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

Association of Salivary Micro Ribonucleic Acid Levels With the Severity of Severe Acute Respiratory Syndrome Coronavirus 2 Infection in Children.

Pediatric discovery·2026
Same author

Integrating natural language processing into radiation oncology: a practical guide to transformer architecture and large language models.

BJR artificial intelligence·2026
Same author

Multi-institutional Comparison of Novel O-ring Linac Cone Beam Computed Tomography with Fan Beam Computed Tomography.

Journal of medical physics·2026
Same author

Unraveling salt-responsive genes in Suaeda salsa through genomic and transcriptomic profiling across salinity gradients.

BMC genomics·2026
Same author

The role of myeloid-derived suppressor cells in Sjögren's disease.

Autoimmunity reviews·2026
Same author

Authors' Reply: Toward Retrieval-Grounded Evaluation for Conversational Large Language Model-Based Risk Assessment.

JMIR AI·2026
Same journal

Correction to "On the shape of the radiation survival curve in tumor spheroids: The role of oxygen heterogeneity".

Medical physics·2026
Same journal

Multi-view constrained semi-supervised vertebra detection for 3D ultrasound spine volume.

Medical physics·2026
Same journal

Accuracy of quantitative <sup>177</sup>Lu SPECT/CT imaging: A systematic review.

Medical physics·2026
Same journal

Physics-constrained dual-domain network for CBCT reconstruction from orthogonal X-rays in gynecologic radiotherapy.

Medical physics·2026
Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026
Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026
查看所有相关文章

相关实验视频

Updated: May 10, 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

2.6K

通过整体损失函数优化提高CT图像分割精度.

Chengyin Li1,2, Rafi Ibn Sultan1, Hassan Bagher-Ebadian2,3,4,5

  • 1Department of Computer Science, Wayne State University, Detroit, Michigan, USA.

Medical physics
|April 25, 2025
PubMed
概括
此摘要是机器生成的。

在CT医疗图像细分中优化整体损失函数显著提高了准确性. 有权重组合的可学习组合可以提高对单个或线性组合损失函数的细分性能.

关键词:
CT图像细分的部分化CT图像细分组合学习组合学习损失功能的优化优化损失功能的优化.

更多相关视频

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

42.4K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.3K

相关实验视频

Last Updated: May 10, 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

2.6K
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

42.4K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.3K

科学领域:

  • 医学图像分析 医学图像分析
  • 深度学习 (Deep Learning) 是一种深度学习.
  • 计算成像技术的成像

背景情况:

  • 深度神经网络训练CT医疗图像分割对损失功能选择敏感.
  • 个别损失函数 (交叉,子,边界,TopK) 有限制和偏差.

研究的目的:

  • 通过优化集合损失函数来提高细分精度.
  • 为了减轻单损失函数及其线性组合固有的偏差和局限性.

主要方法:

  • 通过线性组合和模型级合集评估集成损失函数 (交叉,子,边界,TopK).
  • 在机构和公共CT数据集上使用了Attention U-Net (AttUNet) 和SwinUNETR架构.
  • 采用静态平均和可学习的动态权重用于整体策略.

主要成果:

  • 与非集体方法相比,集体方法使子相似系数 (DSC) 的得分提高了2%-7%.
  • 在豪斯多夫距离 (HD) 和平均表面距离 (ASD) 中实现了显著的减少,例如,在直肠细分方面减少了19.1%的HD.
  • 具有优化权重的可学习合奏产生了更细致的细分细节,并超过了静态合奏.

结论:

  • 带有优化权重的组合模型有效地提高了医疗图像细分的准确性.
  • 这种方法显示了推进自动化医疗图像分析应用的潜力.