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

Dynamic multimodal radiomic model for survival prediction in cervical cancer: a multi-cohort study.

NPJ precision oncology·2026

Same author

Exploring the dominant endophytic pleosporalean fungi in <i>Poaceae</i> plants: taxonomic novelties within the suborder <i>Massarineae</i>.

Mycology·2026

Same author

A versatile method for accurately predicting electronic absorption spectra of tetrapyrrole macrocycles.

Scientific reports·2026

Same author

Dual-Track Genome Evolution in <i>Curvularia muehlenbeckiae</i> Suggests Host Jump to Pecan via Putative Mini-Chromosome Acquisition and Zn<sub>2</sub>Cys<sub>6</sub>-Centric Co-adaptation.

Plant disease·2026

Same author

First Tetraploa Genome and Multi-Omics Analysis Reveal Key Plant-Microbe-Soil Interactions for Salt Tolerance and Yield Improvement of Wheat.

Plant biotechnology journal·2026

Same author

Author Correction: Multimodal deep learning model for prognostic prediction in cervical cancer receiving definitive radiotherapy: a multi-center study.

NPJ digital medicine·2025

Search research articles

相关实验视频

Updated: Jul 13, 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

一种基于统计变形模型的数据增强方法,用于体积医学图像分割.

Wenfeng He¹, Chulong Zhang², Jingjing Dai²

¹Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China; School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China.

Medical image analysis

|October 14, 2023

概括

一个新的统计变形模型增强了用于放射治疗计划的医疗图像细分. 这种方法提高了风险器官划分的准确性,即使患者数据有限.

关键词:

数据增强的数据增强.深度学习 (Deep Learning) 是一种深度学习.可变形图像注册变形图像注册医疗图像细分医疗图像细分

更多相关视频

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

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

相关实验视频

Last Updated: Jul 13, 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

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

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

科学领域:

辐射疗法辐射疗法
医疗成像医学成像
人工智能的人工智能

背景情况:

精确划分有风险的器官 (OAR) 对于放射治疗计划至关重要,以尽量减少对健康组织的损伤.
在CT图像中手动OAR轮是耗时的,容易出错的,对于低对比度组织来说具有挑战性.
深度学习方法需要大量的注释数据集,这些数据集很难和昂贵地获取.

研究的目的:

引入基于统计变形模型的数据增强方法,用于体积医学图像细分.
为了提高放射治疗中自动化OAR细分的准确性和效率.
为了应对有限的注释医学成像数据的挑战.

主要方法:

开发了一个统计变形模型,用于体积医学图像细分中的现实数据增强.
从有限的患者队列中对CT图像进行了多样化和现实的增强.
评估了OAR分类在头部,部,胸部和腹部数据集的框架.

主要成果:

拟议的方法显著改善了全自动OAR在各种身体部位的细分.
在众多OAR细分挑战中实现了最先进的性能.
在有限的数据集上证明了数据增强技术的有效性.

结论:

基于统计变形模型的增强有效地提高了医疗图像细分性能.
这种方法克服了传统增强技术的局限性,通过产生更现实的变形.
该方法显示了改善放射治疗治疗计划和其他医学成像子领域的显著潜力,这些子领域面临着数据稀缺.