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

Artificial intelligence and automation in enzyme engineering: evolution, advances, and future perspectives.

Bioresources and bioprocessing·2026
Same author

High-speed optical tracking and augmented reality platform for image-guided interventions.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

Anthocyanin-based colorimetric sensor for aflatoxin B1 (AFB1) detection in wheat: Performance optimization via near-infrared (NIR) spectral characterization and structurally improved recurrent neural network (RNN).

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026
Same author

Microvascular ultrasound imaging of the neonatal brain: a scoping review.

European journal of pediatrics·2026
Same author

Nuclear factor IX promotes endometriosis progression through transcriptional activation of tetraspanin-2.

Journal of molecular medicine (Berlin, Germany)·2026
Same author

Enhancing 1p/19q Classification in Brain Gliomas Using IDH Status: A Deep Learning Study.

AJNR. American journal of neuroradiology·2026

相关实验视频

Updated: Jun 30, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K

使用中心注意力卷积神经网络对不平衡数据进行肺结节假阳性减少.

Kexin Hao1, Annan Cai1, XingYu Feng1

  • 1College of Software, Nankai University.

Proceedings of SPIE--the International Society for Optical Engineering
|March 15, 2024
PubMed
概括

这项研究引入了一种新的深度学习模型,即对不平衡数据的中心注意力卷积神经网络 (CACNNID),通过减少错误阳性来改善肺结节检测. 在CT扫描中,CACNNID模型有效地区分了实际的结节和相似的假阳性.

关键词:
图像 图像 图像 图像 图像肺结节检测 肺结节检测关注注意力注意力注意力注意力假阳性减值是一个错误的减值.不平衡的学习学习.

更多相关视频

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

1.8K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.4K

相关实验视频

Last Updated: Jun 30, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

1.8K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.4K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算机辅助诊断 计算机辅助诊断

背景情况:

  • 计算机辅助检测 (CAD) 系统对于早期肺结节诊断至关重要.
  • 减少虚假阳性是肺结节检测的一个关键挑战,因为与良性发现的视觉相似性.
  • 不平衡的学习数据集给准确的结节识别带来了困难.

研究的目的:

  • 开发一种深度学习模型,以有效地减少肺结节检测的假阳性.
  • 为了应对肺结节分类中不平衡数据集的挑战.
  • 提高计算机辅助肺结节检测系统的准确性.

主要方法:

  • 提出了一个关于不平衡数据的中心注意力卷积神经网络 (CACNNID).
  • 包括密度分布,数据增强,噪声降低和均衡采样在内的技术被用来处理不平衡的数据.
  • 该模型的设计是专注于中央信息,并最大限度地减少不相关的边缘特征,以进行歧视性特征提取.

主要成果:

  • 在Luna16数据集上,CACNNID模型实现了92.64%的平均灵敏度.
  • 该模型的特异性为98.71%,准确率为98.69%.
  • 曲线下的面积 (AUC) 为95.67%,表明在区分结节方面表现强.

结论:

  • 拟议的CACNNID模型在减少肺结节检测虚假阳性结果方面表现令人满意.
  • 注意力机制有效地提取分辨特征,提高分类准确性.
  • 用于解决数据不平衡的方法有助于建立更强大,更可靠的检测系统.