SharpXR: Structure-Aware Denoising for Pediatric Chest X-Rays

2025-08-11

AI Summary

To address the challenge of pronounced noise in low-dose pediatric chest X-rays—which obscures critical anatomical details and hinders early diagnosis—this paper proposes a Structure-Aware Dual-Decoder U-Net. The method incorporates a Laplacian-guided edge-preserving module and a learnable fusion mechanism to adaptively balance denoising performance and structural fidelity. A Poisson–Gaussian mixed-noise modeling strategy is introduced for realistic data augmentation, while an edge-aware loss function and a lightweight architecture jointly optimize diagnostic accuracy and deployability on edge devices. Evaluated on a pediatric pneumonia X-ray dataset, the proposed approach improves post-denoising classification accuracy from 88.8% to 92.5%, outperforming state-of-the-art methods. Notably, it achieves, for the first time, simultaneous suppression of low-dose imaging noise and faithful preservation of clinically critical structures—including bronchi and pulmonary textures—thereby enhancing diagnostic reliability in resource-constrained settings.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Low Level & Physics-based Vision
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Pediatric chest X-ray imaging is essential for early diagnosis, particularly in low-resource settings where advanced imaging modalities are often inaccessible. Low-dose protocols reduce radiation exposure in children but introduce substantial noise that can obscure critical anatomical details. Conventional denoising methods often degrade fine details, compromising diagnostic accuracy. In this paper, we present SharpXR, a structure-aware dual-decoder U-Net designed to denoise low-dose pediatric X-rays while preserving diagnostically relevant features. SharpXR combines a Laplacian-guided edge-preserving decoder with a learnable fusion module that adaptively balances noise suppression and structural detail retention. To address the scarcity of paired training data, we simulate realistic Poisson-Gaussian noise on the Pediatric Pneumonia Chest X-ray dataset. SharpXR outperforms state-of-the-art baselines across all evaluation metrics while maintaining computational efficiency suitable for resource-constrained settings. SharpXR-denoised images improved downstream pneumonia classification accuracy from 88.8% to 92.5%, underscoring its diagnostic value in low-resource pediatric care.

Problem

• Denoise low-dose pediatric chest X-rays preserving critical details
• Address noise from reduced radiation in child X-ray imaging
• Improve diagnostic accuracy in resource-limited pediatric healthcare

Innovation

• Structure-aware dual-decoder U-Net for denoising
• Laplacian-guided edge-preserving decoder with fusion
• Simulated Poisson-Gaussian noise for training data