基于Mamba的深度学习模型用于根尖周指数自动分类
本研究开发并验证了一种基于Mamba架构的分类模型,整合根尖周X线片与结构化临床元数据,预测完整5级PAI评分。模型在5分类中达到54.72%准确率和0.713的二次加权kappa,优于CNN和目标检测网络,年龄对性能影响最大。
要点
- Mamba模型整合X线片与临床元数据实现5级PAI分类,QWK达0.713。
- 模型性能优于基于CNN和目标检测的最新模型。
- 年龄是影响模型性能的最重要临床元数据因素。
核心结论
- 基于Mamba的模型利用完整PAI评分并整合结构化临床信息,可支持更一致的影像解读并减少检查者间变异。
研究设计与样本
- 回顾性诊断准确性研究,从单一机构收集根尖周X线片及元数据(年龄、牙位、牙号、牙弓类型),由两名牙髓病专家依据Ørstavik标准独立评分(1-5)并以共识确定参考标准,采用分层5折交叉验证。
主要发现
- 模型在5分类中达到54.72%准确率和0.713的二次加权kappa。
- 模型优于基于CNN和目标检测网络的最新模型。
- 消融分析显示年龄对模型性能影响最大。
- Grad-CAM分析显示模型高亮区域与临床有意义的根尖周区域一致。
关键数值与推荐
- PAI评分依据Ørstavik标准分为1-5级。
- 模型5分类准确率为54.72%,二次加权kappa为0.713。
临床怎么用
- 该模型有潜力作为可解释工具用于教育和临床决策支持,辅助根尖周炎的影像解读。
局限性
- 研究为单中心回顾性设计,外部泛化性需进一步验证。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
AIM: Apical periodontitis (AP) diagnosis primarily relies on periapical radiographs (PRs) and the Periapical Index (PAI) scoring system. However, existing automated approaches often simplify PAI into binary categories or ignore essential clinical metadata, limiting diagnostic performance and applicability. Such limitations hinder timely and accurate diagnosis of AP, which may complicate treatment planning by creating uncertainty about the appropriate timing and type of intervention, and ultimately challenge clinicians' ability to make consistent and informed decisions. This study aimed to develop and validate a novel Mamba-based classification model that integrates PR with structured clinical metadata to predict detailed PAI scores across the full 5-class. METHODOLOGY: In this retrospective diagnostic accuracy study, PRs and corresponding metadata-including patient age, tooth location, tooth number and arch type-were collected from a single institution. Two expert endodontists independently assigned PAI scores (1-5) based on Ørstavik's criteria, with the final reference standard set by consensus. The proposed artificial intelligence (AI) model utilized a Mamba-based state-space architecture to capture spatial dependencies and incorporate structured clinical metadata features. Training and evaluation were conducted using stratified 5-fold cross-validation. RESULTS: The model achieved 54.72% accuracy and a quadratic-weighted kappa (QWK) of 0.713 in 5-class classification, outperforming the latest models based on convolutional neural networks (CNNs) and object detection networks. Ablation analysis further supported the value of integrating patient information, showing that age was the largest impact on model performance. Gradient-weighted Class Activation Mapping (Grad-CAM) analysis for model explainability demonstrated that the model's highlighted areas were aligned with clinically meaningful periapical regions. CONCLUSIONS: The proposed model addresses limitations of prior methods by leveraging the full range of the PAI scores and incorporating structured clinical information. It has the potential to support more consistent radiographic interpretation, reduce inter-examiner variability and serve as an interpretable tool in educational and clinical decision-support.
引用
- Lee J, Park Y, Kim S, et al. Mamba-Based Deep Learning Model for Automated Periapical Index Classification Using Periapical Radiographs and Clinical Metadata. Int Endod J. 2026. PMID: 42108657. doi:10.1111/iej.70170
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。