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

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

Genomic and genetic insights into speciation and pigment pattern diversification in <i>Danio</i> fishes.

bioRxiv : the preprint server for biology·2025
Same author

A machine learning-based method to optimize the immunogenicity of human leukocyte antigen class I-restricted neoantigens.

Briefings in bioinformatics·2025
Same author

Triple-effect correction for Cell Painting data with contrastive and domain-adversarial learning.

Nature communications·2025
Same author

Predicting fine-grained cell types from histology images through cross-modal learning in spatial transcriptomics.

Bioinformatics (Oxford, England)·2025
Same author

Pairpot: a database with real-time lasso-based analysis tailored for paired single-cell and spatial transcriptomics.

Nucleic acids research·2024
Same author

PhiHER2: phenotype-informed weakly supervised model for HER2 status prediction from pathological images.

Bioinformatics (Oxford, England)·2024
Same journal

Targeted Delivery of Indole-3-Pyruvic Acid Suppresses Macrophage Ferroptosis to Enhance CD8<sup>+</sup> T Cell-Mediated Immunotherapy Response in Bladder Cancer.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same journal

Pathological Copper Overload Reprograms SOD1 Activation via COMMD1 to Promote Senescence and Fibrosis.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same journal

Bending-Resistant Intimate 3D Graphene-Metal Heterojunctions for Highly Sensitive and Robust Flexible Sensors.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same journal

A Pathology-Instructed Theranostic Platform with Mechanoadaptive and ROS-Powered Nanobreathing Functions for Precision Myocardial Repair.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same journal

Targeting p21-High Senescent Kupffer Cells Nanotherapeutically Potentiates Antitumor Immunity in Advanced Hepatocellular Carcinoma with Portal Vein Tumor Thrombus.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same journal

A Ceramic Network for Hybrid Solid Electrolyte Lithium Metal Batteries.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
查看所有相关文章

相关实验视频

Updated: Jan 12, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.6K

预测乳腺癌病理图像的MammaPrint复发风险 使用弱监督的变压器

Chaoyang Yan1, Linwei Li2,3,4, Xiaolong Qian3,4,5

  • 1Centre for Bioinformatics and Intelligent Medicine, College of Computer Science, Nankai University, Tianjin, 300350, China.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)
|November 8, 2025
PubMed
概括
此摘要是机器生成的。

一个新的AI模型,CPMP,从病理幻灯片预测乳腺癌复发风险,补充基因组测试. 这种方法提供了对瘤形态和空间模式的洞察,提高了预后准确性.

关键词:
乳腺癌 乳腺癌 乳腺癌计算病理学计算病理学复发风险评估 复发风险评估瘤的空间形态学缺乏监督的学习学习.

更多相关视频

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K

相关实验视频

Last Updated: Jan 12, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.6K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K

科学领域:

  • 计算病理学计算病理学
  • 人工智能在瘤学中的应用
  • 基因组医学是一种基因组医学.

背景情况:

  • 乳腺癌 (BC) 的复发显著影响死亡率.
  • 在MammaPrint (MP) 基因组测定评估复发风险和化疗效益的早期阶段HR+/HER2-BC.
  • MP的局限性包括高成本和无法分析瘤形态.

研究的目的:

  • 开发一个弱监督的代理-注意力变压器模型 (CPMP) 用于预测MP复发风险,使用基因病理幻灯片.
  • 探索与MP风险组相关的空间和形态模式.
  • 评估CPMP在外部队列中的预后能力.

主要方法:

  • 建立一个乳腺癌MammaPrint队列.
  • 开发CPMP,一个监督较弱的代理人注意力转换器模型.
  • 从没有注释的基因病理幻灯片中预测MP风险组.
  • 使用CPMP进行空间和形态分析.
  • 在外部队列中预测评估.

主要成果:

  • 在预测MP风险组中,CPMP获得了0.824±0.03的AUROC.
  • 该模型揭示了瘤的空间定位和不同MP风险组的细胞间相互作用模式.
  • CPMP特征瘤形态多样性,识别与MP风险相关的独特表型.
  • 预后评估显示了远程转移风险的显著分层 (HR: 3.14,p值 = 0.0014).

结论:

  • CPMP有效地预测了从基因病理幻灯片的MammaPrint复发风险.
  • 该模型为与复发风险相关的瘤空间和形态特征提供了新的见解.
  • CPMP证明具有显著的预后价值,为早期乳腺癌的基因组风险评估提供了具有成本效益的补充.