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

Helping Underdeveloped Lungs with Cells (HULC-2): mesenchymal stromal cells in extreme preterm infants at risk of developing bronchopulmonary dysplasia - a study protocol of a phase 2 multicentre double blind randomised controlled trial in Canada.

BMJ open·2026

Same author

Endothelial Activation and Stress Index in Different Types of Hypertensive Pregnancy Disorders.

Journal of the American Heart Association·2026

Same author

Repeated versus selective tactile stimulation for preterm infants at birth: protocol and statistical analysis plan for a stepped-wedge cluster randomised controlled trial (NEU-stim trial).

BMJ open·2026

Same author

Evaluating multi-task network architectures for simultaneous breast lesion segmentation and classification in ultrasound images.

Medical & biological engineering & computing·2026

Same author

AIBAN-AI Bronchial Detection and Airway Navigation System.

Journal of bronchology & interventional pulmonology·2026

Same author

An autonomous bronchoscopy robot controlled by artificial intelligence (BronchoBot) outperforms experienced bronchoscopists in a simulated setting.

ERJ open research·2026

Search research articles

相关实验视频

Updated: Jun 17, 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

深度DM:使用有限数据进行3D图像分割的深度驱动可变形模型.

Helena R Torres, Bruno Oliveira, Anne Fritze

IEEE journal of biomedical and health informatics

|August 7, 2024

概括

此摘要是机器生成的。

深度DM是一种新的框架,通过将学习的能量函数与可变形模型集成,通过使用有限的数据来增强3D医疗图像细分. 这种方法不像深度学习 (DL) 方法那样依赖数据,通过更少的培训样本提高了细分精度.

更多相关视频

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

相关实验视频

Last Updated: Jun 17, 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

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

科学领域:

医疗成像医学成像
计算机视觉计算机视觉
机器学习机器学习

背景情况:

医学图像细分对于诊断和治疗计划等临床任务至关重要.
深度学习 (DL) 方法是最先进的,但需要大量的注释数据集,这些数据集在临床实践中往往很少,特别是在3D图像中.

研究的目的:

提出Deep-DM,一个以学习为导向的可变形模型框架,用于3D医学图像细分.
为了应对医疗图像细分方面的有限培训数据的挑战.

主要方法:

一个卷积神经网络 (CNN) 学习了一个集成到明确可变形模型中的能量函数.
能量函数是从在不断变化的表面周围的局部解剖图像表示中代地检索出来的.
这侧重于感兴趣的区域,排除了无关的信息来帮助学习过程.

主要成果:

深度DM框架在各种3D医学图像细分任务 (左心室,胎儿头部,左心室,膀) 和模式 (超声波,MRI,CT) 中展示了可行性.
该方法显示,与最先进的DL方法相比,培训数据集大小的依赖性减少了.
当有限的训练样本可用时,深度DM的表现优于DL方法.

结论:

深度DM提供了一种强大且数据效率高的方法,用于在3D医学图像中对解剖结构进行细分.
该方法有可能显著提高依赖于精确图像细分的临床任务.