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 16, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

735

嵌入式文本Swin-UMamba用于DeepLesion细分

Ruida Cheng1, Tejas Sudharshan Mathai2, Pritam Mukherjee2

  • 1Scientific Application Services, Center of Information Technology, NIH.

ArXiv
|October 1, 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

Characterizing facilitators and barriers to Hypoglycemic Confidence among patients with diabetes: a qualitative descriptive study.

Frontiers in psychology·2026
Same author

LCAL4-FUS cooperation switches on MMP13 and drives osteolytic bone metastasis in breast cancer.

Oncogene·2026
Same author

Heterointerface-engineered SnO<sub>2</sub>@CoFe layered double hydroxide interfacial catalysts for efficient water dissociation in bipolar membranes.

Journal of colloid and interface science·2026
Same author

A stacked ensemble model with NNLS-based weighting for influenza forecasting: a case study of Anhui Province, China.

Frontiers in public health·2026
Same author

Assessment of active and inactive sacroiliitis in axial spondyloarthritis using DCE-MRI and ZOOMit-DWI parameters: A prospective study.

Medicine·2026
Same author

Risk factors and in-hospital outcomes of acute kidney injury requiring continuous renal replacement therapy after left ventricular assist device implantation.

SAGE open medicine·2026
Same journal

Poisoning the Genome: Targeted Backdoor Attacks on DNA Foundation Models.

ArXiv·2026
Same journal

Mechanistic mathematical model of the in vitro infection dynamics of Bunyamwera and Batai viruses including MOI-dependent shortening of the eclipse phase.

ArXiv·2026
Same journal

AI-Driven Lumped-Element Modeling of Human Respiratory System for Studying Voice Mechanics.

ArXiv·2026
Same journal

Beyond Algorithms: Conceptual Innovation in Medical Imaging AI.

ArXiv·2026
Same journal

Feynman Kac Reweighted Schrödinger Bridge Matching for Surface-Based Tau PET Harmonization.

ArXiv·2026
Same journal

Agentic Discovery of Non-Canonical Antimicrobial Peptides with AMPGAN v3.

ArXiv·2026
查看所有相关文章

这项研究将大型语言模型 (LLM) 与用于病变细分的医学成像相结合. 新的Text-Swin-UMamba模型在CT扫描上显示了细分病变的更高准确性.

科学领域:

  • 医学成像分析分析 医学成像分析
  • 医疗保健中的人工智能
  • 放射学报告的解释.

背景情况:

  • 在CT扫描上损伤细分对于评估淋巴瘤等慢性疾病至关重要.
  • 将大型语言模型 (LLM) 与成像数据集成可以通过结合放射学报告细节来增强细分.
  • 目前的细分方法可能无法充分利用图像和文本数据的综合潜力.

研究的目的:

  • 调查将文本描述集成到Swin-UMamba架构中的可行性,以改善损伤细分.
  • 开发和评估一种新的Text-Swin-UMamba模型,用于结合成像特征和放射学报告信息.
  • 评估拟议模型的性能与现有的损伤细分方法相比.

主要方法:

  • 使用ULS23 DeepLesion数据集进行培训和测试.
  • 将放射学报告中的简短描述集成到Swin-UMamba架构中.
  • 开发了Text-Swin-UMamba模型用于病变细分.
  • 使用子得分和豪斯多夫距离指标比较模型的性能.

主要成果:

  • 实现了82±18%的高子得分和6.58±10.64像素的低豪斯多夫距离,用于损伤细分.
  • 文本-Swin-UMamba模型在LLM驱动的LanGuideMedSeg模型上显示了37%的改进 (p < 0.001).
关键词:
这是一个深度Lesion.全面的损伤细分 全面的损伤细分

更多相关视频

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K
Automated Analysis of C. elegans Fluorescence Images using SegElegans
06:27

Automated Analysis of C. elegans Fluorescence Images using SegElegans

Published on: October 10, 2025

593

相关实验视频

Last Updated: Jan 16, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

735
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K
Automated Analysis of C. elegans Fluorescence Images using SegElegans
06:27

Automated Analysis of C. elegans Fluorescence Images using SegElegans

Published on: October 10, 2025

593
  • 仅仅基于图像的模型的性能优于xLSTM-UNet的1.74%和nnUNet的0.22%.

    • 结论:

    • 将文本信息集成到Swin-UMamba架构中是可行的,并显著提高了损伤细分的准确性.
    • 文本-Swin-UMamba模型代表了病变细分的最先进的方法,有效地结合了图像和文本数据.
    • 开发的模型显示了通过更准确的自动化病变测量来提高慢性疾病的临床评估的前景.