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

Human-in-the-loop validation of a sequential multi-LLM medical education pipeline.

NPJ digital medicine·2026
Same author

Feasibility and psychometric evaluation of large language model-generated radiology learning materials for board examination preparation: a prospective pilot study.

BMC medical education·2026
Same author

Deep learning-based assessment of coronary artery disease using curved-multiplanar reconstruction: comprehensive evaluation of stenosis, calcification, and plaque.

Frontiers in artificial intelligence·2026
Same author

Generative AI for developing foundation models in radiology and imaging: engineering perspectives.

Biomedical engineering letters·2026
Same author

Endoscopic Diagnosis of Eosinophilic Esophagitis Using a Multi-Task U-Net: A Pilot Study.

Yonsei medical journal·2026
Same author

Generating Lung Ventilation Images with Virtual Non-contrast Images from Dual-Energy CT Scans Using Multi-task Conditional Generative Adversarial Networks.

Journal of imaging informatics in medicine·2026

相关实验视频

Updated: Jun 15, 2025

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

具有强大的区分器的生成对抗网络,通过多任务学习来实现低剂量CT Denoising.

Sunggu Kyung, Jongjun Won, Seongyong Pak

    IEEE transactions on medical imaging
    |August 26, 2024
    PubMed
    概括

    这项研究引入了一种新的生成对抗网络 (GAN) 用于低剂量计算机断层扫描 (LDCT) 测试. 改进后的模型通过减少噪音,同时保持细节来提高图像质量和诊断准确性.

    科学领域:

    • 医疗成像医学成像
    • 人工智能的人工智能
    • 放射学 放射学是一门学科.

    背景情况:

    • 在计算机断层扫描 (CT) 中降低辐射剂量对于最小化二次癌症风险至关重要.
    • 低剂量CT (LDCT) 图像往往会增加噪音,这可能会阻碍诊断的准确性.
    • 现有的深度学习方法在视觉一致性,性能指标和稳定性方面面临挑战.

    研究的目的:

    • 开发一个先进的深度学习模型,以有效地消除LDCT的形象.
    • 解决当前方法的局限性,包括视觉差异和性能变化.
    • 为了提高LDCT图像的稳定性和诊断实用性.

    主要方法:

    • 一个新的生成对抗网络 (GAN),将多任务学习纳入其区分器.
    • 引入恢复一致性 (RC) 和非差异抑制 (NDS) 以提高分辨器能力.
    • 剩余快里叶变换与卷积 (Res-FFT-Conv) 块的集成,以增强特征表示.

    主要成果:

    • 拟议的GAN在所有定量和定性评估中都表现出优异的染性能.
    • 区分器中的多任务学习为生成器的拒绝提供了更有效的反.
    • 该模型在放射学家的视觉评分中,与最先进的否定技术相比,取得了更好的结果.

    更多相关视频

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    494
    Deep Learning-Based Segmentation of Cryo-Electron Tomograms
    10:25

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms

    Published on: November 11, 2022

    8.6K

    相关实验视频

    Last Updated: Jun 15, 2025

    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
    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    494
    Deep Learning-Based Segmentation of Cryo-Electron Tomograms
    10:25

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms

    Published on: November 11, 2022

    8.6K

    结论:

    • 具有多任务学习和专业块的新型GAN架构显著改善了LDCT的Denoising.
    • 拟议的监管机制提高了GAN培训和歧视者表现.
    • 这种方法为高质量的LDCT成像提供了有希望的解决方案,有助于准确诊断和减少辐射暴露.