NAADA: A Noise-Aware Attention Denoising Autoencoder for Dental Panoramic Radiographs

2025-06-24

AI Summary

Traditional convolutional denoising autoencoders (DAEs) for dental panoramic X-ray images suffer from insufficient recovery of high-frequency anatomical details, while existing self-attention mechanisms often overlook noise-obscured critical structures. To address this, we propose a Noise-Aware Self-Attention Mechanism (NASAM), which explicitly models noise distribution to steer attention toward salient high-frequency regions masked by noise—thereby overcoming the bias of conventional methods toward clean, low-detail areas. Integrated into a lightweight convolutional DAE architecture, NASAM enhances reconstruction fidelity of fine anatomical structures (e.g., root apices, trabecular bone) without significant parameter overhead. Experiments on public dental X-ray datasets demonstrate that our method achieves superior PSNR and SSIM compared to state-of-the-art models including Uformer and MResDNN. Moreover, qualitative evaluation confirms marked improvements in image interpretability and clinical diagnostic utility.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Safety and Robustness

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Convolutional denoising autoencoders (DAEs) are powerful tools for image restoration. However, they inherit a key limitation of convolutional neural networks (CNNs): they tend to recover low-frequency features, such as smooth regions, more effectively than high-frequency details. This leads to the loss of fine details, which is particularly problematic in dental radiographs where preserving subtle anatomical structures is crucial. While self-attention mechanisms can help mitigate this issue by emphasizing important features, conventional attention methods often prioritize features corresponding to cleaner regions and may overlook those obscured by noise. To address this limitation, we propose a noise-aware self-attention method, which allows the model to effectively focus on and recover key features even within noisy regions. Building on this approach, we introduce the noise-aware attention-enhanced denoising autoencoder (NAADA) network for enhancing noisy panoramic dental radiographs. Compared with the recent state of the art (and much heavier) methods like Uformer, MResDNN etc., our method improves the reconstruction of fine details, ensuring better image quality and diagnostic accuracy.

Problem

• Recover high-frequency details in dental radiographs
• Improve attention on noisy regions in images
• Enhance image quality for diagnostic accuracy

Innovation

• Noise-aware self-attention for feature recovery
• Enhanced denoising autoencoder for dental radiographs
• Improved reconstruction of fine anatomical details