MIND: A Noise-Adaptive Denoising Framework for Medical Images Integrating Multi-Scale Transformer

TL;DR

This paper introduces MI-ND, a noise-adaptive denoising framework for medical images that combines multi-scale convolutional and Transformer architectures with noise perception modules, significantly improving image quality and diagnostic performance.

Contribution

The paper presents a novel MI-ND model integrating noise level estimation and adaptive attention, enhancing medical image denoising beyond existing methods.

Findings

Outperforms comparative methods in PSNR, SSIM, and LPIPS.

Improves F1 score and ROC-AUC in diagnostic tasks.

Enhances structural recovery and robustness in medical images.

Abstract

The core role of medical images in disease diagnosis makes their quality directly affect the accuracy of clinical judgment. However, due to factors such as low-dose scanning, equipment limitations and imaging artifacts, medical images are often accompanied by non-uniform noise interference, which seriously affects structure recognition and lesion detection. This paper proposes a medical image adaptive denoising model (MI-ND) that integrates multi-scale convolutional and Transformer architecture, introduces a noise level estimator (NLE) and a noise adaptive attention module (NAAB), and realizes channel-spatial attention regulation and cross-modal feature fusion driven by noise perception. Systematic testing is carried out on multimodal public datasets. Experiments show that this method significantly outperforms the comparative methods in image quality indicators such as PSNR, SSIM, and LPIPS, and improves the F1 score and ROC-AUC in downstream diagnostic tasks, showing strong prac-tical value and promotional potential. The model has outstanding benefits in structural recovery, diagnostic sensitivity, and cross-modal robustness, and provides an effective solution for medical image enhancement and AI-assisted diagnosis and treatment.