Sparse Mixture-of-Experts for Non-Uniform Noise Reduction in MRI Images
This addresses noise reduction in MRI images for clinical diagnostics, representing a domain-specific incremental improvement.
The paper tackled the problem of non-uniform noise in MRI images, which hinders diagnostic utility, by introducing a sparse mixture-of-experts framework that outperformed state-of-the-art denoising techniques on synthetic and real-world datasets.
Magnetic Resonance Imaging (MRI) is an essential diagnostic tool in clinical settings but its utility is often hindered by noise artifacts introduced during the imaging process. Effective denoising is critical for enhancing image quality while preserving anatomical structures. However traditional denoising methods which typically assume uniform noise distributions struggle to handle the non-uniform noise commonly present in MRI images. In this paper we introduce a novel approach leveraging a sparse mixture-of-experts framework for MRI image denoising. Each expert is a specialized denoising convolutional neural network fine-tuned to target specific noise characteristics associated with different image regions. Our method demonstrates superior performance over state-of-the-art denoising techniques on both synthetic and real-world MRI datasets. Furthermore we show that it generalizes effectively to unseen datasets highlighting its robustness and adaptability.