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

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

Photoactive Heteropore Covalent Metal-Organic Frameworks for CO<sub>2</sub> Photoreduction.

Journal of the American Chemical Society·2026

Same author

Lewis Acid/Base Au-Mn Pairs in Metal Nanoclusters for Enhanced Photocatalytic C(sp<sup>2</sup>)-H Arylation.

Angewandte Chemie (International ed. in English)·2026

Same author

Artificial intelligence-detected HER2 strong-positive tumor proportion predicts FISH positivity and treatment response in breast cancer.

PloS one·2026

Same author

Dysbiosis and unsustainable delayed gut microbiota development as non-invasive biomarkers for predicting autism spectrum disorder in Chinese children.

Frontiers in microbiology·2026

Same author

Artificial intelligence-guided analysis of the tumor microenvironment predicts response to pembrolizumab in rare tumors.

Journal for immunotherapy of cancer·2026

Same author

Analysis of the impact of altitude changes on human physiological indicators and response capabilities.

Scientific reports·2026

Search research articles

相关实验视频

Updated: Sep 12, 2025

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments

Published on: April 30, 2021

OCELOT 2023:通过细胞-组织相互作用挑战细胞检测.

JaeWoong Shin¹, Jeongun Ryu¹, Aaron Valero Puche¹

¹Lunit Inc., Seoul, Republic of Korea.

Medical image analysis

|August 9, 2025

概括

在全幻灯片图像中了解细胞和组织相互作用,可以显著改善病理学的深度学习模型. 在OCELOT 2023挑战中表明,结合多尺度的细胞-组织语义可以提高性能,而不是仅检测细胞.

关键词:

癌细胞组织细分的细分.细胞组织关系瘤细胞检测检测器

更多相关视频

A Mimic of the Tumor Microenvironment: A Simple Method for Generating Enriched Cell Populations and Investigating Intercellular Communication

A Mimic of the Tumor Microenvironment: A Simple Method for Generating Enriched Cell Populations and Investigating Intercellular Communication

Published on: September 20, 2016

In-vivo Detection of Protein-protein Interactions on Micro-patterned Surfaces

In-vivo Detection of Protein-protein Interactions on Micro-patterned Surfaces

Published on: March 19, 2010

相关实验视频

Last Updated: Sep 12, 2025

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments

Published on: April 30, 2021

A Mimic of the Tumor Microenvironment: A Simple Method for Generating Enriched Cell Populations and Investigating Intercellular Communication

A Mimic of the Tumor Microenvironment: A Simple Method for Generating Enriched Cell Populations and Investigating Intercellular Communication

Published on: September 20, 2016

In-vivo Detection of Protein-protein Interactions on Micro-patterned Surfaces

In-vivo Detection of Protein-protein Interactions on Micro-patterned Surfaces

Published on: March 19, 2010

科学领域:

数字病理学数字病理学
计算生物学是一种计算生物学.
医学中的人工智能

背景情况:

病理学家在全幻灯片图像上使用不同的放大值进行诊断,评估组织形态和细胞细节.
目前的深度学习细胞检测模型缺乏整合多尺度信息的能力,并且无法理解不同放大度的结构之间的相互依赖语义.
该领域的一个关键局限性是缺乏具有多尺度,重叠的细胞和组织注释的数据集.

研究的目的:

验证这一假设,即理解细胞-组织相互作用对于在数字病理学中实现人类水平的表现至关重要.
通过提供标准化的挑战和数据集,加快在多尺度细胞和组织分析方面的研究.
促进社区参与,并收集有关病理图像分析的先进深度学习方法的见解.

主要方法:

策划了OCELOT 2023挑战数据集,其中包括来自六个器官的重叠细胞检测和组织细分注释.
数据来源于癌症基因组图谱 (TCGA) 的全幻灯片图像,用血素和色素染色.
数据集包括306个整张幻灯片图像中的673个注释对,分为培训,验证和测试子集.

主要成果:

参与模型在理解细胞-组织关系方面表现出显著的改善.
与基线单细胞模型相比,表现最好的模型在测试组中的F1得分增加了7.99.
这些结果突出了通过结合多尺度语义和细胞-组织相互作用来实现的显著性能增长.

结论:

整合多层次语义和细胞-组织关系对于推进数字病理学的深度学习至关重要.
通过OCELOT 2023挑战,成功推动了细胞和组织相互作用建模方面的创新.
未来的研究应该专注于开发可以有效利用多规模上下文信息以提供更准确的诊断支持的模型.