Deep Learning Architectures for Medical Image Denoising: A Comparative Study of CNN-DAE, CADTra, and DCMIEDNet

TL;DR

This study compares three deep learning models for MRI brain image denoising, showing their strengths at different noise levels and outperforming traditional methods, thus providing valuable benchmarks and insights.

Contribution

It offers a comprehensive evaluation of CNN-DAE, CADTra, and DCMIEDNet architectures for MRI denoising across multiple noise levels, highlighting their respective advantages.

Findings

DCMIEDNet outperforms at low noise levels with higher PSNR.

CADTra is more robust under high noise conditions.

Deep learning methods outperform wavelet-based denoising by 5-8 dB.

Abstract

Medical imaging modalities are inherently susceptible to noise contamination that degrades diagnostic utility and clinical assessment accuracy. This paper presents a comprehensive comparative evaluation of three state-of-the-art deep learning architectures for MRI brain image denoising: CNN-DAE, CADTra, and DCMIEDNet. We systematically evaluate these models across multiple Gaussian noise intensities ($\sigma = 10, 15, 25$) using the Figshare MRI Brain Dataset. Our experimental results demonstrate that DCMIEDNet achieves superior performance at lower noise levels, with PSNR values of $32.921 \pm 2.350$ dB and $30.943 \pm 2.339$ dB for $\sigma = 10$ and $15$ respectively. However, CADTra exhibits greater robustness under severe noise conditions ($\sigma = 25$), achieving the highest PSNR of $27.671 \pm 2.091$ dB. All deep learning approaches significantly outperform traditional wavelet-based methods, with improvements ranging from 5-8 dB across tested conditions. This study establishes quantitative benchmarks for medical image denoising and provides insights into architecture-specific strengths for varying noise intensities.