面向口腔美学修复的CBCT影像技术创新与放射组学应用前景
DOI:
CSTR:
作者:
作者单位:

1.北京大学第三医院口腔科 北京;2.北京大学第三医院口腔科 北京 100191

作者简介:

通讯作者:

中图分类号:

基金项目:


Innovations in CBCT Imaging Technology and Applications of Radiomics in Aesthetic Dental Restoration
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    锥形束计算机断层扫描(CBCT)作为口腔颌面部核心三维影像技术,凭借低辐射、高分辨率的成像优势,贯穿美学修复术前评估、术中引导与术后复查全过程。随着数字化技术与人工智能的融合应用,CBCT成像降噪、伪影去除、三维重建等技术持续迭代,突破了传统二维影像与常规CBCT定性诊断的局限。放射组学可深度挖掘CBCT影像隐性量化特征,实现口腔软硬组织的精准评估,为个性化修复方案制定、疗效预判与风险防控提供数据支撑。本文系统综述CBCT技术创新与放射组学在各类口腔美学修复中的应用现状,分析技术应用瓶颈并展望发展趋势,为精准化、个性化口腔美学修复的临床规范化推广提供理论参考。

    Abstract:

    Cone-beam computed tomography (CBCT), as a core three-dimensional imaging technique in oral and maxillofacial medicine, plays a pivotal role throughout the entire process of aesthetic restoration—including preoperative assessment, intraoperative guidance, and postoperative follow-up—thanks to its advantages of low radiation exposure and high-resolution imaging. With the integration of digital technologies and artificial intelligence, continuous advancements in CBCT image denoising, artifact reduction, and 3D reconstruction have overcome the limitations of traditional two-dimensional imaging and conventional qualitative CBCT diagnosis. Radiomics enables deep extraction of hidden quantitative features from CBCT images, facilitating precise evaluation of both soft and hard tissues in the oral cavity, thereby providing data support for personalized treatment planning, outcome prediction, and risk management. This article systematically reviews the current status of CBCT technological innovations and radiomics applications across various aesthetic dental restorations, analyzes existing technical challenges, and outlines future development trends, offering theoretical insights for the standardized clinical implementation of precise and personalized aesthetic dental care.

    参考文献
    相似文献
    引证文献
引用本文
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2026-10-09
  • 最后修改日期:2026-10-29
  • 录用日期:2026-10-29
  • 在线发布日期:
  • 出版日期:
文章二维码