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

Ranks01:02

Ranks

290
Unlike parametric methods, nonparametric statistics are ideal for nominal and ordinal data, requiring fewer assumptions about the population's nature or distribution. This makes nonparametric methods easier to apply and interpret, as they do not depend on parameters like mean or standard deviation. One common approach in nonparametric analysis is to sort data according to a specific criterion. For instance, we might arrange weather data from hottest to coldest days in a month or rank cities...
290

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

Assessing Preparedness and Preventive Measures for Managing Food Allergy and Anaphylaxis in Primary Schools of Rabigh, Saudi Arabia.

International journal of environmental research and public health·2025
Same author

Fast Anomaly Detection for Vision-Based Industrial Inspection Using Cascades of Null Subspace PCA Detectors.

Sensors (Basel, Switzerland)·2025
Same author

Exploiting the features of deep residual network with SVM classifier for human posture recognition.

PloS one·2024
Same author

A novel user clustering and efficient resource allocation in non-orthogonal mutliple access for IoT networks.

PloS one·2024
Same author

Using multi-label ensemble CNN classifiers to mitigate labelling inconsistencies in patch-level Gleason grading.

PloS one·2024
Same author

DeepVision: Enhanced Drone Detection and Recognition in Visible Imagery through Deep Learning Networks.

Sensors (Basel, Switzerland)·2023

相关实验视频

Updated: Sep 18, 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

6.9K

提高多标签胸部X射线分类使用改进的排名损失.

Muhammad Shehzad Hanif1, Muhammad Bilal1, Abdullah H Alsaggaf2

  • 1Department of Electrical and Computer Engineering, King Abdulaziz University, Jeddah 21589, Saudi Arabia.

Bioengineering (Basel, Switzerland)
|June 26, 2025
PubMed
概括

这项研究引入了一个新的焦点ZLPR损失函数,以改善胸部X射线图像中胸部疾病的多标签分类,有效处理类失衡并提高诊断准确性.

关键词:
胸部X射线 胸部X射线 胸部X射线卷积神经网络是一种卷积神经网络.通过排名来学习学习.多个标签的分类.

更多相关视频

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

683
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

相关实验视频

Last Updated: Sep 18, 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

6.9K
Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

683
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

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算机视觉 计算机视觉

背景情况:

  • 对胸部疾病的胸部X射线 (CXR) 分析,由于同时出现的病理,提出了多标签分类的挑战.
  • 在CXR数据集中的类失衡,其中一些疾病是罕见的,使准确的模型训练复杂化.
  • 从头开始训练深度学习模型需要大量的数据集,通常无法用于特定的医疗任务.

研究的目的:

  • 开发一种有效的方法,在CXR图像中对胸部疾病进行多标签分类.
  • 为应对CXR数据集中类不平衡的挑战.
  • 提高深度学习模型在胸部疾病检测中的性能.

主要方法:

  • 通过对NIH胸部X射线14数据集上预训练的DenseNet121模型进行微调来利用转移学习.
  • 提出了一种新的基于等级的损失函数,焦点ZLPR (FZLPR),灵感来自焦点损失,以解决阶级不平衡.
  • 在FZLPR中加入了一个温度参数,以强调难以分类的罕见疾病病例.

主要成果:

  • 拟议的FZLPR损失函数超过了标准的损失函数,如二进制交叉 (BCE) 和焦点损失.
  • 用FZLPR训练的模型在NIH胸部X射线14数据集上表现出卓越的表现.
  • 通过使用FZLPR训练模型的测试时间增强,获得了80.96%的竞争平均AUC.

结论:

  • 焦点ZLPR损失函数是改善CXR图像中胸部疾病多标签分类的有希望的方法.
  • 该方法有效地处理了阶级不平衡,从而更准确地检测出常见和罕见疾病.
  • 开发的模型表现出竞争力的性能,在临床环境中提供了增强诊断支持的潜力.