Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Classification of Illness

Classification of Illness

The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...

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

An attention-infused deep convolutional paradigm for multi-label classification of thoracic pathologies in chest radiographs.

Scientific reports·2026

Same author

Single-Cell Analysis of Preeclamptic Cord Blood Mononuclear Cells Revealed Activation of Heme-Associated Signalling Pathways.

Journal of cellular and molecular medicine·2026

Same author

Rethinking DeepVariant: Efficient Neural Architectures for Intelligent Variant Calling.

International journal of molecular sciences·2026

Same author

Extracellular Vesicles from iPSC-Derived Glial Progenitor Cells Prevent Glutamate-Induced Excitotoxicity by Stabilising Calcium Oscillations and Mitochondrial Depolarisation.

Cells·2025

Same author

Artificial Intelligence Tools for Supporting Histopathologic and Molecular Characterization of Gynecological Cancers: A Review.

Journal of clinical medicine·2025

Same author

Computer Vision-Assisted Spatial Analysis of Mitoses and Vasculature in Lung Cancer.

Journal of clinical medicine·2025

Search research articles

相关实验视频

Updated: Jan 13, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

临床意识学习:普通损失改善了医疗图像分类器.

Arsenii Litvinov¹, Egor Ushakov¹, Sofia Senotrusova¹

¹Trusted AI Research Center, RAS, 109004 Moscow, Russia.

Journal of clinical medicine

|January 10, 2026

概括

整合顺序意识损失功能显著提高了乳房成像报告和数据系统 (BI-RADS) 乳房影像的分类准确性. 这种方法更好地反映了错误分类的临床严重性,提高了早期乳腺癌检测的可靠性.

关键词:

乳腺癌查乳腺癌查乳腺成像风险分类的风险分类深度学习是一种深度学习.损失功能损失功能损失功能按顺序分类进行分类.

更多相关视频

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

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

Published on: November 30, 2022

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

相关实验视频

Last Updated: Jan 13, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

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

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

Published on: November 30, 2022

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

科学领域:

医学成像人工智能医学成像人工智能
机器学习用于医疗保健
乳腺癌查乳腺癌查

背景情况:

乳腺成像报告和数据系统 (BI-RADS) 对于乳腺癌检测至关重要.
当前的模型通常将BI-RADS视为名义,忽视其顺序性和错误分类的临床影响.
模型优化和临床严重性之间的不匹配是一个未被充分探索的问题.

研究的目的:

评估顺序意识损失函数是否可以提高BI-RADS分类的性能.
在受控条件下,将顺序损失与标准交叉进行比较.
分析数据集和标签平衡对业绩的影响.

主要方法:

系统评估顺序意识损失函数 (例如,地球移动器距离) 与交叉.
在具有固定的架构的多个数据集中统一的培训管道.
数据集和标签平衡策略的分析.
以接收器运行特征曲线 (AUROC) 下面面积和宏观F1分数衡量的性能.

主要成果:

在训练期间均衡采样显著提高了性能.
顺位损失函数的表现始终优于传统的交叉.
在减少严重错误分类方面特别注意到改善,提高了临床相关性.
地球移动距离 (EMD) 展示了卓越的性能.

结论:

将学习目标与顺序 BI-RADS 结构对齐,大大提高了分类准确性.
顺序意识方法提高AI模型的稳定性和乳腺癌查中的临床相关性.
强调了医疗AI中损失函数设计,规范化和数据平衡的重要性.