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

Leaf adhesion and insecticidal efficacy of a starch-chitosan based dual-network hydrogel pesticide delivery system.

International journal of biological macromolecules·2026
Same author

Ancient mitogenomes reveal the genetic relationship among extinct and extant water buffaloes.

iScience·2026
Same author

RPL27 Promotes Gastric Cancer Progression by Enhancing Oxidative Phosphorylation Via FMC1.

Cell biology international·2026
Same author

Exploring a tolerable and effective dosage of omega-3 fatty acids as a supplement in enterally fed patients with severe pneumonia: A pilot study.

Asia Pacific journal of clinical nutrition·2026
Same author

Monolithically integrated photon-mapping infrared imager.

Nature communications·2026
Same author

Longitudinal Plasma Proteomics Reveals an Immuno-thrombotic Signature That Predicts Radiation Pneumonitis in Lung Cancer.

International journal of radiation oncology, biology, physics·2026

相关实验视频

Updated: Jun 17, 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

SFPL:用于不平衡医疗图像分类的样本特定细粒度原型学习.

Yongbei Zhu1, Shuo Wang1, He Yu2

  • 1Key Laboratory of Big Data-Based Precision Medicine, Ministry of Industry and Information Technology, School of Engineering Medicine, Beihang University, China; CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, China.

Medical image analysis
|August 6, 2024
PubMed
概括
此摘要是机器生成的。

本研究引入了样本特定的细粒度原型学习 (SFPL),以解决医学成像中的不平衡分类问题. 通过专注于单个样本特征,SFPL提高了模型的准确性,优于现有的方法.

关键词:
相反的学习学习.一个细粒度原型.不平衡的分类是不平衡的一个特定样本的分类器.

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K

相关实验视频

Last Updated: Jun 17, 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
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K

科学领域:

  • 医学图像分析 医学图像分析
  • 机器学习 机器学习
  • 计算机视觉 计算机视觉

背景情况:

  • 不平衡的分类在医学图像分析中带来了重大挑战.
  • 现有的方法往往忽略了类内异质性和个体样本变异.
  • 解决这些局限性对于提高诊断准确性至关重要.

研究的目的:

  • 提出一种新的样本特定细粒度原型学习 (SFPL) 方法.
  • 通过捕获单个样本特征来增强分类模型.
  • 为了提高不平衡医疗图像数据集的性能.

主要方法:

  • SFPL学习了使用多个原型的多数类的细粒度表示.
  • 原型通过混合物权重策略和统一损失函数进行更新.
  • 一个选择性注意力聚合模块将原型与样本特定的等位数分类器联系起来.

主要成果:

  • 与最先进的方法相比,SFPL在三个任务中表现出更高的性能.
  • 随着不平衡比率的提高和培训数据的减少,绩效增长有所增加.
  • 该方法有效地处理类内异质性和样本个性.

结论:

  • 在医学成像中,SFPL为不平衡的分类提供了一个强大的解决方案.
  • 该方法提高了模型适应单个样本特征的适应性.
  • 在医疗图像分析应用中,SFPL具有显著的潜力.