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

Gramado consensus on imaging evaluation of the response to neoadjuvant systemic therapy for breast cancer.

Radiologia brasileira·2026
Same author

Childhood maltreatment associated with psychological stress in head and neck cancer patients: a cross-sectional study.

Psychology, health & medicine·2026
Same author

Periocular basal cell carcinoma worldwide distribution - a systematic review.

Orbit (Amsterdam, Netherlands)·2026
Same author

Structural Equation Modeling of Genetic and Residual Covariance Matrices for Multiple-Trait Evaluation in Beef Cattle.

Animals : an open access journal from MDPI·2026
Same author

Challenges and opportunities: computational biology and the future of agriculture.

Bioinformatics advances·2026
Same author

Predicting kidney graft survival with a machine learning model based on for-cause biopsy transcriptomics.

Scientific reports·2026

相关实验视频

Updated: Sep 8, 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

43.0K

通过人工智能提高乳房密度评估

Naila Camila da Rocha1,2, Abner Macola Pacheco Barbosa3,4, Yaron Oliveira Schnr4

  • 1University of Wisconsin-Madison, 1675 Observatory Dr, Madison, WI, 53706, USA. ndarocha@wisc.edu.

Journal of imaging informatics in medicine
|September 5, 2025
PubMed
概括

这项研究引入了一个可访问的,开源的AI工具,用于在乳房影像中进行一致的乳腺密度分类,从而改善早期乳腺癌检测. 人工智能模型具有很高的准确性,有助于放射科医生对乳腺密度进行客观评估.

关键词:
乳腺癌乳腺密度计算机辅助诊断卷积神经网络乳房检查

更多相关视频

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.6K
Intraductal Delivery and X-ray Visualization of Ethanol-Based Ablative Solution for Prevention and Local Treatment of Breast Cancer in Mouse Models
13:43

Intraductal Delivery and X-ray Visualization of Ethanol-Based Ablative Solution for Prevention and Local Treatment of Breast Cancer in Mouse Models

Published on: April 1, 2022

4.6K

相关实验视频

Last Updated: Sep 8, 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

43.0K
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.6K
Intraductal Delivery and X-ray Visualization of Ethanol-Based Ablative Solution for Prevention and Local Treatment of Breast Cancer in Mouse Models
13:43

Intraductal Delivery and X-ray Visualization of Ethanol-Based Ablative Solution for Prevention and Local Treatment of Breast Cancer in Mouse Models

Published on: April 1, 2022

4.6K

科学领域:

  • 医疗成像中的人工智能
  • 医疗保健中的计算机视觉
  • 放射学和诊断成像

背景情况:

  • 乳腺癌仍然是全球女性癌症死亡的主要原因.
  • 乳房扫描对于早期检测至关重要, 乳房密度是一个关键因素.
  • 目前的乳腺密度评估 (BI-RADS) 是主观的,有所不同,需要客观的工具.

研究的目的:

  • 开发和验证一个开源的,人工智能驱动的计算机视觉方法,用于客观的乳腺密度分类.
  • 创建一个可访问的,低成本的解决方案,用于一致的乳腺密度评估,特别是在资源有限的环境中.
  • 通过改善乳房图解来提高早期乳腺癌检测.

主要方法:

  • 开发了一个与极端学习机器 (ELM) 层集成的定制卷积神经网络 (CD-CNN).
  • 该模型在由BI-RADS密度 (A-D) 分类的10,371张全场数字乳房图像的回顾性数据集上进行了训练和测试.
  • 使用准确度,灵敏度,特异性和加权卡帕,包括对迷你MIAS数据集的验证来评估性能.

主要成果:

  • 拟议的人工智能模型在初级数据集上实现了高性能:95.4%的准确性,98.0%的特异性和92.5%的灵敏性.
  • 在自动分类和专家共识之间观察到很强的一致性 (加权卡帕=0. 90).
  • 在独立的迷你MIAS数据集上获得了可比的结果,证明了稳定性和通用性.

结论:

  • 开发的开源AI方法提供了一种一致且准确的乳房密度评估方法.
  • 这种工具有潜力显著支持早期发现乳腺癌的努力,特别是在服务不足的医疗环境中.
  • 通过CD-CNN和ELM的整合,可以实现自动化乳房分析,从而提高诊断的一致性.