DentalX: Context-Aware Dental Disease Detection with Radiographs

TL;DR

DentalX introduces a novel context-aware approach for dental disease detection in radiographs by leveraging dental anatomy segmentation to improve detection accuracy of subtle diseases.

Contribution

The paper presents DentalX, a new method that integrates structural context extraction with disease detection, enhancing performance over existing approaches.

Findings

DentalX outperforms prior methods on a dedicated benchmark.

Structural context improves detection of subtle dental diseases.

Joint training of tasks captures meaningful correlations.

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.