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

相关实验视频

Updated: Jan 7, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

721

[形状感知跨模式域自适应细分模型]

Yusi Liu1,2,3, Liangce Qi1,2,3, Zhaoheng Diao1,2,3

  • 1School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, P. R. China.

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi
|December 25, 2025
PubMed
概括
此摘要是机器生成的。

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

Development and validation of machine learning models for early diagnosis of hemophagocytic lymphohistiocytosis in pediatric Epstein-Barr virus infection.

BMC medical informatics and decision making·2026
Same author

Targeted Protein Degradation of NUDT5 Dissociates Catalytic Inhibition from Protein Loss in 6-Thioguanine Response.

Nature communications·2026
Same author

Double vs. single autologous stem cell transplantation in patients with multiple myeloma and high-risk factors: A systematic review and meta-analysis.

Oncology letters·2026
Same author

MonoGID: geometry and illumination aware enhancement with distillation for self-supervised monocular endoscopic depth estimation.

BMC medical imaging·2026
Same author

[A reweighted graph matching-based algorithm for automatic extraction of corresponding landmarks in medical images].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2026
Same author

[Novel framework based on multi-stage random sampling and differentiable rendering for automated three-dimensional orientation estimation of skull base foramina].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2026
Same journal

[Advances in research on neuroelectrophysiological characteristics of post-stroke cognitive impairment based on quantitative electroencephalography and acupuncture interventions].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2026
Same journal

[Mechanisms and applications of magnesium ion-regulated stem cell functions in promoting tendon-bone interface healing].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2026
Same journal

[Applications and challenges of ultra-high molecular weight polyethylene fibers in minimally invasive medical devices].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2026
Same journal

[Research on auditory neurofeedback technology and its multi-disciplinary applications].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2026
Same journal

[Application and perspective of novel auditory intervention paradigms based on verbal and nonverbal stimuli for severe traumatic brain injury].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2026
Same journal

[Research progress on the neuromodulation targets in stroke rehabilitation].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2026
查看所有相关文章

这项研究引入了一种新的形状感知自适应加权 (SAWS) 模型,用于跨模式的医疗图像细分. 通过更好地感知目标区域和利用形状先验,SAWS提高了细分精度,提高了无监督域调整任务的概括性.

科学领域:

  • 医疗图像分析 医学图像分析
  • 计算机视觉 计算机视觉 计算机视觉
  • 人工智能的人工智能是人工智能.

背景情况:

  • 跨模式无监督域适应 (UDA) 由于未充分利用形状先验和中间特征,因此具有有限的概括性.
  • 跨模式细分的现有方法往往无法有效地捕获全球和本地信息,影响业绩.

研究的目的:

  • 提出一种新的细分模型,形状感知自适应加权 (SAWS),以提高跨模式的UDA性能.
  • 增强模型感知目标区域的能力,并捕获全球和本地信息,以便更好地细分.

主要方法:

  • 开发了一个多角度条形形状感知 (MSSP) 模块,使用角度聚合来捕获多个方向的形状特征.
  • 引入了自适应加权分层对比 (AWHC) 损失,以利用中间特征并改善小结构的细分.
  • 评估了SAWS模型在多模态全心细分 (MMWHS) 数据集上的跨模态心脏细分.

主要成果:

  • 在跨模态心脏细分任务中,SAWS模型实现了卓越的性能.
  • 对于CT→MRI,SAWS获得了70.1%的子得分和4.0的平均对称表面距离 (ASSD).
  • 对于MRI→CT,SAWS获得了83.8%的Dice分数和3.7的ASSD分数,超过了最先进的方法.
关键词:
跨模式的交叉模式.域名适应领域适应自己适应的自我适应.语义细分 语义细分是指语义细分.形状感知 形状感知

更多相关视频

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

相关实验视频

Last Updated: Jan 7, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

721
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

结论:

  • 拟议的SAWS方法有效地提高了UDA模型在跨模式医疗图像细分中的结构意识能力和概括性能.
  • 在不同的成像模式中,SAWS在细分精度和稳定性方面取得了重大进展.
  • 形状感知方法提高了模型处理医学成像中复杂解剖结构的能力.