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

Multi-class segmentation of aortic branches and zones in computed tomography angiography: The AortaSeg24 challenge.

Medical image analysis·2026

Same author

Spectral super-resolution for Parkinson's voice via representation-level methods under mixed-reality acquisition.

Computer methods and programs in biomedicine·2026

Same author

Multi-structure segmentation in CBCT volumes: The ToothFairy2 challenge.

Medical image analysis·2026

Same author

Radiomics-based mapping of glioblastoma infiltration beyond contrast enhancement: diffusion-perfusion correlations and survival analysis in large public cohorts.

European journal of radiology·2026

Same author

Prospective biopsy-controlled validation of an AI model for predicting glioblastoma infiltration: Results from the SupraGlio trial.

Neuro-oncology·2026

Same author

Translating AI research into reality: summary of the 2025 voice AI Symposium and Hackathon.

Frontiers in digital health·2026

Search research articles

相关实验视频

Updated: Jun 13, 2025

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

通过大量数据增强来改进基于深度学习的自动缺陷重建:从图像注册到潜在扩散模型.

Marek Wodzinski¹, Kamil Kwarciak², Mateusz Daniol²

¹AGH University of Krakow, Department of Measurement and Electronics, Kraków, al. Mickiewicza 30, PL32059, Poland; University of Applied Sciences Western Switzerland (HES-SO Valais), Information Systems Institute, Sierre, Rue de Technopôle 3, 3960, Switzerland.

Computers in biology and medicine

|September 12, 2024

概括

此摘要是机器生成的。

这项研究通过使用先进的数据增强,包括潜在扩散模型,增强了个性化的头骨植入物建模. 结果显示,改进了准确性和成功重建现实世界缺陷,降低了患者的成本和等待时间.

关键词:

人工智能的人工智能是人工智能.头骨缺陷头骨缺陷头骨缺陷部植入物可以在部植入.数据增强数据增强深度学习是一种深度学习.扩散模型的扩散模型.生成性网络生成性网络图像的注册图像的注册神经外科神经外科

更多相关视频

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: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

相关实验视频

Last Updated: Jun 13, 2025

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

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: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

科学领域:

医疗成像医学成像
人工智能的人工智能
生物医学工程生物医学工程

背景情况:

个性化部植入物建模对于部损伤患者至关重要.
深度学习方法提供了自动化,但在数据通用性和注释获取方面遇到了困难.
提高数据集异质性是人工智能在植入物设计中的临床应用的关键.

研究的目的:

调查各种数据增强技术对深度学习模型对个性化部植入物建模的影响.
评估生成增强策略的有效性,特别是潜在扩散模型.
证明增强模型能够在没有手册注释的情况下重建真实临床缺陷的能力.

主要方法:

扩增技术的大规模研究:几何变换,图像注册,VAE,GAN和潜在扩散模型.
在增强数据集上训练深度网络.
使用 SkullBreak 和 SkullFix 数据集上的子分数进行定量和定性评估.
生成增强策略的比较.

主要成果:

强大的数据增量显著改善了定量和定性结果.
平均子得分超过了0.94 (SkullBreak) 和0.96 (SkullFix).
使用VQ-VAE的潜在扩散模型优于其他生成方法.
合成增强网络成功重建了真实的临床缺陷.

结论:

先进的数据增强,特别是潜伏扩散模型,增强了个性化的部植入物建模.
开发的方法减少了对昂贵和耗时的注释的需求.
这项研究促进了更快,更便宜,更容易获得的个性化部植入物的创建,使部受伤患者受益.