·2026

Search research articles

相关实验视频

Updated: Jun 7, 2025

Cell Lineage Analyses and Gene Function Studies Using Twin-spot MARCM

Cell Lineage Analyses and Gene Function Studies Using Twin-spot MARCM

Published on: March 2, 2017

CMTT-JTracker:一个完全测试时间的自适应框架,为自动化细胞系构建服务.

Liuyin Chen¹, Sanyuan Fu², Zijun Zhang¹

¹Department of Data Science, College of Computing, City University of Hong Kong, Hong Kong SAR, China.

Briefings in bioinformatics

|November 18, 2024

概括

这项研究介绍了CMTT-JTracker,这是一个用于自动化细胞跟踪的新框架. 它提高了细胞活动监测的准确性和效率,在各种细胞数据集上表现优于现有的方法.

关键词:

细胞细分细胞细分细胞细分细胞跟踪追踪细胞跟踪深度学习是一种深度学习.测试时间的适应.

更多相关视频

Lineage Tracing and Clonal Analysis in Developing Cerebral Cortex Using Mosaic Analysis with Double Markers MADM

Lineage Tracing and Clonal Analysis in Developing Cerebral Cortex Using Mosaic Analysis with Double Markers MADM

Published on: May 8, 2020

Live Imaging Followed by Single Cell Tracking to Monitor Cell Biology and the Lineage Progression of Multiple Neural Populations

Live Imaging Followed by Single Cell Tracking to Monitor Cell Biology and the Lineage Progression of Multiple Neural Populations

Published on: December 16, 2017

相关实验视频

Last Updated: Jun 7, 2025

Cell Lineage Analyses and Gene Function Studies Using Twin-spot MARCM

Cell Lineage Analyses and Gene Function Studies Using Twin-spot MARCM

Published on: March 2, 2017

Lineage Tracing and Clonal Analysis in Developing Cerebral Cortex Using Mosaic Analysis with Double Markers MADM

Lineage Tracing and Clonal Analysis in Developing Cerebral Cortex Using Mosaic Analysis with Double Markers MADM

Published on: May 8, 2020

Live Imaging Followed by Single Cell Tracking to Monitor Cell Biology and the Lineage Progression of Multiple Neural Populations

Live Imaging Followed by Single Cell Tracking to Monitor Cell Biology and the Lineage Progression of Multiple Neural Populations

Published on: December 16, 2017

科学领域:

计算生物学计算生物学
图像分析图像分析
机器学习机器学习

背景情况:

自动化的细胞活动监测依赖于精确的细胞跟踪.
现有的方法往往难以平衡不同细胞数据集的计算效率,准确性和通用性.
强大的细胞跟踪对于各种生物研究应用至关重要.

研究的目的:

开发一种新,高效,准确的细胞追踪框架.
提高细胞跟踪方法在各种生物数据集中的通用性.
为了增强自动化的细胞活动监控能力.

主要方法:

开发了一个用于细胞跟踪的中央度量完全测试时间自适应框架 (CMTT-JTracker).
设计了一个用于预分段的CMTT机制,在不需要重新训练的情况下,以多个分辨率提取信息.
利用具有空间注意力的多任务学习网络,同时进行细胞检测和重新识别.

主要成果:

与现有基准相比,CMTT-JTracker表现出优越的生物和跟踪性能.
获得了高的多重对象跟踪精度 (MOTA) 评分:Fluo-N2DH-SIM+上为0.894,PhC-C2DL-PSC上为0.850.
仅CMTT细分单元的性能就超过了最先进的方法,特别是在密集细胞场景中,Dice系数从0.758到0.928.

结论:

CMTT-JTracker在自动化细胞跟踪,平衡效率和准确性方面取得了重大进展.
该框架在各种细胞成像数据集中显示出强大的通用性.
CMTT机制为细胞细分提供了强大的工具,特别是在具有挑战性的密集细胞环境中.