DentalX: Context-Aware Dental Disease Detection with Radiographs

2026-01-13

AI Summary

This work addresses the challenge of limited visual cues and subtle pathological signs in dental X-rays, which hinder the performance of general-purpose object detection models. To overcome this, the authors propose a context-aware multi-task learning framework that integrates semantic segmentation of oral anatomical structures as an auxiliary task. A dedicated structural context extraction module fuses anatomical information into the primary disease detection task, effectively mitigating visual ambiguity in radiographic images. The framework enables joint optimization of both tasks within a unified architecture. Evaluated on a specialized benchmark dataset, the proposed method significantly outperforms existing approaches, achieving state-of-the-art performance in both disease detection and anatomical structure segmentation.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Structured Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Bridging structured and unstructured data
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Diagnosing dental diseases from radiographs is time-consuming and challenging due to the subtle nature of diagnostic evidence. Existing methods, which rely on object detection models designed for natural images with more distinct target patterns, struggle to detect dental diseases that present with far less visual support. To address this challenge, we propose {\bf DentalX}, a novel context-aware dental disease detection approach that leverages oral structure information to mitigate the visual ambiguity inherent in radiographs. Specifically, we introduce a structural context extraction module that learns an auxiliary task: semantic segmentation of dental anatomy. The module extracts meaningful structural context and integrates it into the primary disease detection task to enhance the detection of subtle dental diseases. Extensive experiments on a dedicated benchmark demonstrate that DentalX significantly outperforms prior methods in both tasks. This mutual benefit arises naturally during model optimization, as the correlation between the two tasks is effectively captured. Our code is available at https://github.com/zhiqin1998/DentYOLOX.

Problem

• dental disease detection
• radiographs
• visual ambiguity
• context-aware
• diagnostic evidence

Innovation

• context-aware
• dental disease detection
• structural context extraction
• semantic segmentation
• multi-task learning