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

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

Transcutaneous Auricular Vagus Nerve Stimulation as a Potential Novel Treatment for Preoperative Anxiety: A Narrative Literature Review.

Journal of perianesthesia nursing : official journal of the American Society of PeriAnesthesia Nurses·2026

Same author

Primary aldosteronism-induced hypokalemic rhabdomyolysis syndrome: a case report and literature review.

Frontiers in medicine·2026

Same author

The central role of radiotherapy in remodeling the tumor immune microenvironment: mechanisms and therapeutic implications.

Frontiers in cell and developmental biology·2026

Same author

Diagnostic value of cystatin C in acute kidney injury among patients with sepsis: a systematic review and meta-analysis.

Frontiers in medicine·2026

Same author

Characterization of oxidative status in maize protoplasts under temperature and saline-alkali stresses.

BMC plant biology·2026

Same author

RNA interference targeting BxNDUFA2 impairs mitochondrial function and triggers oxidative stress to control pine wood nematode (Bursaphelenchus xylophilus).

Pesticide biochemistry and physiology·2026

Search research articles

相关实验视频

Updated: Jul 5, 2025

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

当地对比学习用于医疗图像识别

Syed A Rizvi¹, Ruixiang Tang², Xiaoqian Jiang³

¹Yale University, New Haven, CT.

AMIA ... Annual Symposium proceedings. AMIA Symposium

|January 15, 2024

概括

当地区域对比学习 (LRCLR) 通过识别关键区域并将其与放射学报告联系起来,改善了医疗图像分析. 这种深度学习方法可以提高诊断准确度,而不需要专家标签.

科学领域:

放射学放射学是一门学科.
医疗成像医学成像
人工智能的人工智能

背景情况:

深度学习 (DL) 方法越来越多地用于放射图像分析.
专家标记的放射学数据有很高的需求.
自主监督框架使用放射学报告,但与微妙的病理学差异作斗争,缺乏区域文本解释性.

研究的目的:

引入地方区对比学习 (LRCLR),一个新的微调框架.
为了使DL模型能够识别重要的图像区域及其与文本的关系.
提高DL模型在医学图像分析中的可解释性和性能.

主要方法:

开发了LRCLR,一个灵活的微调框架.
集成层用于显著的图像区域选择.
集成的跨模式交互用于图像-文本相关性.

主要成果:

在胸部X射线中,LRCLR有效地识别了显著的局部区域.
该框架提供了图像区域和放射文本之间的有意义的解释.
在多个胸部X射线医学发现上,证明了零射击性能的提高.

结论:

更多相关视频

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

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

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

Published on: April 14, 2023

相关实验视频

Last Updated: Jul 5, 2025

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

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

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

Published on: April 14, 2023

在医疗图像分析方面,LRCLR提供了一种灵活和可解释的方法.
该方法通过将图像和文本数据相结合,提高了自我监督学习的实用性.
对于改善放射学诊断能力,LRCLR显示出有前途的迹象.