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

Brain Imaging01:14

Brain Imaging

258
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans),  magnetic resonance imaging (MRI),  functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
258

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

Visionary AI: Decoding Systemic Vascular Health and Hypertensive Disorders in Pregnancy Through Retinal Imaging and Artificial Intelligence.

medRxiv : the preprint server for health sciences·2025
Same author

Contrast-Invariant Self-supervised Segmentation for Quantitative Placental MRI.

Perinatal, preterm and paediatric image analysis (2025)·2025
Same author

Effects of Lung Expansion on Global and Regional Pulmonary Blood Volume in a Sheep Model of Acute Lung Injury.

Anesthesiology·2025
Same author

MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2024
Same author

MULTI-VIEW CNN FOR TOTAL LUNG VOLUME INFERENCE ON CARDIAC COMPUTED TOMOGRAPHY.

Proceedings. IEEE International Symposium on Biomedical Imaging·2024
Same author

UNSUPERVISED DOMAIN ADAPTION WITH ADVERSARIAL LEARNING (UDAA) FOR EMPHYSEMA SUBTYPING ON CARDIAC CT SCANS: THE MESA STUDY.

Proceedings. IEEE International Symposium on Biomedical Imaging·2024

相关实验视频

Updated: Jul 19, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

442

通过使用变压器来改善MRI成像的跨数据集大脑组织细分.

Vishwanatha M Rao1, Zihan Wan2, Soroush Arabshahi1

  • 1Department of Biomedical Engineering, Columbia University, New York, NY, United States.

Frontiers in neuroimaging
|August 9, 2023
PubMed
概括

这项研究引入了一种新的CNN-变压器混合网络,用于MRI扫描中强大的脑组织细分. 新模型在各种数据集中显示出卓越的通用性和可靠性,优于现有方法.

关键词:
这就是为什么MRI是MRI.大脑组织细分 脑组织细分深度学习是一种深度学习.调查调查调查调查调查调查细分化 细分化的细分化变压器变压器变压器变压器

更多相关视频

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

8.9K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.1K

相关实验视频

Last Updated: Jul 19, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

442
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

8.9K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.1K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 神经科学是一个神经科学.

背景情况:

  • 自动化脑组织细分对于MRI数据分析至关重要,但在概括方面面临挑战.
  • 现有的自动化方法,包括卷积神经网络 (CNN),经常与MRI获取的变化作斗争.
  • 显著需要强大的和可通用的大脑细分工具.

研究的目的:

  • 引入一种新的CNN-变压器混合架构,用于在3D医学成像中增强大脑组织细分.
  • 为了提高T1wMRI数据自动细分的性能和普遍性.
  • 为了解决当前的自动化细分技术在处理各种MRI采集属性的局限性.

主要方法:

  • 开发了一个新的CNN-Transformer混合架构 (TABS网络) 用于3D医疗图像细分.
  • 在各种T1wMRI数据集上评估模型的性能.
  • 在不同供应商,场强度,扫描参数和神经精神疾病的多站点数据集中验证了模型的通用性.
  • 使用测试复试扫描评估模型可靠性.

主要成果:

  • 拟议的CNN-变压器混合模型在多个T1wMRI数据集上表现出卓越的性能.
  • 严格的验证证实了该模型在多个多站点数据集中的优秀通用性.
  • 该模型在测试-重新测试扫描中表现出高可靠性,表明了强度.
  • 在通用性和可靠性方面表现优于基准方法.

结论:

  • 新的CNN-变压器混合网络为T1wMRI中大脑组织细分提供了强大的和可泛化的解决方案.
  • 这种方法显著改善了现有的自动化细分工具,解决了MRI数据变化的局限性.
  • TABS网络是大脑相关的MRI研究中定量分析的宝贵工具.