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

Quantifying the development of visual expertise in medical image interpretation using fractal eye-gaze metrics.

Medical & biological engineering & computing·2026

Same author

Characterizing Visual Neurosurgical Expertise in Brain MRI Visualization Using Eye-Tracking and 3D Fractal Dimension Analysis.

Journal of eye movement research·2026

Same author

Integrating microbial community dynamics into life cycle assessment: towards a microbial dimension of aquaculture sustainability.

The Science of the total environment·2026

Same author

Tumor-targeted interferon-α gene therapy for glioblastoma: a phase 1 trial.

Nature medicine·2026

Same author

Distinctive features of the tumor and immune microenvironment in glioblastoma.

NPJ precision oncology·2026

Same author

Correlation of Patient-Reported Symptoms With Rhinogram Features Beyond Simple Airway Resistance.

The Annals of otology, rhinology, and laryngology·2026

Search research articles

相关实验视频

Updated: Jul 8, 2025

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

在脑MRI中进行头骨剥离的深度学习框架.

Mehnaz Tabassum, Abdulla Al Suman, Carlo Russo

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference

|December 12, 2023

概括

使用nnUNet的新深度学习框架显著改善了用于脑MRI的自动头骨剥离,在正常和瘤受影响的大脑上表现优于现有的方法. 这一进步有助于更准确的脑部细分和分析,特别是在复杂的情况下.

科学领域:

神经图像计算器的神经图像计算
医疗图像分析医疗图像分析
放射学中的人工智能

背景情况:

除头骨对于大脑图像分析至关重要,但目前的方法与显著的形态变化作斗争,例如来自脑瘤的变化.
手动细分是耗时的,需要专门的专业知识.
当前的自动化算法在瘤靠近头骨边缘时经常失败,导致不准确的脑组织去除.

研究的目的:

开发和评估一种新的深度学习框架,用于在脑MRI中进行强大的头骨剥离.
解决当前骨剥离技术在重大脑部异常,特别是瘤的情况下的局限性.
为了比较拟议的方法与已建立的头骨剥离算法.

主要方法:

基于nnUNet架构的新型深度学习框架被开发用于自动化骨剥离.
该方法在两个公开可用的数据集上进行了评估:正常大脑的Neurofeedback Skull-stripped Repository (NFBS) 和脑瘤MRI的癌症基因组图谱 (TCGA).
性能与其他六种领先的头骨剥离方法 (BSE,ROBEX,UNet,SC-UNet,MV-UNet,3D U-Net) 相比进行了基准测试.

主要成果:

与其他六种评估方法相比,提出的基于nnUNet的方法表现优越.
在NFBS数据集上,该方法实现了高精度,子系数为0.9960,灵敏度为0.9999,特异性为0.9996.

更多相关视频

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

A MRI-Based Toolbox for Neurosurgical Planning in Nonhuman Primates

A MRI-Based Toolbox for Neurosurgical Planning in Nonhuman Primates

Published on: July 17, 2020

相关实验视频

Last Updated: Jul 8, 2025

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

A MRI-Based Toolbox for Neurosurgical Planning in Nonhuman Primates

A MRI-Based Toolbox for Neurosurgical Planning in Nonhuman Primates

Published on: July 17, 2020

在TCGA脑瘤数据集上,它产生了0.9296的Dice系数,0.9288的灵敏度,0.9866的特异性和0.9762.0的准确性.

结论:

这种新型的深度学习框架有效地进行了骨剥离,即使存在诸如瘤之类的显著脑部异常.
这种方法提供了一个更可靠,更准确的替代方法,以现有的方法预处理大脑MRI.
这些发现表明自动化神经图像分析取得了重大进展,特别是在涉及脑瘤的临床应用中.