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

TL;DR

SharpXR is a novel structure-aware denoising method for pediatric chest X-rays that effectively reduces noise from low-dose imaging while preserving critical diagnostic details, improving classification accuracy in resource-limited settings.

Contribution

Introduces SharpXR, a dual-decoder U-Net with structure-aware features and adaptive fusion, tailored for denoising pediatric X-rays with limited training data.

Findings

Outperforms existing denoising methods across multiple metrics.

Enhances pneumonia classification accuracy from 88.8% to 92.5%.

Maintains computational efficiency suitable for low-resource environments.

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.