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
Concurrent Mantle Cell Lymphoma and Paraneoplastic Membranous Nephropathy.
Kidney medicine·2026
Same author
High-power single-mode master oscillator power amplifier system at 795 nm for a 128-channel SERF magnetometer.
Applied optics·2026
Same author
AI-enhanced Wrist-Hand US Image Acquisition: Development and Initial Clinical Evaluation.
Radiology·2026
Same author
Synergizing high-sugar traits and interspecific diversity: temporal dynamics and trade-offs in temperate grasslands.
Frontiers in plant science·2026
Same author
Astragaloside IV Ameliorates Allergic Rhinitis Comorbid With Asthma by Inhibiting the Antigen-Presenting Function of B Cells.
Basic & clinical pharmacology & toxicology·2026
Same author
Chirality-Induced Twisted Supramolecular Assembly Unlocks Ultrahigh Energy Density at Elevated Temperatures.
Advanced materials (Deerfield Beach, Fla.)·2026
Same journal
A Dataset with Bilingual TV Commands for Silent Speech Interfaces Using Electroencephalographic Signals.
Scientific data·2026
Same journal
BEAMSTER: Brain mEtAstases segMentation for STEreotactic Radiotherapy, A Retrospective MRI Dataset with Expert Segmentations.
Scientific data·2026
Same journal
Chromosomal-level genome assembly of Tetraponera attenuata (Hymenoptera: Formicidae).
Scientific data·2026
Same journal
High quality Chromosome-scale Genome Assembly of Phlebotomus perniciosus, a Vector of Zoonotic Leishmaniasis.
Scientific data·2026
Same journal
Characterisation Data of common pharmaceutical excipient Powders and Tablets for Formulation Development.
Scientific data·2026
Same journal
Chinese Electric Vehicle Policy Database: A Dataset of Policy Goals, Instruments, and Supply Chain Stages.
Scientific data·2026
一个用于半监督深度学习图像细分的多模式牙科数据集.
Yaqi Wang1,2, Fan Ye3, Yifei Chen4
1College of Media Engineering, Communication University of Zhejiang, Hangzhou, 310018, China.
Scientific data
|January 20, 2025
概括
研究人员开发了最大的多模式牙科成像数据集,用于半监督牙细分 (STS-Tooth). 这一数据集结合了全景X射线图像 (PXI) 和圆束计算机断层扫描 (CBCT) 来改进人工智能驱动的牙科诊断.
科学领域:
- 牙科 牙科是指牙科的专业.
- 医疗成像医学成像
- 人工智能的人工智能
背景情况:
- 牙疾病很普遍,需要先进的诊断工具.
- 全景X射线图像 (PXI) 和圆束计算机断层扫描 (CBCT) 对于牙科诊断至关重要.
- 对于牙细分的深度学习有助于识别治疗区域和病变,但缺乏足够的数据.
研究的目的:
- 为半监督牙细分 (STS-Tooth) 引入一个新的多式联络数据集.
- 为解决AI模型培训公共牙科成像数据集的稀缺问题.
主要方法:
- 开发了STS-2D-Tooth,拥有4000张PXI图像和900张口罩,按年龄分类.
- 创建了STS-3D-Tooth,拥有148,400次CBCT扫描和8,800张口罩,提供详细的3D信息.
- 结合PXI和CBCT数据,形成一个全面的多式联运数据集.
主要成果:
- 建立了第一个集成PXI和CBCT的多式联络数据集,用于牙细分.
- 创建了迄今为止最大的牙细分任务数据集.
- 为推进牙科成像中的AI提供了宝贵的资源.
结论:
- STS-Tooth数据集是半监督牙细分研究的一个重大进步.
- 这种多模式数据集将加速开发更准确的牙科诊断人工智能工具.
- 有助于改善牙科状况的本地化和治疗规划.


