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

NMR insights into the role of urea in cellulose dissolution: A stoichiometric study of cellobiose in NaOH/urea aqueous solution.

Magnetic resonance letters·2026
Same author

Multi-Omics Profiling Reveals Immunomodulatory and Pro-Regenerative Effects of a Graphene Oxide-Collagen Scaffold in Massive Rotator Cuff Tears.

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

Evolving classifiers with background suppression transformer for open-set long-tailed class-incremental remote sensing scene classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Synthesis, Antibacterial Activity, and Mechanism of C-6 Aminated β-Carboline Derivatives Against MRSA.

Antibiotics (Basel, Switzerland)·2026
Same author

Synthesis of β-Carboline-Based Dimers and Hybrids and Anti-Methicillin-Resistant Staphylococcus aureus Properties by Targeting FtsZ.

ChemMedChem·2026
Same author

Multiobjective Simulated Annealing-Based Stopwords Substitution for Rubbish Text Attack.

IEEE transactions on neural networks and learning systems·2026

相关实验视频

Updated: Jun 6, 2025

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

42.8K

深度特征的多尺度区域选择网络,用于全场乳房镜分类.

Luhao Sun1, Bowen Han2, Wenzong Jiang3

  • 1Breast Cancer Center, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan 250117, China.

Medical image analysis
|November 30, 2024
PubMed
概括
此摘要是机器生成的。

一个新的深度多尺度区域选择网络 (MRSN) 将乳房图分类为没有兴趣区域 (ROI) 标注的乳房图. 这种方法有效地识别瘤,改善早期发现乳腺癌并降低诊断成本.

关键词:
乳腺癌 乳腺癌 乳腺癌早期诊断 早期诊断 早期诊断全场性乳房扫描全场性乳房扫描地区选择区域选择

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

470
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

6.7K

相关实验视频

Last Updated: Jun 6, 2025

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

42.8K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

470
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

6.7K

科学领域:

  • 医疗成像医学成像
  • 计算机辅助诊断 (CAD) 是一种计算机辅助诊断.
  • 深度学习 (Deep Learning) 是一种深度学习.

背景情况:

  • 早期发现乳腺癌显著降低了死亡率,而乳房影像是主要的查工具.
  • 目前用于乳房镜分类的深卷积神经网络 (CNN) 模型通常需要感兴趣区域 (ROI) 或细分注释,这些注释是昂贵且难以获得的.
  • 现有的绕过ROI依赖的方法增加了计算负载和功能冗余.

研究的目的:

  • 提出一个全新的深度多尺度区域选择网络 (MRSN),用于端到端对全场乳房图像进行分类.
  • 为了消除对乳房镜分类中的ROI或细分注释的需求.
  • 提高乳腺癌计算机辅助诊断系统的效率和准确性.

主要方法:

  • 开发了一个深度的多级区域选择网络 (MRSN) 用于特征提取和分类.
  • MRSN过器具有信息特征,只保留相关的瘤区域特征,灵感来自多个例子学习.
  • 该网络评分区域以确定瘤位置,并选择高得分区域作为图像特征表示,用于集中分析.

主要成果:

  • 拟议的MRSN有效地分类全场造乳镜图像,而不需要ROI或细分数据.
  • 通过专注于关键瘤区域,MRSN实现了与基于补丁的分类器可比的性能.
  • 公共和私人数据集的实验结果表明MRSN的最新性能.

结论:

  • 在计算机辅助诊断中,MRSN为自动化乳腺扫描分类提供了具有成本效益和高效的解决方案.
  • 这种方法显著降低了注释负担,促进了深度学习在乳腺癌查中的更广泛采用.
  • 在不依赖于详细的特定区域注释的情况下,MRSN通过实现准确的全场乳房学分类来推进该领域.