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

Statescope: an integrative deconvolution framework for discovering cell states in tumors.

Nature communications·2026
Same author

Human epididymis protein 4 and risk of malignancy index as risk assessment tools in the decision for referral to an oncology center in patients with an ovarian mass: a cost-effectiveness analysis from a Dutch health care perspective.

International journal of gynecological cancer : official journal of the International Gynecological Cancer Society·2026
Same author

Local immunotherapy in the neoadjuvant treatment of cancer: optimizing efficacy while limiting toxicity?

Journal for immunotherapy of cancer·2026
Same author

The contribution of rare germline variants to the immune landscape of breast cancer.

Genome medicine·2026
Same author

Recommendations for Pathologist-Led Deployment of Artificial Intelligence Tools as Laboratory-Developed Tests.

Laboratory investigation; a journal of technical methods and pathology·2026
Same author

Transcriptome-Based Classification of Resected Pancreatic Ductal Adenocarcinoma Enhances Prognostic Modelling Accuracy of Overall Survival Following Adjuvant Treatment.

International journal of cancer·2026

相关实验视频

Updated: Jan 11, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.3K

基于深度学习的算法对卵巢癌基因型鉴定在独立数据集中的性能评估.

Hein S Zelisse1, Maryam Asadi-Aghbolaghi2, Hossein Farahani2

  • 1Department of Pathology, Cancer Center Amsterdam, Amsterdam Reproduction and Development research institute, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands.

The American journal of surgical pathology
|November 18, 2025
PubMed
概括
此摘要是机器生成的。

基于富里埃的对抗域适应 (AIDA) 模型显示了对分类上皮卵巢癌基因型的承诺,达到79.7%的准确性. 进一步改进可以提高临床环境中的诊断准确性.

关键词:
对抗式基于四项的域调整 (AIDA)人工智能的人工智能是人工智能.深度学习算法深度学习算法上皮卵巢癌 卵巢癌 卵巢癌基因型 基因型 基因型

更多相关视频

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

4.4K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

相关实验视频

Last Updated: Jan 11, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.3K
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

4.4K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

科学领域:

  • 在瘤学瘤学.
  • 病理学 病理学 病理学
  • 人工智能的人工智能

背景情况:

  • 在上皮卵巢癌中,组型分类对于治疗至关重要,但由于机构间的幻灯片变化,它面临着挑战.
  • 需要域调整技术来解决来自不同来源的数据的变化.

研究的目的:

  • 评估对抗性富里埃基域适应 (AIDA) 模型在使用独立队列对五种主要卵巢癌基因型进行分类时的性能.
  • 评估AIDA模型与额外的幻灯片重新训练对分类准确性的影响.

主要方法:

  • 一个回顾性研究应用了AIDA深度学习模型,在温哥华总医院的数据上进行训练,对阿姆斯特丹大学医学中心的独立队列进行了回顾性研究.
  • 基因型预测是使用15个模型的多数投票进行的,并使用额外的幻灯片对错误分类的病例进行重新训练.
  • 用单片和多数投票方法评估分类准确性.

主要成果:

  • 艾达模型在透明细胞 (CCC),子宫内膜 (EC),高度血清 (HGSC),低度血清 (LGSC) 和粘膜性 (MC) 卵巢癌亚型中实现了79.7%的整体平衡精度.
  • 对CCC (90.9%) 和LGSC (89.8%) 观察到的精度最高,而EC (62.4%) 显示最低.
  • 使用额外的幻灯片进行重新训练,使平衡精度提高到85.8% (单幻灯片) 和82.6% (多数投票).

结论:

  • 艾达模型证明了在上皮卵巢癌中准确地分类组织型的潜力,解决了域转移的挑战.
  • 需要进一步改进模型,以改善困难病例的性能,从而可能提高临床诊断的准确性.