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

Relation of High CHA₂DS₂-VASc Score With Contrast-Induced Nephropathy Following Percutaneous Coronary Intervention.

Cureus·2026
Same author

Prevalence and Phenotypic Correlations of GAD65 and ZnT8 Autoantibodies in Young-Onset Diabetes: A Pilot Study in a Tertiary Centre in Bangladesh.

Endocrinology, diabetes & metabolism·2026
Same author

Soft, Skin-Conformal Electronic Interfaces for Multimodal Biosignal Monitoring and Transcutaneous Stimulation.

ACS applied materials & interfaces·2026
Same author

Lower limb and feet wound image dataset.

Data in brief·2026
Same author

A Brief Overview of Antenatal Care Services at Two Primary Care Centers in Bangladesh.

Cureus·2026
Same author

Ultrasound-enabled refreshable electrochemical sensors for cardiac biomarker monitoring.

Biosensors & bioelectronics·2026

相关实验视频

Updated: Jan 11, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

727

使用局部窗口视觉变压器进行跨平台多种癌症组织病理学分类.

Md Darun Nayeem1, Nusrat Jahan Nisita1, Md Masudul Islam2

  • 1Bangladesh University of Business and Technology, Mirpur, Dhaka, Bangladesh.

Scientific reports
|November 19, 2025
PubMed
概括

CancerDet-Net使用人工智能准确地分类了9种癌症亚型,分为4种主要类型. 这种先进的深度学习模型通过可解释的AI提供实时临床使用,改善癌症诊断.

关键词:
癌症的诊断 癌症的诊断组织病理图像分类的分类.局部窗口稀疏的自我注意力多种癌症的检测检测.视觉变压器 视觉变压器在XAI,XAI就是XAI.

更多相关视频

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.9K
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

相关实验视频

Last Updated: Jan 11, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

727
Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.9K
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

科学领域:

  • 数字病理学数字病理学
  • 在瘤学中使用人工智能
  • 计算生物学 计算生物学

背景情况:

  • 准确的组织病理图像分类对于癌症诊断和治疗至关重要.
  • 当前的深度学习模型往往缺乏临床应用的概括性和透明度.
  • 现有的模型通常仅限于单一癌症分类.

研究的目的:

  • 开发一个统一的深度学习框架,CancerDet-Net,用于多种癌症的基因病理图像分类.
  • 为了提高模型的概括性,解释性和临床适用性.
  • 为了在分类各种癌症亚型时实现高精度.

主要方法:

  • 可分离的卷积层的集成,视觉变压器 (ViT) 块具有局部窗口稀疏的自我注意力.
  • 通过交叉尺度特征 (CSF) 融合结合的分层多尺度门式注意力机制 (HMSGA) 的应用.
  • 开发可解释的人工智能 (XAI) 可视化,以实现模型透明度.

主要成果:

  • 在四种主要癌症类型中,CancerDet-Net在分类9种组织病理学亚型时实现了98.51%的最高性能准确度.
  • 该模型在数据集中显示出强大的通用性.
  • 集成的XAI可视化为临床解释提供了透明度.

结论:

  • CancerDet-Net为数字病理学中的多种癌症分类提供了一个全面和统一的框架.
  • 该模型的高精度,可概括性和可解释性代表了显著的进步.
  • 通过网络和移动平台的部署准备有助于实时临床使用,增强AI驱动的癌症诊断.