PerioDet: Large-Scale Panoramic Radiograph Benchmark for Clinical-Oriented Apical Periodontitis Detection

2025-07-25

AI Summary

Automated diagnosis of periapical periodontitis is hindered by the scarcity of large-scale, high-quality annotated datasets. To address this, we introduce PerioXrays—the first large-scale panoramic radiograph dataset specifically designed for this task—comprising 3,673 images with 5,662 fine-grained lesion annotations. We further propose PerioDet, a clinically oriented detection framework featuring two key innovations: (1) Background Denoising Attention (BDA), which suppresses complex anatomical background interference prevalent in dental radiographs, and (2) IoU-Dynamic Calibration (IDC), which enhances localization accuracy for small lesions. On PerioXrays, PerioDet significantly outperforms state-of-the-art object detectors in both detection accuracy and robustness. A human–AI collaborative study confirms its clinical utility in assisting radiographic interpretation. This work establishes a benchmark dataset and delivers an interpretable, end-to-end solution achieving high diagnostic precision for periapical periodontitis.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Computer Vision: Interpretability, Explainability, and Transparency
• Natural Language Processing: Information Extraction

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Apical periodontitis is a prevalent oral pathology that presents significant public health challenges. Despite advances in automated diagnostic systems across various medical fields, the development of Computer-Aided Diagnosis (CAD) applications for apical periodontitis is still constrained by the lack of a large-scale, high-quality annotated dataset. To address this issue, we release a large-scale panoramic radiograph benchmark called "PerioXrays", comprising 3,673 images and 5,662 meticulously annotated instances of apical periodontitis. To the best of our knowledge, this is the first benchmark dataset for automated apical periodontitis diagnosis. This paper further proposes a clinical-oriented apical periodontitis detection (PerioDet) paradigm, which jointly incorporates Background-Denoising Attention (BDA) and IoU-Dynamic Calibration (IDC) mechanisms to address the challenges posed by background noise and small targets in automated detection. Extensive experiments on the PerioXrays dataset demonstrate the superiority of PerioDet in advancing automated apical periodontitis detection. Additionally, a well-designed human-computer collaborative experiment underscores the clinical applicability of our method as an auxiliary diagnostic tool for professional dentists.

Problem

• Lack of large-scale annotated dataset for apical periodontitis detection
• Challenges from background noise and small targets in detection
• Need for clinical-oriented automated diagnostic tools for dentists

Innovation

• Large-scale annotated dataset PerioXrays for diagnosis
• BDA and IDC mechanisms for noise and small targets
• Human-computer collaboration for clinical applicability