患者级、防泄漏感知的跨中心根尖周X光片分类深度学习
Patient-Level, Leakage-Aware Deep Learning for Cross-Center Periapical Radiograph Classification
浏览论文内容
中文总结 AI 辅助
针对根尖周X光片分类缺乏患者级防泄漏基准的问题，提出DentIRO数据集上的首个患者级防泄漏分类基准，采用患者分组交叉验证比较五种迁移学习模型，DenseNet121最优，宏F1达0.9787，跨中心泛化差距小。
中文摘要 AI 辅助
龋齿和牙髓疾病是全球最常见的健康状况之一，口内根尖周X光片在其检测、治疗规划和随访中至关重要。然而，这些图像的自动化牙齿级分类缺乏可复现的基准，通常使用图像级划分进行评估，导致训练和测试之间患者泄漏，并且很少在多个诊所间进行验证。本文在DentIRO数据集上提出了首个针对单颗牙齿口内根尖周X光片的患者级、防泄漏感知分类基准，该数据集包含来自两个诊所的3,243名患者的5,300张图像，涵盖四个类别：健康、龋齿、冠修复和根管治疗。通过患者分组分层交叉验证比较了五种迁移学习模型，确保每位患者仅出现在一个折中。DenseNet121在平均宏F1分数0.9787上表现最强且最稳定，而四个ImageNet初始化的骨干网络表现相当。在固定架构上的对照比较显示，胸部X光片预训练迁移效果不如ImageNet初始化。双向跨中心验证产生了0.0077的小平均泛化差距，Grad-CAM确认预测依赖于临床有意义的牙齿区域而非采集伪影。该基准为口内根尖周X光片分类提供了严谨且可复现的基线。
英文摘要
Dental caries and endodontic disease are among the most common health conditions worldwide, and intraoral periapical radiographs are central to their detection, treatment planning, and follow-up. Automated tooth-level classification of these images, however, lacks reproducible benchmarks, is often evaluated with image-level splits that leak patients between training and test, and is rarely validated across clinics. This paper presents the first patient-level, leakage-aware classification benchmark for single-tooth intraoral periapical radiographs on the DentIRO dataset, which comprises 5,300 images from 3,243 patients across two clinics and four classes: Healthy, Caries, Crowned, and Root Canal. Five transfer-learning models are compared with patient-grouped stratified cross-validation, so that every patient remains within a single fold. DenseNet121 gave the strongest and most stable result at a mean macro-F1 of 0.9787, while the four ImageNet-initialized backbones performed comparably. A controlled comparison on a fixed architecture showed that chest-radiograph pretraining transferred less effectively than ImageNet initialization. Bidirectional cross-center validation produced a small average generalization gap of 0.0077, and Grad-CAM confirmed that predictions rely on clinically meaningful tooth regions rather than acquisition artifacts. The benchmark offers a rigorous and reproducible baseline for intraoral radiograph classification.
发表机构
- Islamic University（伊斯兰大学）
- Northwestern University（西北大学）
机构由 AI 辅助整理，请以论文原文为准。
