Department of Oral Radiology, Academic Centre for Dentistry Amsterdam, Universiteit Van Amsterdam and Vrije Universiteit Amsterdam, Amsterdam, Netherlands.
Department of Biomedical Engineering and Physics, Amsterdam University Medical Center, Universiteit Van Amsterdam, Amsterdam, Netherlands.
BMC Oral Health. 2024 Oct 30;24(1):1325. doi: 10.1186/s12903-024-05076-x.
Proximal caries datasets for training artificial intelligence (AI) algorithms commonly include clinician-annotated radiographs. These conventional annotations are susceptible to observer variability, and early caries may be missed. Micro-computed tomography (CT), while not feasible in clinical applications, offers a more accurate imaging modality to support the creation of a reference-standard dataset for caries annotations. Herein, we present the Academic Center for Dentistry Amsterdam-Diagnostic Insights for Radiographic Early-caries with micro-CT (ACTA-DIRECT) dataset, which is the first dataset pairing dental radiographs and micro-CT scans to enable higher-quality annotations.
The ACTA-DIRECT dataset encompasses 179 paired micro-CT scans and radiographs of early proximal carious teeth, along with three types of annotations: conventional annotations on radiographs, micro-CT-assisted annotations on radiographs, and micro-CT annotations (reference standard). Three dentists independently annotated proximal caries on radiographs, both with and without micro-CT assistance, enabling determinations of interobserver agreement and diagnostic accuracy. To establish a reference standard, one dental radiologist annotated all caries on the related micro-CT scans.
Micro-CT support improved interobserver agreement (Cohen's Kappa), averaging 0.64 (95% confidence interval [CI]: 0.59-0.68) versus 0.46 (95% CI: 0.44-0.48) in its absence. Likewise, average sensitivity and specificity increased from 42% (95% CI: 34-51%) to 63% (95% CI: 54-71%) and from 92% (95% CI: 88-95%) to 95% (95% CI: 92-97%), respectively.
The ACTA-DIRECT dataset offers high-quality images and annotations to support AI-based early caries diagnostics for training and validation. This study underscores the benefits of incorporating micro-CT scans in lesion assessments, providing enhanced precision and reliability.
用于训练人工智能 (AI) 算法的近中龋数据集通常包括临床医生标注的射线照片。这些传统的标注容易受到观察者变异的影响，早期龋可能会被遗漏。虽然微计算机断层扫描 (CT) 在临床应用中不可行，但它提供了一种更准确的成像方式，可以支持创建龋齿标注的参考标准数据集。本文介绍了阿姆斯特丹牙科学院 - 放射学早期龋人工智能诊断（ACTA-DIRECT）数据集，这是第一个将牙科射线照片和微 CT 扫描配对的数据集，可实现更高质量的标注。
ACTA-DIRECT 数据集包含 179 对早期近中龋牙齿的微 CT 扫描和射线照片，以及三种类型的标注：射线照片上的常规标注、射线照片上的微 CT 辅助标注和微 CT 标注（参考标准）。三位牙医分别在射线照片上独立标注近中龋，包括有无微 CT 辅助，以确定观察者间的一致性和诊断准确性。为了建立参考标准，一位牙科放射科医生对所有相关微 CT 扫描上的龋病进行了标注。
微 CT 支持提高了观察者间的一致性（Cohen's Kappa），平均为 0.64（95%置信区间 [CI]：0.59-0.68），而没有微 CT 支持时为 0.46（95% CI：0.44-0.48）。同样，平均敏感性和特异性分别从 42%（95% CI：34-51%）增加到 63%（95% CI：54-71%）和从 92%（95% CI：88-95%）增加到 95%（95% CI：92-97%）。
ACTA-DIRECT 数据集提供高质量的图像和标注，以支持基于 AI 的早期龋诊断的培训和验证。本研究强调了在病变评估中纳入微 CT 扫描的益处，提供了更高的精度和可靠性。
