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

Improved the slow digestion property of maize starch using partially β-amylolysis.

Food chemistry·2014
Same author

Blend-modification of soy protein/lauric acid edible films using polysaccharides.

Food chemistry·2014
Same author

Structure and physicochemical properties of octenyl succinic esters of sugary maize soluble starch and waxy maize starch.

Food chemistry·2014
Same author

[Effects of left renal vein division on postoperative renal function during open repair of abdominal aortic aneurysm].

Zhonghua yi xue za zhi·2014
Same author

Association of four insulin resistance genes with type 2 diabetes mellitus and hypertension in the Chinese Han population.

Molecular biology reports·2014
Same author

Neuroprotective effect of pseudoginsenoside-f11 on a rat model of Parkinson's disease induced by 6-hydroxydopamine.

Evidence-based complementary and alternative medicine : eCAM·2014

相关实验视频

Updated: Jan 9, 2026

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

3.3K

在数据稀缺场景中改进超声波图像细分,使用自主监督学习与幻影数据预训练.

Bo Jiang, Keshi He, Hayoung Cho

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |December 3, 2025
    PubMed
    概括

    用BT-UNet进行自主监督学习,预先训练了幻影超声图像,在低数据场景中显著提高了医疗图像细分的准确性. 这种方法以最小的临床注释提高了性能.

    更多相关视频

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

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms

    Published on: November 11, 2022

    10.5K
    Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning
    08:41

    Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

    Published on: July 14, 2020

    9.0K

    相关实验视频

    Last Updated: Jan 9, 2026

    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

    3.3K
    Deep Learning-Based Segmentation of Cryo-Electron Tomograms
    10:25

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms

    Published on: November 11, 2022

    10.5K
    Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning
    08:41

    Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

    Published on: July 14, 2020

    9.0K

    科学领域:

    • 医学成像医学成像
    • 计算机视觉 计算机视觉 计算机视觉
    • 机器学习 机器学习

    背景情况:

    • 超声波图像细分至关重要,但受到有限的注释数据集的阻碍,特别是在临床环境中.
    • 现有的方法因数据稀缺而困难,影响诊断准确度.

    研究的目的:

    • 通过自主监督学习框架,在低数据条件下提高超声波图像细分性能.
    • 在对临床数据进行微调之前,对幻影超声数据进行预训练的有效性进行调查.

    主要方法:

    • 雇佣BT-UNet,一个自我监督的框架,将Barlow Twins (BT) 与UNet架构相结合.
    • 在未标记的肌肉骨幻影超声图像上预先训练的BT-UNet.
    • 在一小组注释的临床超声波图像上微调模型.

    主要成果:

    • BT-UNet获得了0.9311的Dice分数,5%的临床数据被标记,超过了标准UNet (0.9250).
    • 在1%的数据稀缺率下,BT-UNet保持了0.7114的子得分,而UNet则下降到0.2253.
    • 在极端数据稀缺的情况下,表现出显著的性能改善.

    结论:

    • 在虚拟数据集上进行自我监督的预训练有效地解决了医疗成像细分中的数据稀缺问题.
    • BT-UNet提供了一种有前途的解决方案,用于提高细分精度,并尽量减少临床注释.
    • 减少对临床应用中大型,昂贵的注释数据集的依赖.