Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Evidence for early, clinically silent medial temporal lobe inflammation after CAR-T cell therapy.

European journal of cancer (Oxford, England : 1990)·2026

Same author

Hundreds of cardiac MRI traits derived using 3D diffusion autoencoders share a common genetic architecture.

Nature communications·2026

Same author

Individualized phenotyping of functional amyotrophic lateral sclerosis pathology in sensorimotor cortex.

Brain communications·2026

Same author

Phase-constrained zero-shot self-supervised learning for BLADE liver MRI reconstruction.

Magma (New York, N.Y.)·2026

Same author

Assessing a Stimulator Modification for Simultaneous Noninvasive Auricular Vagus Nerve Stimulation and MRI.

Journal of neuroimaging : official journal of the American Society of Neuroimaging·2025

Same author

Evaluating T1/T2 Relaxometry with OCRA Tabletop MRI System in Fresh Clinical Samples: Preliminary Insights into ZEB1-Associated Tissue Characteristics.

Technology in cancer research & treatment·2025

Search research articles

相关实验视频

Updated: Jul 21, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

MICDIR:使用UNetMSS进行多尺度反向一致的可变形图像注册,具有自建图形隐藏图形.

Soumick Chatterjee¹, Himanshi Bajaj², Istiyak H Siddiquee²

¹Faculty of Computer Science, Otto von Guericke University Magdeburg, Germany; Data and Knowledge Engineering Group, Otto von Guericke University Magdeburg, Germany; Biomedical Magnetic Resonance, Otto von Guericke University Magdeburg, Germany; Genomics Research Centre, Human Technopole, Milan, Italy.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society

|July 28, 2023

概括

这项研究引入了医疗图像注册的增强深度学习模型,提高了跟踪大小变形的准确性. 这种新方法在脑MRI数据集上的VoxelMorph等现有技术的表现显著超过了现有技术.

关键词:

深度学习是一种深度学习.可变形图像的注册方式图表潜伏的时间图像的注册图像的注册

更多相关视频

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

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

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

Published on: September 25, 2019

相关实验视频

Last Updated: Jul 21, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

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

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

Published on: September 25, 2019

科学领域:

医疗成像医学成像
计算机视觉计算机视觉
人工智能的人工智能

背景情况:

图像注册将各种图像对齐成一个统一的坐标系统,这对于医学成像分析至关重要.
像VoxelMorph这样的当前深度学习方法在细微的变形方面表现出色,但由于缺乏全球依赖编码,与大型解剖变化作斗争.

研究的目的:

为医疗图像注册开发先进的深度学习模型,能够准确地处理小和大变形.
通过整合全球解剖学背景来提高图像注册模型的稳定性和通用性.

主要方法:

该研究扩展了Voxelmorph的方法,通过整合一个多层次的UNet来进行解决方案特定的监督.
自建图形网络 (SCGNet) 被用作潜伏组件来捕捉复杂的结构相关性.
使用循环一致性损失来确保反向一致的变形.

主要成果:

拟议的方法在脑MRI注册任务中比ANT和VoxelMorph显著改善.
获得了0.8013 ± 0.0243 (内部) 和0.6211 ± 0.0309 (间) 的子得分,超过了VoxelMorph的得分.

结论:

这种新方法有效地解决了现有方法在处理大变形时的局限性.
多级监督,图形网络和循环一致性的整合提高了医疗成像应用的注册准确性和稳定性.