PatchDenoiser: Parameter-efficient multi-scale patch learning and fusion denoiser for medical images

2026-02-25

AI Summary

Medical images are often degraded by noise arising from low-dose protocols, patient motion, or hardware limitations. Conventional denoising methods tend to over-smooth fine details, while existing deep learning approaches suffer from high computational costs and insufficient preservation of anatomical structures. To address these challenges, this work proposes a lightweight, multi-scale block learning framework with spatially aware feature fusion that decomposes denoising into local texture extraction and global contextual aggregation. The proposed method achieves significant reductions in model parameters (approximately 9×) and inference energy consumption (approximately 27×), while effectively suppressing noise and preserving fine anatomical details. Notably, it generalizes across diverse scanning conditions—including slice thickness, reconstruction kernels, and Hounsfield Unit window widths—without requiring task-specific fine-tuning, and outperforms state-of-the-art CNN- and GAN-based methods in both PSNR and SSIM on the 2016 Mayo Low-Dose CT dataset.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Medical images are essential for diagnosis, treatment planning, and research, but their quality is often degraded by noise from low-dose acquisition, patient motion, or scanner limitations, affecting both clinical interpretation and downstream analysis. Traditional filtering approaches often over-smooth and lose fine anatomical details, while deep learning methods, including CNNs, GANs, and transformers, may struggle to preserve such details or require large, computationally expensive models, limiting clinical practicality. We propose PatchDenoiser, a lightweight, energy-efficient multi-scale patch-based denoising framework. It decomposes denoising into local texture extraction and global context aggregation, fused via a spatially aware patch fusion strategy. This design enables effective noise suppression while preserving fine structural and anatomical details. PatchDenoiser is ultra-lightweight, with far fewer parameters and lower computational complexity than CNN-, GAN-, and transformer-based denoisers. On the 2016 Mayo Low-Dose CT dataset, PatchDenoiser consistently outperforms state-of-the-art CNN- and GAN-based methods in PSNR and SSIM. It is robust to variations in slice thickness, reconstruction kernels, and HU windows, generalizes across scanners without fine-tuning, and reduces parameters by ~9x and energy consumption per inference by ~27x compared with conventional CNN denoisers. PatchDenoiser thus provides a practical, scalable, and computationally efficient solution for medical image denoising, balancing performance, robustness, and clinical deployability.

Problem

• medical image denoising
• noise reduction
• fine anatomical detail preservation
• computational efficiency
• clinical deployability

Innovation

• patch-based denoising
• multi-scale fusion
• parameter-efficient
• medical image denoising
• spatially aware fusion