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

Topiramate protects against neuroinflammation in response to traumatic brain injury via activating Sirt1 signaling.

Scientific reports·2026
Same author

A dirigent protein redirects extracellular terpenoid metabolism for defense against biotic challenges.

Nature communications·2025
Same author

Regulation of Glandular Size and Phytoalexin Biosynthesis by a Negative Feedback Loop in Cotton.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2024
Same author

A dirigent protein complex directs lignin polymerization and assembly of the root diffusion barrier.

Science (New York, N.Y.)·2023
Same author

Stereoelectronic Switches of Single-Molecule Junctions through Conformation-Modulated Intramolecular Coupling Approaches.

The journal of physical chemistry letters·2023
Same author

Single-cell RNA sequencing reveals a hierarchical transcriptional regulatory network of terpenoid biosynthesis in cotton secretory glandular cells.

Molecular plant·2023

相关实验视频

Updated: Jun 28, 2025

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

6.8K

乳腺瘤组织图像分类使用单任务超级学习与辅助网络.

Jiann-Shu Lee1, Wen-Kai Wu1

  • 1Department of Computer Science and Information Engineering, National University of Tainan, Tainan 700, Taiwan.

Cancers
|April 13, 2024
PubMed
概括

一个新的乳腺癌分类模型,单任务超学习与辅助网络 (STMLAN),提高了诊断的准确性. 这种先进的模型增强了各种病理图像的概括性,有助于早期发现乳腺癌和患者的生存.

科学领域:

  • 医疗成像医学成像
  • 计算病理学计算病理学
  • 在瘤学中使用人工智能

背景情况:

  • 乳腺癌仍然是全球癌症死亡的主要原因.
  • 准确的乳腺瘤类型的早期诊断对于改善患者存活率至关重要.
  • 现有的卷积神经网络 (CNN) 模型在各种乳腺病理图像特征的概括方面扎.

研究的目的:

  • 为乳腺病理图像引入一种新的分类模型STMLAN (单任务超级学习与辅助网络).
  • 提高乳腺癌图像分类模型的概括能力.
  • 提高乳腺病理学多重分类任务的准确性和特征可区分性.

主要方法:

  • 整合超级学习以提高概括性.
  • 使用辅助网络来改善病理图像的特征表示.
  • 开发单任务超级学习与辅助网络 (STMLAN) 模型.

主要成果:

  • 在具有挑战性的多重分类任务中,STMLAN模型实现了至少1.85%的精度改进.
  • 显示Silhouette分数增加了31.85%,表明更具歧视性的特征学习.
  • 展示了改善的概括能力,以对具有不同特征的乳腺病理图像进行分类.
关键词:
辅助网络 辅助网络是辅助网络的辅助网络.图像的分类图像的分类.医学图像 医学图像 医学图像单一任务的超级学习.

更多相关视频

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
08:32

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Published on: October 2, 2020

6.3K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.2K

相关实验视频

Last Updated: Jun 28, 2025

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

6.8K
Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
08:32

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Published on: October 2, 2020

6.3K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.2K

结论:

  • 与现有的方法相比,STMLAN模型在乳腺病理图像分类中提供了更高的性能.
  • 整合Meta Learning和辅助网络有效地解决了当前基于CNN的模型的概括限制.
  • 由于STMLAN能够学习更多的辨别特征,这对改善早期乳腺癌诊断和患者治疗结果具有显著的前景.