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

SAMP-Net: a medical image segmentation network with split attention and multi-layer perceptron.

Medical & biological engineering & computing·2025
Same author

Deep Matrix Factorization Based on Convolutional Neural Networks for Image Inpainting.

Entropy (Basel, Switzerland)·2023
Same journal

Literature Reviews After AI.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

Illustration of transfer learning from breast cancer detection to risk prediction: adaptation to local data and local objectives.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

RadGazeGen: radiomics and gaze-guided chest X-ray generation using diffusion models.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

DDARes-U<sup>2</sup>Net: a dual-decoder adversarial residual U<sup>2</sup>Net algorithm for segmentation of COVID-19 pneumonia lesions.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

High-speed optical tracking and augmented reality platform for image-guided interventions.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

Transplant-ready? Evaluating AI lung segmentation models in candidates with severe lung disease.

Journal of medical imaging (Bellingham, Wash.)·2026
查看所有相关文章

相关实验视频

Updated: Jan 6, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.4K

使用位置和时间对比信息进行心脏组织细分的Scribble监督方法.

Xiaoxuan Ma1, Yingao Du1, Kuncheng Lian1

  • 1Beijing University of Civil Engineering and Architecture, School of Intelligence Science and Technology, Beijing, China.

Journal of medical imaging (Bellingham, Wash.)
|November 25, 2025
PubMed
概括
此摘要是机器生成的。

这项研究引入了Scribble Position and Temporal Contrast Learning (SPTCL) 用于医疗图像细分,减少了对广泛注释的需求. SPTCL提高了细分任务的准确性和效率,使其适合临床使用.

关键词:
相反的学习学习学习.医疗图像细分 医疗图像细分涂-监督学习学习.监管能力较弱的监管机构.

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

719
Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection
06:57

Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection

Published on: September 22, 2023

1.4K

相关实验视频

Last Updated: Jan 6, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.4K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

719
Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection
06:57

Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection

Published on: September 22, 2023

1.4K

科学领域:

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

背景情况:

  • 精确的像素级别细分对于医学诊断和治疗规划至关重要.
  • 完全监督的方法需要大量高质量的注释,这些注释往往稀缺且昂贵.
  • 弱监督的学习旨在减少对精确注释的依赖.

研究的目的:

  • 开发一种创新的细分方法,将对比性学习与弱监督相结合.
  • 为了减少在医学图像细分中对精确注释的依赖.
  • 使用有限的注释数据来提高细分性能.

主要方法:

  • 拟议的写位置和时间对比学习 (SPTCL) 方法.
  • 在3D医学卷中利用空间连续性和跨心脏阶段的时间相似性进行对比学习.
  • 使用预先训练的编码器,在弱监督的细分网络上微调,使用双分支解码器.
  • 合并预测以生成伪标签,用于代训练,带有涂注释.

主要成果:

  • 在ACDC数据集上获得了90.5%的子系数.
  • 超越现有模型的性能,比基线改进2.5%,比最新模型改进1.7%.
  • 培训时间缩短约33%.

结论:

  • SPTCL有效地解决了医学图像细分中的注释短缺问题.
  • 该方法显示了实际临床部署的强大潜力.
  • 结合了对比的学习与弱监督,以实现强大的特征表示和细分.